an essay about water quality

Essay on Water Quality

Students are often asked to write an essay on Water Quality in their schools and colleges. And if you’re also looking for the same, we have created 100-word, 250-word, and 500-word essays on the topic.

Let’s take a look…

100 Words Essay on Water Quality

What is water quality.

Water quality tells us how clean or dirty water is. It is important because it affects the health of people, animals, and plants. Clean water is safe to drink and supports life.

Why Water Quality Matters

Good water quality is crucial for our health. Drinking dirty water can make us very sick. It also matters for fish and other water animals to live.

Things That Pollute Water

Many things can make water dirty. Chemicals from factories, waste from homes, and oil spills are big problems. These pollutants harm water quality.

Keeping Water Clean

To keep water clean, we should not throw trash or chemicals into water. Everyone can help by being careful about what goes down the drain.

250 Words Essay on Water Quality

Water quality: the foundation of life, water is the elixir of life, sustaining all living organisms on our planet. its quality directly impacts our health and well-being. good water quality ensures clean drinking water, healthy ecosystems, and thriving communities., sources of water pollution, numerous factors contribute to water pollution. industrial waste, agricultural runoff, sewage discharge, and littering are major culprits. these pollutants contaminate water sources, making them unsafe for consumption and damaging aquatic life., consequences of poor water quality, poor water quality leads to a range of health issues, including waterborne diseases like cholera, typhoid, and dysentery. contaminated water also affects aquatic ecosystems, leading to biodiversity loss and disrupting the food chain. additionally, it hinders economic activities like fishing and tourism, which rely on clean water., water treatment and conservation, to ensure access to clean water, water treatment facilities employ various methods like filtration, disinfection, and reverse osmosis. these processes remove impurities and harmful substances, making water safe for consumption. water conservation practices such as rainwater harvesting, leak detection, and efficient irrigation techniques help reduce demand and preserve water resources., individual and collective action, improving water quality requires collective efforts. as individuals, we can reduce our water footprint by taking shorter showers, fixing leaky faucets, and using water-saving appliances. additionally, supporting policies that promote water conservation, pollution control, and sustainable development is crucial. in conclusion, water quality is paramount to life on earth. by understanding the sources of pollution, its consequences, and the importance of water treatment and conservation, we can work together to protect this vital resource and ensure a healthy future for generations to come., 500 words essay on water quality.

Water is the elixir of life, an indispensable resource that sustains all living organisms on Earth. Its quality directly impacts our health, environment, and overall well-being. Understanding water quality and taking steps to preserve it are crucial for ensuring a healthy and sustainable future.

Various human activities contribute to water pollution, contaminating our precious water sources. Industrial waste, agricultural runoff, sewage discharge, and littering are major culprits. These pollutants, when released into water bodies, can cause severe damage to aquatic ecosystems and pose health risks to humans.

Effects of Water Pollution

Polluted water has numerous detrimental effects. It can cause a range of waterborne diseases, such as diarrhea, typhoid, and cholera, when consumed. Additionally, it harms aquatic life, leading to a decline in biodiversity and disruption of the food chain. Water pollution also affects the aesthetics of water bodies, making them unpleasant for recreational activities like swimming and fishing.

Importance of Water Quality

Maintaining good water quality is essential for several reasons. It ensures safe drinking water, preventing waterborne diseases and promoting public health. Healthy water bodies support thriving aquatic ecosystems, providing habitat for diverse plants and animals. Clean water is also vital for various economic activities, including agriculture, fishing, and tourism, contributing to sustainable livelihoods.

Water Quality Monitoring

Monitoring water quality is crucial for assessing its health and taking appropriate action to protect it. Regular testing for various parameters, such as pH, dissolved oxygen, and the presence of pollutants, helps identify potential problems and track water quality trends over time. This information is essential for developing effective water management and pollution control strategies.

Water Conservation and Preservation

Conserving water and preventing pollution are critical steps in maintaining water quality. Reducing water consumption, using water-efficient appliances, and fixing leaky faucets can help conserve precious water resources. Additionally, implementing pollution control measures, such as wastewater treatment plants and proper waste disposal systems, helps minimize the discharge of pollutants into water bodies.

Water quality is a fundamental aspect of our planet’s health and well-being. With increasing human activities, protecting our water resources from pollution is more crucial than ever. By understanding the sources and effects of water pollution, and implementing effective water quality monitoring and conservation measures, we can ensure a sustainable future where clean water is accessible to all.

That’s it! I hope the essay helped you.

If you’re looking for more, here are essays on other interesting topics:

Essay on Water On Earth
Essay on Water Is Essential For Life
Essay on Water For Sustainable Development

Apart from these, you can look at all the essays by clicking here .

Happy studying!

Drinking Water Quality and Human Health: An Editorial

Patrick levallois.

1 Direction de la santé environnementale et de la toxicologie, Institut national de la santé publique du Québec, QC G1V 5B3, Canada

2 Département de médecine sociale et préventive, Faculté de médecine, Université Laval, Québec, QC G1V 0A6, Canada

Cristina M. Villanueva

3 ISGlobal, 08003 Barcelona, Spain; [email protected]

4 Universitat Pompeu Fabra (UPF), 08002 Barcelona, Spain

5 Consortium for Biomedical Research in Epidemiology and Public Health (CIBERESP), Carlos III Institute of Health, 28029 Madrid, Spain

6 IMIM (Hospital del Mar Medical Research Institute), 08003 Barcelona, Spain

Drinking water quality is paramount for public health. Despite improvements in recent decades, access to good quality drinking water remains a critical issue. The World Health Organization estimates that almost 10% of the population in the world do not have access to improved drinking water sources [ 1 ], and one of the United Nations Sustainable Development Goals is to ensure universal access to water and sanitation by 2030 [ 2 ]. Among other diseases, waterborne infections cause diarrhea, which kills nearly one million people every year. Most are children under the age of five [ 1 ]. At the same time, chemical pollution is an ongoing concern, particularly in industrialized countries and increasingly in low and medium income countries (LMICs). Exposure to chemicals in drinking water may lead to a range of chronic diseases (e.g., cancer and cardiovascular disease), adverse reproductive outcomes and effects on children’s health (e.g., neurodevelopment), among other health effects [ 3 ].

Although drinking water quality is regulated and monitored in many countries, increasing knowledge leads to the need for reviewing standards and guidelines on a nearly permanent basis, both for regulated and newly identified contaminants. Drinking water standards are mostly based on animal toxicity data, and more robust epidemiologic studies with an accurate exposure assessment are rare. The current risk assessment paradigm dealing mostly with one-by-one chemicals dismisses potential synergisms or interactions from exposures to mixtures of contaminants, particularly at the low-exposure range. Thus, evidence is needed on exposure and health effects of mixtures of contaminants in drinking water [ 4 ].

In a special issue on “Drinking Water Quality and Human Health” IJERPH [ 5 ], 20 papers were recently published on different topics related to drinking water. Eight papers were on microbiological contamination, 11 papers on chemical contamination, and one on radioactivity. Five of the eight papers were on microbiology and the one on radioactivity concerned developing countries, but none on chemical quality. In fact, all the papers on chemical contamination were from industrialized countries, illustrating that microbial quality is still the priority in LMICs. However, chemical pollution from a diversity of sources may also affect these settings and research will be necessary in the future.

Concerning microbiological contamination, one paper deals with the quality of well water in Maryland, USA [ 6 ], and it confirms the frequent contamination by fecal indicators and recommends continuous monitoring of such unregulated water. Another paper did a review of Vibrio pathogens, which are an ongoing concern in rural sub-Saharan Africa [ 7 ]. Two papers focus on the importance of global primary prevention. One investigated the effectiveness of Water Safety Plans (WSP) implemented in 12 countries of the Asia-Pacific region [ 8 ]. The other evaluated the lack of intervention to improve Water, Sanitation and Hygiene (WASH) in Nigerian communities and its effect on the frequency of common childhood diseases (mainly diarrhea) in children [ 9 ]. The efficacies of two types of intervention were also presented. One was a cost-effective household treatment in a village in South Africa [ 10 ], the other a community intervention in mid-western Nepal [ 11 ]. Finally, two epidemiological studies were conducted in industrialized countries. A time-series study evaluated the association between general indicators of drinking water quality (mainly turbidity) and the occurrence of gastroenteritis in 17 urban sites in the USA and Europe. [ 12 ] The other evaluated the performance of an algorithm to predict the occurrence of waterborne disease outbreaks in France [ 13 ].

On the eleven papers on chemical contamination, three focused on the descriptive characteristics of the contamination: one on nitrite seasonality in Finland [ 14 ], the second on geogenic cation (Na, K, Mg, and Ca) stability in Denmark [ 15 ] and the third on historical variation of THM concentrations in french water networks [ 16 ]. Another paper focused on fluoride exposure assessments using biomonitoring data in the Canadian population [ 17 ]. The other papers targeted the health effects associated with drinking water contamination. An extensive up-to-date review was provided regarding the health effects of nitrate [ 18 ]. A more limited review was on heterogeneity in studies on cancer and disinfection by-products [ 19 ]. A thorough epidemiological study on adverse birth outcomes and atrazine exposure in Ohio found a small link with lower birth weight [ 20 ]. Another more geographical study, found a link between some characteristics of drinking water in Taiwan and chronic kidney diseases [ 21 ]. Finally, the other papers discuss the methods of deriving drinking water standards. One focuses on manganese in Quebec, Canada [ 22 ], another on the screening values for pharmaceuticals in drinking water, in Minnesota, USA [ 23 ]. The latter developed the methodology used in Minnesota to derive guidelines—taking the enhanced exposure of young babies to water chemicals into particular consideration [ 24 ]. Finally, the paper on radioactivity presented a description of Polonium 210 water contamination in Malaysia [ 25 ].

In conclusion, despite several constraints (e.g., time schedule, fees, etc.), co-editors were satisfied to gather 20 papers by worldwide teams on such important topics. Our small experience demonstrates the variety and importance of microbiological and chemical contamination of drinking water and their possible health effects.

Acknowledgments

Authors want to acknowledge the important work of the IJERPH staff and of numbers of anonymous reviewers.

Author Contributions

P.L. wrote a first draft of the editorial and approved the final version. C.M.V. did a critical review and added important complementary information to finalize this editorial.

This editorial work received no special funding.

Conflicts of Interest

The authors declare no conflict of interest.

Water Quality Importance Essay

Having accessibility to high-quality water is essential for the survival of humans. We all use water, not only for drinking but for other purposes such as cleaning, cooking, bathing, and so forth. We are constantly in contact with water, hence one must ensure that the water does not contain substances harmful to one’s health.

Quality of water and public health

The human body is 70% water. Water in other words is an essential component of all processes that take place within our system. Therefore, a component that is so significant must be safe, such that it does not harm one’s health.

However, this is not the case. In a lot of areas, the water available to the public is contaminated; that is it has substances that can be of great harm to public health. Health risks due to the quality of water may include Water-contact diseases, Water Borne diseases, Vector-Borne diseases, and Poisoning. (water quality and health)

Dirty water when accumulates in an area, is the start of numerous harmful diseases. This is usually what happens in slums, and the reason behind the death of many innocent people.

For instance, due to the immense increase in industrialization, most of the waste products are dumped into the seas and oceans for their convenience. This waste contains heavy metals, which can be fatal for the human body. If they make their way into the public drinking or cooking water supply, our health is immediately at great risk. Metals such as mercury and lead can destroy one’s immune system, making one vulnerable to any diseases. Metals such as arsenic and cadmium can cause human poisoning. Not only this, if these metals are dumped into the sea, and go into the bodies of the fish we eat, we too will be indirect victims of the harmful effects. Already the quantity of water available in the world is decreasing as it is, polluting it just leaves us with no options. (water quality information).

Water-Borne diseases can be fatal for human health. If our drinking water or say the water we normally go swim in, is contaminated with pathogenic organisms, we can acquire certain diseases which may include: diarrhea, malaria, polio, dengue, typhoid, and many others. These can destroy human lives, and examples can be seen in areas with low water maintenance. (Water Borne Diseases).

Water quality and quantity concerns in the US

Water quality concerns can be found all over the world. In some areas, they are on a larger scale as compared to others. In the United States, let us look at a report from 2002. In that year 695, 540 miles of rivers and streams, or 19% of the nation’s approximately 3.7 million stream miles were assessed for their quality by the state. It was identified that 45% of it was contaminated, that is not suitable for its appropriate use, 55% was suitable for usage and 5% was heavily contaminated. In 2000 99% of all fish advisories were affected by toxic substances such as mercury lead and so on. Now, whoever had those fish had been at risk, hence, stating that there are quality concerns in the US. (water quality report 2002) (water quality facts)

As far as water quantity is concerned, the United States never really faced such a serious problem. However, more recently, with the increase in industrialization and urbanization, water shortage problems in certain areas have been identified. The state has established rights given to each area regarding their quantity limits; which is a good thing. (Water Quantity and policy)

If one compares these concerns with the developing countries, one will find stark differences. Since these countries have an increasing population, their resources are limited. Not only do they have a shortage of quality water, but even the contaminated water for cleaning and reuse is scarcely available. This is mainly because of industrialization and the race to develop their industries to fit into the world market. Then again there are natural causes such and drought which unfortunately strike some areas more than others.

Works Cited

Findings. Web.

Water Borne Diseases . Web.

Water quality and health. Web.

Water quality facts. Web.

Water quality information. Web.

Water quality report 2002. Web.

Water Quantity and policy. Web.

Chicago (A-D)
Chicago (N-B)

IvyPanda. (2022, May 28). Water Quality Importance. https://ivypanda.com/essays/water-quality-importance/

"Water Quality Importance." IvyPanda , 28 May 2022, ivypanda.com/essays/water-quality-importance/.

IvyPanda . (2022) 'Water Quality Importance'. 28 May.

IvyPanda . 2022. "Water Quality Importance." May 28, 2022. https://ivypanda.com/essays/water-quality-importance/.

1. IvyPanda . "Water Quality Importance." May 28, 2022. https://ivypanda.com/essays/water-quality-importance/.

Bibliography

IvyPanda . "Water Quality Importance." May 28, 2022. https://ivypanda.com/essays/water-quality-importance/.

Lance Armstrong Gets Dumped by R. Albergotti, V. O’Connell and S. Vranica
Occupational Health and Toxicology: Mercury Poisoning
Mercury: Environmental Concerns and Economic Value
Mercury Toxicity: Description of Disease
Importance of Mercury Water Pollution Problem Solutions
Mercury Exploration and Space Missions
Mercury Storage and Packaging in Hawthorne Amy Depot
Salmonellosis and Food-Borne Poisoning
Planet Mercury and Its Exploration
Investigation of a Food Poisoning Incident
"Save the Rhino, Save the Plant" Summary
For Locusts, Overgrazed Land Is a Treat
Environmental Risk Report on Nanoparticles
Comparison Radiation Regulation Between USA and Europe
Ecology: Definition & Ecological Fallacy

Home — Essay Samples — Environment — Earth & Nature — Water Quality

Essays on Water Quality

Water quality, clean water and sanitation: review of the issue of water pollution, made-to-order essay as fast as you need it.

Each essay is customized to cater to your unique preferences

+ experts online

Steps of The Wastewater Treatment Process

Water contamination and the methods of water treatment, importance of clean water and advantages of water dispensers, monitoring of wastewater quality: a review, let us write you an essay from scratch.

450+ experts on 30 subjects ready to help
Custom essay delivered in as few as 3 hours

Soil and Water: Cornerstones of Ecosystem Health

Ecological assessment of mai pokhari wetland, water quality assessment of five southern maine beaches: comparing escherichia coli levels, heavy metal detection from drinking water of district pishin (balochistan, pakistan) by using atomic absorption spectrometry, get a personalized essay in under 3 hours.

Expert-written essays crafted with your exact needs in mind

Florida Hard Water Analysis and Filtration Report

The case of erin brockovich and the issue of water quality, the crucial importance of clean drinking water access, water and food security as an international issue, addressing the urgent issue of ocean acidification, should bottled water be banned, exploring the dynamics of water consumption, how soil and water conservation improves water quality, the impact of a poor drainage system on urban areas, relevant topics.

Biodiversity
Ocean Exploration
Mount Everest

By clicking “Check Writers’ Offers”, you agree to our terms of service and privacy policy . We’ll occasionally send you promo and account related email

No need to pay just yet!

We use cookies to personalyze your web-site experience. By continuing we’ll assume you board with our cookie policy .

Instructions Followed To The Letter
Deadlines Met At Every Stage
Unique And Plagiarism Free

Book Report Examples
Book Review Examples
Case Study Examples
Essay Examples
Research Paper Examples

Paper Writing Services Starting at $12.95/page Order Now How It Works? Support

Custom Essay
Research Paper
Book Report/Review
Admission Essay
High School Essays
College Essays
more services
Essay Types
Citation Styles
Writing Tips
How It Works
Architecture
Communications
Computer Technologies
Environmental Issues
Health and Social Care
Hospitality
Investments
Linguistics
Social Issues

In the modern world the problem of the reliable water supply is extremely important because the water resources are widely exploited and water is used in different fields of human activities. In fact, the life of human beings is impossible without water but nowadays water is used not only simply to provide people with the essential substance they consume to survive but it is also widely used in agriculture and different industries. As a result, the water, being widely used, is naturally deteriorating in quality and decreasing in quantity because the water used in agriculture and industries is often impossible to recycle or filter to make it drinkable. In such a situation, the problem of scarcity of water as the vitally important product seems to be quite real. In this respect, it is necessary to underline that the US undertake various steps to improve the current situation and one of the strategic directions in the development of the federal and state policy is the effective treatment of wastewater. Despite the exiting differences in the water supply and water quality in different states, the high level of standards is equally important in all of the states.

First of all, it should be said that the water quality is extremely important to human health. It is not a secret that the current problem of the water pollution is a serious threat to the health of the entire nation since if the existing standards were lower the national health would be under a threat. The reason is quite obvious since nowadays it is practically impossible to consume water without any artificial treatment being applied (Anon 1998). What is meant here is the fact that nowadays water cannot be used in its original form as it is taken from the nature. In stark contrast, water needs to undergo various stages of special treatment that make it really pure and prepared for the consumption by people without any harm to their health.

Nowadays, due to the development of modern technologies, water undergoes various treatment that make the water purer and closer to its natural and practically ideal consistency. However, the latter is quite difficult to achieve because of the current environmental situation since the development of industries and water pollution undermine the natural potential of the effective water treatment so that the wastewater needs to be specifically treated to avoid the further pollution of natural water (Anon 1998). At this point, it should be said that various states may have different standards concerning the quality of water but, nonetheless, these standards should guarantee the safety of water consumed by people. This means that all states need to supply water which is really safe to human health and is close to its natural consistency without any pollutants.

By the way, it should be said that the water supply is another serious problem since it is getting to be more and more difficult to provide a permanent and ample supply of water to the population. In fact, in the result of the pollution and the increasing costs of its treatment the supply of water may vary depending on states (Bartram 2005). For instance, the states with larger natural resources of water and lower level of pollution could supply more water to consumers compared to the states where the water is naturally scarce and the situation is deteriorated by the high level of the pollution of water.

As a result, the states which are in a disadvantageous position in relation to the water supply need to invest more in the effective treatment of the wastewater and the reliable supply it to consumers. At the same time, these states face a serious problem of the lack of water. In such a situation, the water supply is really a great challenge since it is necessary to provide population with water of possibly higher quality regardless the resources of water and its initial quality. However, the state with larger water resources also need to pay a particular attention to the quality of water since it is the major condition of the supply of water to consumers.

Thus, taking into consideration all above mentioned, it is possible to conclude that nowadays states are in different positions since some states have larger resources of water and have better environmental situation, while others have scarce resources of water and the level of pollution is dangerously high. Nevertheless, regardless all these factors, the states need to provide population with the sufficient amount of water which should be of a high quality in order to guarantee the national health since the low quality of water or its insufficient supply threatens to the health of people and may provoke infectious diseases. This is why the quality of water and high standards remain the major factors that unite all the states in relation to the water supply.

Works cited

Anon. (1998, Jun). Use of reclaimed water in municipal drinking-water supplies. Journal of Environmental Health. 60(10):39-41.
National Resources Defense Council (2003). Whatâs on Tap? Grading Drinking Water in U.S. Cities. Retrieved from the web on 11/16/06 at http://www.nrdc.org/water/drinking/uscities/contents.asp
Bartram, J, Lewis, K, Lentron R. et al. (2005, Feb.-Mar.). Focusing on improved water and sanitation for health. The Lancet. 365(9461): 810-812.
U.S. Environmental Protection Agency. Public Health Concerns About Infectious Diseases. In: The Use of Reclaimed Water and Sludge in Food Crop Productions. Retrieved from the Web
Cooperative Extension Service, University of North Carolina, Soil Science, Septic Systems and Their Maintenance. Retrieved from the Web at http://ces.soil.ncsu.edu/soilscience/publications/Soilfacts/AG-439-13/
East Bay Municipal Utilities District (EBMUD). Retrieved from the Web at http://www.ebmud.com/services/waterquality/plants.html
National Resources Defense Council (2003). What’s on Tap? Grading Drinking Water in U.S. Cities. Retrieved from the web on 11/16/06 at http://www.nrdc.org/water/drinking/uscities/contents.asp
Southern California Coastal Water Research Project, Characteristics of Effluents from Small Municipal Wastewater Treatment Plants in 1993. Retrieved from the Web at http://www.sccwrp.org/pubs/annrpt/93-94/art02.htm
Schiff E. Municipal Wastewater Treatment Process. Retrieved from the Web at http://members.aol.com/ErikSchiff/prelim.htm
U. S. Food and Drug Administration Center for Food Safety and Applied Nutrition (2002). Bottled Water Regulation and the FDA. Retrieved from the web at http://www.cfsan.fda.gov/~dms/botwatr.html

If you need to write an essay for college – Professay.com custom writing service is always ready to help you. We offer original custom written essays on any topic for reasonable prices.

Writing Services

Buy custom essays
Term papers
Research papers
Book reports
Book reviews
Courseworks
Assignments
Personal statements
Dissertations
Thesis papers
Research proposals
Admission essays
Case studies
Movie reviews
PowerPoint presentations
Annotated bibliographies
College essays
High school essays
University essays
Writing topics
Academic writing help
Academic papers

Popular Requests

Essay writers
Write my essay
Best essays
Student essays
Write my paper
Essays online
Term paper help
Research paper help
Essays for sale
Term paper writers
Research paper writers
College papers
Pay for essay
Do my essay
College essay help
Essays for money
Order essays
College term papers
College research papers
Non plagiarized essays
Cheap essays
Cheap papers

Custom Writing Service

Professay.com is a professional writing service. We are 24/7 online to help students with paper writing of all levels. We guarantee that our original custom essays are prepared specially for you and are protected from plagiarism. We do our best to provide you with high quality writing help.

2Checkout.com is an authorized retailer for Professay.com

Disclaimer: Services provided by Professay.com are meant for research purposes and should be used with proper reference.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

View all journals
My Account Login
Explore content
About the journal
Publish with us
Sign up for alerts
Open access
Published: 29 March 2024

Reliable water quality prediction and parametric analysis using explainable AI models

M. K. Nallakaruppan 1 ,
E. Gangadevi 2 ,
M. Lawanya Shri 1 ,
Balamurugan Balusamy 3 ,
Sweta Bhattacharya 1 &
Shitharth Selvarajan 4 , 5

Scientific Reports volume 14 , Article number: 7520 ( 2024 ) Cite this article

479 Accesses

Metrics details

Electrical and electronic engineering
Engineering

The consumption of water constitutes the physical health of most of the living species and hence management of its purity and quality is extremely essential as contaminated water has to potential to create adverse health and environmental consequences. This creates the dire necessity to measure, control and monitor the quality of water. The primary contaminant present in water is Total Dissolved Solids (TDS), which is hard to filter out. There are various substances apart from mere solids such as potassium, sodium, chlorides, lead, nitrate, cadmium, arsenic and other pollutants. The proposed work aims to provide the automation of water quality estimation through Artificial Intelligence and uses Explainable Artificial Intelligence (XAI) for the explanation of the most significant parameters contributing towards the potability of water and the estimation of the impurities. XAI has the transparency and justifiability as a white-box model since the Machine Learning (ML) model is black-box and unable to describe the reasoning behind the ML classification. The proposed work uses various ML models such as Logistic Regression, Support Vector Machine (SVM), Gaussian Naive Bayes, Decision Tree (DT) and Random Forest (RF) to classify whether the water is drinkable. The various representations of XAI such as force plot, test patch, summary plot, dependency plot and decision plot generated in SHAPELY explainer explain the significant features, prediction score, feature importance and justification behind the water quality estimation. The RF classifier is selected for the explanation and yields optimum Accuracy and F1-Score of 0.9999, with Precision and Re-call of 0.9997 and 0.998 respectively. Thus, the work is an exploratory analysis of the estimation and management of water quality with indicators associated with their significance. This work is an emerging research at present with a vision of addressing the water quality for the future as well.

A proficiency assessment of integrating machine learning (ML) schemes on Lahore water ensemble

Nazish Shahid

Source discrimination of mine water based on the random forest method

Zhenwei Yang, Hang Lv, … Xinyi Wang

Computational assessment of groundwater salinity distribution within coastal multi-aquifers of Bangladesh

Mehdi Jamei, Masoud Karbasi, … Zaher Mundher Yaseen

Introduction

The major part of our earth comprises water and it is extremely important for the survival of all humans and animal species. Water makes up over 326 cubic metres of the planet’s surface, which is almost 71% of its total area out of which 97% is seawater. Only 0.5 percentage of the drinkable water on earth is accessible, while the remaining 2.5 percentage is either trapped in glaciers, polar ice caps, the atmosphere, on soil, is polluted, or lies beneath the earth’s surface far beyond human reach. If the global water supply is 100 L, consequently the amount of drinking water would be only 0.003 L, which is just a teaspoon. Therefore, the management and preservation of drinking water is regarded as a top priority. It is the most critical issue for mankind to address given the extremely limited amount of water that is accessible for use. The quantum of water around the world is represented in Table 1 .

Water is a common and crucial resource shared among all humans, animals, and plants and is a necessity for all species. Each one of these species has its own respective needs for water quality. Total Dissolvable Solids (TDS) of soft water for human consumption range from the best quality stated, which is between 50 mg/dL and 150 mg/dL. Between 150 mg/dL and 300 mg/dL is the next level that can be applied to humans. The plants need water that is between 700mg/dL and 800mg/dL. The animals, especially cattle consume water around the quality of 1000 mg/dL. It is thus evident from all these observations that water quality management is essential to ensure sustainability and a healthy life on Earth. The impact of water quality prediction is crucial at a global level for many reasons. First of all, to get clean and safe water is a basic human necessity and water quality prediction aids to guarantee the availability of potable water for societies worldwide. Water quality is related to public health as polluted water may cause waterborne diseases which could affect millions of humans globally. A sustainable environment is an important aspect of human well-being by preserving ecosystems and biodiversity. The significance of water quality assessment is profound and intricate by various organizations globally. The WHO (World Health Organization) , UNEP (United Nations Environment Programme), EPA (United States Environmental Protection Agency), EEA (European Environment Agency), IWA (International Water Association) and WEF (Water Environment Federation) are fanatical for water quality assessment and addressing the mitigation strategies for water quality challenges. Water quality creates impact on public health globally and resulting in dissemination of waterborne diseases like typhoid, dysentery, cholera, dengue and malaria and cause substantial risks worldwide.

The advancement in computing technologies and artificial intelligence have elevated the standards of water quality assessments 1 . Measurements and estimations about the quality of the water have become easier to calculate and accurate, especially with the development of Industry 4.0 standards and Internet of Things (IoT) sensors. With the integration of IoT sensors, AI solely serves as a supporting tool to automate water quality checks 2 . Classification and Regression models based on machine learning help in determining the water quality. Depending on the outcomes, classification results tend to be binary or multi-classified. Real-time sensor data are collected, given feature labels, and then classified based on the importance of the feature labels. Earlier, these measurements used to be carried out with fuzzy-based decision support systems 3 with subjective decision-making models. AI development has made it possible to classify and analyse quality aspects quantitatively. The accuracy of the water quality assessment has been validated using various performance metrics like accuracy, precision, recall, and f1-score. AI models also support such quantitative analysis, classification of water sources, and prediction of drinkable water as well as identifying the mixing of bouyant pollutants in water sources 4 .

Despite its success in automating tasks and making water quality predictions using diverse models, the AI models lack transparency and are considered black-box where the decisions are derived but the reasoning behind such decisions is not revealed. The present generation validation frameworks for water quality management need justifiability, transparency and explainability, which is possible to be rendered by Explainable AI (XAI) based systems. XAI is a technology that is white-box and answers the uncertainty related to the classification and regression problems of AI. XAI applies a model-agnostic approach, where the machine learning models can be treated independently for interpretation. Additionally, XAI discusses how the model is chosen, how it works, and how it performs categorization. Through the assessment of a problem’s feature weights, XAI also can determine a feature’s relevance. This clarifies how a feature value relates to a certain target class classification. As an example, XAI uses models like Partial Dependency Plots (PDP) 5 , which describes the relationship between the features using lasso functions. This model may identify the linear relationship between two characteristics of water quality data and explain their correlation. In XAI, models like Local Interpretable Model agnostic Explainer(LIME), explain the relationship between a single feature and relevant others in local surrogacy. This infers that, except for the one-row value of the dataset, it is possible to relate a target attribute to the other independent variables. LIME in this regard can be used to explain the target classification for a single row instance about the water quality 6 . In the proposed work, XAI, which employs both local and global surrogates, includes SHAPELY. The model offers a solution that takes into account the importance of each feature in determining the target as well as the dependency between features, the relationship between features, and the explanation of decisions through a variety of plots, including force plots, summary plots, dependency plots, and decision plots. The framework is very adaptable and capable of giving a thorough explanation of the characteristics of the water quality and how they affect the classification of the water quality.

Advantages of the proposed model

Explainable AI plays an important role in improving the interpretability of predictions made by machine learning models. More transparent predictions are generated by these models. In the proposed approach, the authors have employed LIME and SHAP to interpret predictions achieved from machine learning, which identifies inputs as an important metric for selecting the features. By applying the XAI approach, the proposed model provides deep insights into the features and allows informed decision-making in water management processes.

Contributions of the paper

The following points describe the contribution of the proposed work.

The proposed work offers a comprehensive analysis and white-box description of the classification problem for water quality.

The framework incorporates extensive pre-processing of the dataset to ensure it fit to be fed into the XAI model.

Imputation of missing data is carried out to increase the accuracy of the findings.

The proposed work ensures achievement of most significant features, identification of the feature importance, feature dependencies, and feature weights, that enable optimized classification of water quality dataset.

The proposed approach employs both model-based and model-agnostic interpretations, using model-based ML implementations and model-agnostic XAI implementations.

Organization of the paper

Section “ Introduction ” of the paper introduces the problem of the research paper with the description of the unique contributions. Section. Introduction ” also describes the literature review of the related problems on water quality, in related works subsection, with an exhaustive survey of the various applications and case studies pertaining to water quality management using AI and machine learning approaches. Section “ System model and architecture ” describes the methods applied in the proposed work with the implementation of the mathematical model with the algorithm of the proposed work. Section “ Results ” describes the results of various ML and XAI models with relevant tables and graphs. Section “ Discussion ” provides the comparative analysis of the results with a discussion of challenges and solutions of the proposed work. Section “ Conclusion ” concludes the paper with future directions.

Related works

Lu et al. 7 proposed the central environmental protection inspection (CEPI), which was implemented and the causes of transboundary water contamination were investigated. The triple difference technique (DDD) was used to assess how the CEPI affected pollution and the results to determine how significantly water pollution was decreased as well as the significance of CEPI laws for addressing transboundary pollution. Halder et al. 8 , the Turag River’s neighbouring communities are suffering from major health problems as a result of water contamination. For the sustainability of household and aquatic life, the river’s water quality was unsuitable. The study noted that the threshold values for turbidity, total dissolved solids (TDS), chloride (CL-), chemical oxygen demand (COD), carbon dioxide (CO2), and biochemical oxygen demand (BOD) are higher than the standard permissible limits, which may result in health problems like respiratory illnesses, diarrhoea, cholera, dengue, malaria, anaemia, and skin problems. A study evaluating metal pollution management and mitigation tactics on soil and water was presented by Wang et al. 9 . In this study, the remediation of metal contamination from water and soil utilising chemical, physical, and biological approaches was discussed. In this study, the current methods for reducing heavy metal pollution of the soil and water are examined. Elehinafe et al. 10 discussed the importance of water contamination and examined the main cause of water scarcity. The proposed work discussed the effect of hazardous chemicals on the water, including pesticides, heavy metals, and micro-pollutants. This study outlined the numerous technologies that are currently available to eliminate hazardous materials and provide sustainable clean water resources. Mu et al. 11 proposed a solution for the investigation into farmers’ readiness to implement Rural Water Pollution Control (RWPC). This study examines farmers’ viewpoints to improve the quality of life for locals who reside in rural regions and avoid water contamination. To analyse the contributions of contaminants, Wang et al. 12 developed a unique contaminant flux variable model for river water quality assessment. The framework effectively identified the sources of pollution and evaluated the efficacy of projects designed to reduce water pollution. Zadeh et al. 13 proposed WQPs for estimating chemical oxygen demand and biochemical oxygen demand using the MKSVR algorithm. PSO algorithm is used for solving optimization problems. The multiple kernel support vector regression (MKSVR) is compared with SVR and Random Forest Regression and achieves a better accuracy level for BOD prediction. Nagaf et al. 14 presented a framework for assessing the WQI values based on the NSF guidelines. This framework uses four data-driven models such as EPR, M5 MT, GEP and MARS for predicting WQI values in the Karun River. The classification uses 12 water quality parameters and missing values were extracted from the image analysis. Zadeh et al. 15 proposed a model that utilizes gene expression programming, evolutionary polynomial regression, and model trees for predicting WQPs. The biochemical oxygen demand, dissolved oxygen and chemical oxygen demand are used for estimation with nine parameters. The gamma test is used for determining important parameters. Najaf et al. 16 proposed a water quality predicting framework for estimating the water quality index in the Hudson River based on Canadian Council of Ministers of the Environment (CCME) guidelines. The four artificial intelligence techniques M5 MT, Multivariate Adaptive Regression Spline, Evolutionary Polynomial Regression and Gene Expression Programming are used with Landsat 8 OLI-TIRS images. The results proved that the MARS technique achieved the best outcome compared to other models.

Chowdhury et al. 17 emphasized the sources of water contamination which are caused by densely populated industrial areas that are located close to water bodies. The main causes of water contamination are dangerous chemicals and heavy metals. Farmers’ pre-owned pesticides, including different types of carbamate and organophosphorus pesticides, are the main causes of water contamination on agricultural grounds as per the study. Ahivar et al. 18 examined the use of heavy metal pollution indices (HPIs) in soil, water, and sediments. For assessing metal contamination, HPI is considered a crucial instrument. Each method’s pollution index is assessed to interpret the pollution levels. The selection of HPIs based on the parameters and standards for evaluating the quality of the water and soil is offered. Chen et al. 19 presented a study by used various mathematical and statistical approaches to check the quality of water. The factors indicating the water pollution and the seasonal characteristics are evaluated to reduce the river water pollution. The Principal Component Analysis, Cluster Analysis, Network Analysis and Co-Occurrence Analysis were carried out to find the potential source of river water pollution. Fan et al. 20 examined the quality of water using several mathematical and statistical techniques. To lessen river water pollution, the variables implicating contamination and the seasonal traits are assessed. To identify a likely cause of river water pollution, the Principal Component Analysis, Cluster Analysis, Network Analysis, and Co-Occurrence Analysis were performed. Wang et al. 21 formulated the performance indices for explaining the Water-Energy-Pollution nexus (InWEP) effects of scales. The Nexus Pressure Index (NPI) and Nexus Coupling Index (NCI) were used to represent the pollution pressure and the interacted relations. The factors for InWEP were analysed using the Structural Equation Model (SEM) considering four objects namely enterprises, countries, industrial zones and cities. The performance of InWEP was evaluated for the performance metrics - efficiency, structure and location. To evaluate the quality of groundwater surrounding nearby areas in an industrial metropolis, Asomaku 22 evaluated the water pollution indices. Nine samples from three landfills are used in the analysis of the groundwater’s chemical and metal characteristics. The study in Balaram et al. 23 explored many elements that have an impact on water quality, including climate change, industry, aquaculture, mining, and agriculture. For the quantitative and qualitative evaluation of hazardous metals, metal species, isotopes, and other contaminants that are present in water, various ICP-MS techniques are applied. Yuan et al. 24 proposed a water quality monitoring framework using biological sensors for water quality assessment. Borzooei et al. 25 presented a study to estimate the frequency weather events that creates impact on waste water assessment. The Time series data mining approach is used for categorizing the dry and wet weather events. Noori et al. 26 presented a report on decline of groundwater recharge in Iran. The study presents the average amount of ground water recharge is more than the annual runoff 4 utilized WCSPH (A weakly compressible smoothed particle hydrodynamics) model for simulating the near-shore hydrodynamics. The study conducted experimental and numerical evaluation for detecting the causes for mixing the buoyant pollutants in coastal water source. Yeganeh-Bakhtiar 27 presented a framework using MOS (Model Output Statistics) for establishing the statistical relationships among predicator and predicant.

When evaluating water quality using factors like toxicity and pollutants, computer vision and biological sensor systems are utilised in tandem. To retrieve the important data from images taken by a microscope, a microfluidic chip with sensors is utilised. This chip monitors water samples. Figure 1 describes various factors causing water pollution in smart cities including construction activities, atmospheric deposition, natural factors, municipal wastewater, stormwater runoff, incorrect waste disposal, industrial discharges, agricultural runoff, and municipal wastewater. Jeihouni et al. 28 implemented and compared five data mining techniques, including the Ordinary Decision Tree (ODT), Random Forest (RF), Chi-square Automatic Interaction Detector (CHAID), Iterative Dichotomiser 3 (ID3), and Random tree, to identify high-quality water zones. Eight parameters are used in the evaluation process while deriving rules. Compared to the remaining models, the RF performed well, with an accuracy rate of 97.10%. Lee et al. 29 implemented a framework for evaluating the quality of groundwater utilising a Self-Organizing Map (SOM) technique and fuzzy c-means clustering (FCM) was given. The two methods are employed to describe the complex nature of groundwater. SOM employed 91 neurons to categorise 343 groundwater samples, and FCM grouped the water sources into three groups. Agarwal et al. 30 proposed AI based water evaluating technique to predict the water quality index using Particle Swarm Optimization (PSO), Naïve Bayes Classifier (NBC), and Support vector machine (SVM). PSO was used in this regard for optimizing the classifiers wherein the PSO-optimized NBC obtained 92.8% accuracy and PSO-optimized SVM obtained 77.60% accuracy. Table 3 illustrates various existing state-of-art techniques proposed for assessing water quality, its advantages and research gaps.

Figure 1 illustrates the factors causing water pollution. The factors includes Industrial discharges, agricultural runoff, municipal waste water, storm water, improper waste disposal, oil spills and chemical spills, construction wastages, and atmospheric deposition. The factors are very crucial to protect public health and ecosystem , sustainability development, creating public awareness and for pollution prevention.

Factors causing water pollution.

Figure 2 depicts the required physical parameters such as Temperature, Turbidity, Conductivity, Odour and Color represented in percentage, for evaluating the quality of water. Examining the physical parameters is essential for identifying the potential hazards that leads to poor water quality and for preventing ecosystem health.

Physical Parameters.

Figure 3 depicts the necessary chemical parameters, such as pH, Dissolved Oxygen (DO), Total Dissolved Solids (TDS), Nutrients (nitrogen and phosphorus), Total Suspended Solids (TSS), Heavy Metals, and Organic Matter (OM), as well as Chemical Oxygen Demand (COD) and Biochemical Oxygen Demand (BOD) with percentages, that must be measured in order to assess the water’s quality.

Chemical parameters.

Figure 4 presents various supervised learning models for estimating water quality, including Random Forest, Support Vector Machine (SVM), Decision Trees, Neural Networks, and Gradient Boosting Approaches like XGBoost and AdaBoost.

Supervised learning models.

Figure 5 represents various unsupervised learning models such as Principal Component Analysis, Cluster Analysis and Self-Organizing Maps (SOM) for addressing the quality of the water. PCA is a dimensionality reduction approach mainly utilized for analyzing the high dimensional datasets. Cluster analysis techniques are used primarily for grouping water samples based on similarities. SOM technique is principally used for organizing the water quality data.

Unsupervised learning models.

Figure 6 highlights the various Hybrid ML models such as ensemble models with Reinforcement Learning (RL) for addressing the evaluation of quality of water. The various machine learning models can be verified based on the applications, parameters in order to determine the quality of the water, dataset size and its quality based on the assessment of the performance metrics.

Hybrid ML models.

The motivation for the proposed research, along with the research gap analysis with similar existing research works is discussed as per Table 2 . The comparative analysis and research of similar existing works are presented in Table 3 . These two discussions provide a comprehensive understanding of the requirements, that are essentially required in the design of the proposed system and implementation.

Table 3 refers to similar literature review of various models of machine learning such as DT,RF,DCF, SVM, and so on. This table also discusses about various deep learning models such as, Artificial Neural Networks (ANN), Probablistic Neural Network (PNN), Convolution Neural Networks (CNN) and statistical regression models such as Auto-Regression in Moving Average(ARIMA). This table discusses the the research gaps identified and enhanced in the proposed work. These models were mostly numerical evaluations with regression analysis. The proposed model and the system is classifier which deploys XAI framework, to discuss the impact of parameters, that determine the portability of the water with end user perspective. This is towards achieving environmental sustainability on water conservation and harvesting.

Statement of objectives

The proposed work offers a comprehensive analysis and white-box description of the classification problem for water quality . The framework incorporates extensive pre-processing of the dataset to ensure it fits into the XAI model. Imputation of missing data is carried out to increase the accuracy of the findings. The proposed work ensures the achievement of the most significant features, identification of the feature importance, feature dependencies, and feature weights, that enable optimized classification of the water quality dataset. The proposed approach employs both model-based and model-agnostic interpretations, using model-based ML. Donnelly et al. 46 implementations and model-agnostic XAI implementations. The quality of water is greatly challenged by innumerable influencing factors. These factors vary from condition to condition and place to place. For example, Microplastics (MP) are emerging pollutants in the marine environment with potential toxic effects on littoral and coastal ecosystems 47 and as well as identifying the mixing of bouyant pollutants in water sources 4 . The laboratory evaluations show the presence of polyethene (PE) particles in the waves of the ocean with wave steepness Sop of 2–5%. The transportation of which could cause severe water pollution on the seashores 48 .These measurements require quantification and feature analysis when it is evaluated with AI. This is where the XAI plays a vital role in measuring the order and degree of the pollutants causing the quantifiable pollution in the water.

Case studies

Importance of XAI in Water Quality Assessment: The following case studies delineate the advent of the potential impact of XAI, with a groundbreaking revolution in water quality assessment.

Case Study 1: Pollution of Ganges 49 This case study emphasises the Ganga River pollution issue in India, which has an extremely detrimental impact on humans and the entire ecosystem. The Ganga River is polluted by industrial, animal, and human waste. The main source of pollutants is industrial rubber waste, followed by leather and plastic manufacturers who dump their untreated wastewater into the river. The Ganga Action Plan was developed by the Indian government to combat Ganga pollution. This implies the need for the reinforcement of environmental restrictions to improve river quality.

Materials and methods

An effective policy for health protection should thus emphasize providing access to safe drinking water regardless of social and economic diversity. In some places, it is evident from previous studies that investments in access to clean water and sanitation yield economic benefits for any country. It is a significant aspect of eco-friendly health and public safety, as it regulates the appropriateness of water for numerous purposes, such as drinking, agriculture, industry, and recreational purposes. The important key indicators related to water quality are its physical, chemical, and biological characteristics and its sources of pollution. The dependent target class is potability. The other independent features are pH value, hardness, solids (Total Dissolved Solids-TDS), Chloramines, sulfate, conductivity, organic carbon, trihalomethanes, and turbidity. Water’s potability indicates its purity and safety for ingestion. The parameters used and their WHO limits, the hyper-parametric analysis are listed in Table 4 , and the feature description of parameters are listed in Table 5 .

XAI framework facilitates transparent and interpretable explanations of the outcome generated by the ML algorithm-based frameworks. XAI can thus be applied in the present context of water quality assessment to ensure accurate decision-making, thereby, enabling trustworthiness, enhancement of transparency and interpretability of the behaviour of the model.

Hydro-climatic application

XAI framework can be used to solve Hydro-Climatic problems 50 with diverse spatio-temporal scales. XAI is utilized to unveil the nonlinear correlative causes, in which the performance of the model is enhanced. It enables the users to discover new knowledge and further easily understand the rationale behind the decision outcomes.

Groundwater potential predictions

XAI approach can explain the decisions made by ML models for groundwater potential prediction. The user can easily interpret the outcomes and further comprehend the underlying for an outcome in the realm of water quality evaluation for conservation, and sustainability of water management.

Water quality predictions

XAI framework can forecast water quality using metrics and factors with interpretable results. Water quality assessment managers can comprehend the variables and parameters used for outcomes. This forces quality managers to mitigate water quality issues.

Flood hazard risk predictions

Floods can trigger landslides from excessive rainfall. Flooding causes countless casualties and property damage. Disaster warning systems need a flood risk assessment. XAI can forecast rapid water depths and provide timely, interpretable alerts to protect public health and safety.

Environmental impact assessment

XAI approach can be used for assessing the environmental impact on the water pollution incidents, and provide insight for mitigation and management. It enhances transparency and accountability by providing insights into the factors and parameters influencing environmental conditions. The analysis provided by the XAI model helps the stakeholders to identify the most significant factors contributing towards the environmental outcome.

System model and architecture

System model.

Worldwide, numerous water bodies are contaminated by a variety of anthropogenic and natural processes, resulting in a variety of health problems for human life. Thus water quality requires rigorous monitoring and management to prevent pollution. In accordance with WHO guidelines, the polluted water must be treated using the proper water treatment techniques before consumption. The quality of water is contaminated by the incessant addition of toxic chemicals and microbes and also by the relentless addition of local and industrial sewage sludge, trash, and extra hazardous waste that are toxic to humans and society. Many uncertainties are required to be quantified for all machine learning models. The uncertainties such as selecting and gathering the training data, absolute and accurate training data, understanding the machine learning models with performance bounds and drawbacks and finally the uncertainties which are based on the operational data. To minimize the challenges, adhoc steps like studying the model variability and sensitivity analysis are applied. In current years, the validation of water quality has taken active momentum because of ever-increasing water pollutants which spoil water that is dedicated for domestic use and irrigation. Water quality indices (WQIs) are used worldwide very efficiently for the assessment of the quality of both groundwater and other relevant water sources. Machine Learning techniques play a substantial role in identifying the quality of water using explainable AI. Figure 7 depicts the overall architecture of the proposed framework of our study. The dataset used in the study is split into the ratio of 70:30 wherein 70% is used for training and 30% is used for testing. The model is trained using a decision tree, random forest, SVM, logistic regression, and Naive Bayes algorithms. XAI model is implemented in the framework wherein LIME and Shapely are used to provide explainability and interpretability to the results generated by the machine learning model .

Interfacing ML algorithms with XAI.

Decision tree

The decision tree is stated as a recursive partition of the set of all possible instances 27 51 . The goal of a decision tree is to split the data which consequences in maximum information gain 52 . Let L be a sample for learning, L= ( $v_{1}$ , $c_{1}$ ), ( $v_{2}$ , $c_{2}$ ),( $v_{i}$ , $c_{j}$ ). Here, $v_{1}$ , $v_{2}$ , $v_{3}$ , $v_{i}$ are represented for measurement vectors, and $c_{1}$ , $c_{2}$ , $c_{3}$ , $c_{j}$ are represented for class labels.The batch conditions are reliant on one of the vector variables denoted as $s_{i}$ 53 . Let us assume if the $e_{i}$ of an element fits class label $c_{i}$ , then $p_{i}$ is denoted as per the Eq. ( 1 ).

Entropy evaluates the random value from the given samples and the homogeneity of the expected rate of a group of data 54 . To divide the data most optimally, the lowest value of entropy signifies better homogeneity.

L represents the data set evaluated by the entropy, ‘i’ denotes the classes in the set L, and $e_{i}$ indicates the number of data labels that fit class ’i’ 55 . The least value of entropy is used for choosing the best feature. Information gain enumerates the amount of information provided by a particular characteristic about the target variable to minimize the uncertainty present in the data set. It is calculated by comparing the weighted average of entropy to the original data set after the splitting process. Let us assume that R is the rate for the features ‘f’, $[|{L}^R|]$ denotes the subset of LS so that bf=R 56 . After splitting L on the feature, information gain is given as follows.

The Gini index evaluates the heterogeneity of a selected node in the decision tree. It counts the probability of wrongly identifying data in the node. The Gini index begins from the value 0 to 1, where 0 indicates a pure node and 1 denotes a node that is distributed equally. The Gini index is represented as

Here, $e_{i}$ represents the quantity of data labels. When the data is divided on class d as L1 and L2 with sizes $s_{1}$ and $s_{2}$ , Gini is evaluated as

Due to its comprehensible nature, decision trees can manage both numerical and categorical data with automatic feature selection.

Random forest

Random forest is an ensemble method that groups the results of multiple decision trees to compute predictions with enhanced accuracy. Every decision tree is improved on a random subset of labels from the dataset, to achieve diversity between the trees. When the data in the training label is t, then with replacement ‘n’ data are verified as bootstrap data 57 . This is done to produce the decision tree with training data. When there are ’m’ labels, a $<<$ m is selected so that ‘a’ values are considered at random from ‘m’. The value ‘a’ is constant when the tree is growing to the highest level. The highest vote is noted as a new instance. (GE*) is the generalization error for the random forest and is denoted as

Here, f(X, Y) is a margin function to count the average number of votes from (X, Y). X denotes the prediction value and Y denotes the classification problem. The margin function is represented as

where ’F’ is for the indicator function. The value for the margin function is indicated as

The average value of a random forest and the mean correlation of the classifiers are combined as generalization errors. The p denotes the mean of the correlation. The generalization error for the upper bound is

Random forest reduces the over-fitting problem compared to a single decision tree. It can effectively manage high-dimensional data.

Support vector machine (SVM)

Let us consider a binary classification problem 1 or −1 to represent the sample variables 58 . When i elements of the sample variable is − 1, it is a positive class. When the i variables of the samples is 1, it is a negative set. Let V_i = X1, X2,...Xn, Yi, i = 1,2,...n, $Y\_{i}\in {-1,1}$ , Si indicates i item from the samples. Yi is the i item of the tests performed 59 . To split the samples into two parts, the function f(X) = ZTX+ b is used, where Z is the coefficient vector to normalize the hyperplane. The optimal margin is given as

$\underbrace{MIN}_{\begin{array}{c} w, b, \\ \varepsilon \end{array}} \left( {\frac{1}{2}}Z^{TZ}+C\sum _{i=1}^{n}\varepsilon _i\right)$

subject to:

The Lagrangian equation is given as

$\underbrace{MAX}_{\propto } \left( \sum _{i=1}^{n}{\propto _i-\frac{1}{2}}\sum _{i,j=1}^{n}{\propto _i\propto _jY_iY_jX_iX_j}\right)$

The Lagrangian equation with the maximum value with $\propto _i$ a positive multiplier for the equation $\sum _{i=1}^{n}{\propto _iY_i=0}$ and $\propto _i\ge 0$ to change the optimal hyperplane 60 is presented. The optimal equation is given as

In the above equation $\propto _i=0$ of the Lagrangian multiplier is nearest to the margin of the optimal hyperplane denoted as a support vector. This data is linearly separable by the kernel to evaluate the expected result from the instance 61 . The kernel function is denoted as

The generalized linear equation is changed to represent the non-linear dual Lagrangian $La(\alpha )$ .

$Lag\left( \propto \right) =\ \sum _{i=1}^{n}{\propto _i-\frac{1}{2}\sum _{i,j=1}^{n}{\propto _i\propto _jY_iY_jK\left( X_i,X_j\right) }}$

Subject to:

The Lagrangian equation can be used for the separable case as

The SVM algorithm is very effective when the quantity of features is higher than the number of samples 62 .

Logistic regression

Logistic regression is used for binary classification problems to forecast the probability of an occurrence matching to a particular class. If the dependent value is binary, a regression analysis is used. The idea in logistic regression(logreg) is the logarithm ‘logn’ of odds of X, and odds are the ratios of probabilities ‘pb’ of X 63 . The rate of the independent value is termed odds because logistic regression measures the probability of an act that happens over the likelihood of an occurrence that does not happen.

where p is the probability of a positive output and x is the variable. The $\alpha$ and $\beta$ , are the logistic regression parameters 64 . The above equation is used for finding the number of occurrences as

$p=probability(Y=positive\ outcome|X=x,$ a specific value)

For multiple predictors, a logic regression equation can be written as

$p=probability(Y=positive\ outcome|X_1=x_1,\ldots ,x_k)$

Here, pb refers to the probability of the positive occurrence of the event, the Y-intercept is $\alpha$ , the regression coefficient is $\beta$ , and e is 2.71828. Logistic regression is applied in various domains like finance, healthcare, social sciences, and many more for predicting diseases, credit default, etc.

Naive Bayesian classification

Gaussian Naive Bayes is a probabilistic classification algorithm developed based on Bayes theorem. It refers to the features which represent a normal distribution 65 . It classifies the samples as most likely classified as

If the sample $Y_{j}$ is a vector, $x_{j}$ is the $j^{th}$ value which contains different values of $y_{j}$ . The attributes used are dependent and it is shown as

Substituting the above equation into Bayes classification, we get

The Gaussian Naive Bayes algorithm is mainly applied for spam filtering, sentiment analysis, and text classification problems where the features must be continuous and follow the Gaussian distribution 66 .

LIME (Local interpretable model-agnostic explanations)

LIME explains the predictions of any kind of classifier by approximating locally along with an interpretable system. It changes the data sample by altering the values of features and monitors the impact of the result. It explains the predictions from every sample 67 . To receive the labels for the current data, alter the samples z ’s into the unique form $z \in {\mathbb {R}}^d$ . Since the samples x ’ are generated randomly, x samples closer to the unique instance z for weighing are considered. The weight is evaluated as $\Pi _z(x)$ for measuring the intimacy between the data z to x. The currently weighted data X and the samples formed by f ( x ), are trained as $g \in G$ , where G is a model. The interpretable model $\xi (x)$ of the current data g for explaining f ( x ) as

L is the loss function to measure whether g is following the state of f in the nearest neighborhood of z . If the loss function is reduced, the behaviour of g takes the behaviour of f as $\Pi _z$ . The complexity of the model $\Omega (g)$ should be low. When $g(x')$ is considered as a linear function, $g(x') = \varphi ^T x' + \varphi _0$ , changes the equation into a linear regression task to evaluate $\varphi$ and $\varphi _0$ .

SHAP (SHAPELY Additive exPlanations)

SHAP values determine the status of each feature for the prediction of a specific class 68 . The prediction f ( y ), using $s(y')$ , a model for the binary elements $x' \in \{0,1\}^M$ with the sets $\emptyset _i \in {\mathbb {R}}$ , is given as

M refers to the explanation variable.

where f is the model of the SHAP, z refers to the variable, and $z'$ are the variables chosen. The value $f_y(x') - f_y(x'\setminus i)$ indicates all the predictions.

In this section two algorithms are discussed: one for the algorithm-based evaluation of water quality 1 and another for the algorithm-based explanation of water quality 2 . These two algorithms provide a holistic analysis and explanation of water quality management.

Algorithm for water quality classification

Algorithm for water quality Explanation

The water quality is assessed in the proposed work based on nine parameters such as pH value, Hardness (Total Dissolved Soils), Sulphate, Chloramines, Trihalomethanes, Conductivity, Organic carbon, and Turbidity. The target class for this dataset is Potability which is binary where 0 indicates that the water is not potable and 1 reflects its potability.

The dataset consisted of high missing values on sulphate and lower missing values on Chloramines and Trihalomethanes. The missing value imputation is hence performed and all the attributes are imputed for the missing values. The target class is converted into a numeric array for the processing of XAI models. This is done with the label encoder application of Python. The dataset is split with a ratio of 80:20 for training and testing.

The correlation analysis is performed on the dataset. The attribute Hardness has a high correlation of 0.34 with the target attribute potability. The next best correlation value is 0.24, which is rendered by the attribute Chloramines, followed by 0.21 produced by the Trihalomethanes attribute. Turbidity is the next better parameter with a correlation value of 0.16. The correlation heat map between the attributes of interest and the target attribute is presented in Fig. 8 .

Correlation analysis for water quality attributes.

The trained dataset is applied with SVM, LR, DT, RF and Gaussian Naive Bayes machine learning models. The SVM did not provide the desired classification and failed to converge for the portable data. The other models generated the results within the desired range and are presented in Table 6 .

The sensitivity and specificity measurements for the Machine learning models are presented in Table 7 . Considering the performance metrics, the results reveal the superiority of the RF model which generates a better outcome in comparison to the other models and thus it has been selected to be fed into the XAI model to provide enhanced interpretability, justifiability and transparency.

The XAI model implementation is performed considering SHAPELY values in the pandas’ application. This application focuses on the value of each feature in determining the target attribute which is potability. The significance of every feature is assessed through the various applications of SHAPELY. The first XAI model generated is the force plot, which provides the minimum and maximum prediction score of the target attribute in a dataset. The blue colored contour shows that a low score is measured and the red color shows a high score. The values at the separation boundary have the highest priority attribute. The force plot is presented in the Figs. 9 and 10 .

Force plot for water quality.

Force plot for potability.

The Global surrogate version of the force plot is presented in Fig. 11 . The blue regions indicate no potability and the red-coloured regions indicate potability. The border areas of the intersection show the attributes which have higher significance for the feature selection. The Sulphate value of 444 at the point of intersection indicates its significance in explaining this test patch for the entire dataset.

Test patch for potability.

The next XAI application of SHAPELY is the summary plot. This plot describes the features in determining binary classification problems. This predicts the scale of low to high for two significant results. The blue contour indicates lower significance towards the prediction and red indicates higher significance. The summary plot is shown in Fig. 12 . The Solids, pH, Sulfate, and Hardness show higher significance in determining the output.

Summary plot for potability.

The dependency plot shows the relationship between two features in the dataset. It provides the output in granular form with a variable-like result rather than simply a graph-like result of a Partial Dependency Plot(PDP). The relationship between the Sulphate and Potability is depicted in Fig. 13 . The mid-range of the dataset provides more granular output, which shows that the Sulphate parameter values are more significant in determining the values of potability in the mid-range of the dataset.

Dependency plot for potability.

The decision plot, which displays how the values of the features affect the goal, is the final model of XAI. This plot is a local surrogate plot, which would only explain a certain data instance, in which what values of the attributes influence the decision to be 1 or 0 as the decision of the model. The decision plot for the potability as 1 is illustrated in Fig. 14 . The potability 0 is illustrated in Fig. 15 .

Decision plot for potability.

The results of the experiment reveal the superiority of the RF model which generates an accuracy of 0.999 followed by DT, generating an accuracy of 0.998. The lowest accuracy is generated by the SVM model of 0.63. The RF is thus chosen for the implementation of the XAI model using SHAPELY. The comparative analysis of the aforementioned various models is depicted in Fig. 16 , considering evaluation metrics accuracy, precision, recall, and f1-score. In the case of all the performance metrics, the RF model outperforms the other models. Figure 17 shows the comparison of the sensitivity and specificity measures. The RF model stands superior in these considerations as well. Thus, the discussion offers a visual representation and justification of the reasoning behind the choice of RF to be included in the XAI framework to offer explainability.

Comparative analysis of machine learning models used.

Comparative analysis of sensitivity and specificity.

Apart from the selection of the RF model, SHAPELY provided five different models to explain the feature importance and relationships. The proposed work presented the force plot, summary plot, test patch, dependency plot, and decision plot. The Final decision plot explained how the classification is carried out using the corresponding values of the independent variables. Thus the black-box classification is explained in the white-box context of XAI. The following section describes the challenges and opportunities of the proposed work with an emphasis on future directions.

The proposed work may be influenced by the following challenges which are described in detail as follows,

Global unity

For the successful implementation of the system, a unanimously accepted implementation is essential. Unfortunately, water quality estimation and related research are limited to consideration of specific datasets acquired for a particular region, wherein the generated results may differ with the changes in geographic location. Thus the generated results can never be considered suitable on a global scale. The parameters that influence the water quality may also vary across the world, and hence the proposed work can never be considered as a universal solution.

Training and re-training

The qualifying attributes that determine the quality of water vary across the globe and hence the proposed model needs to be re-trained 69 when applied to a new environment of study. This would allow the model to unlearn and re-learn new environments. On the contrary, the complexity of the model would also increase. The accuracy and other performance metrics which are measured in the proposed work may drastically decrease as well in a different environment of study. Thus applying this model to versatile environments is complex and would be a challenging task.

Subjective or quantitative

The trade-off from subjective analysis (which was done through fuzzy-based methods in the form of the Analytical Hierarchy Process (AHP) and The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS)) has improved the performance and ability to classify the models with better accuracy. However, the involvement of a subject matter expert is a missing point in the current research. Despite all the implementation and analysis from an engineering perspective, the involvement of an environmental scientist in any aspect of water research would contribute towards the enhancement of research quality.

Confusing solids

The proposed work identifies Solids as the primary influencing factor that affects potability. In real-world applications, solids can be of any form. For example, in sewage water treatment plants it can be either mud, Fat-Oil-Grease(FOG), or any other substances. Every solid wastage has its way of filtration and impact on water quality, which makes the recordings unstable from time to time. The attributes of research are too complex to handle in real-life scenarios, which acts as an inevitable yet detrimental impact.

Environmental challenges

Water resources are under serious threat due to water scarcity, water contamination, water conflicts and climate changes. Chemical and the municipal wastewater contaminates the water and endangering the life of the aquatic organisms and affect their ability to reproduce. This also makes them an easier prey to their predators. The food cycle and livelihood of the human is also greatly affected by the water contamination. Chemical substances make the water hard to recycle and consume by reducing the regeneration ratios.

Water quality and industrial sustainability

The era of Industry 5.0 focuses on the consumer centric industrial evolution with the idea of environmental sustainability. The futuristic technologies evolve with the improvement of technical viability, with the mission of sustainable development in the environmental aspects. Since the water is an irreplaceable and finite, the demand of the water is increasing with the industrial evolution and the water requirements on manufacturing and production industries would be very much essential as ever. The challenge is enhancement of the water harvesting, recycling and conservation. For all the above said processes quality of the water is the common essential requirement. Thus the quality of the water is more critical in all futuristic technological developments.

Research finding of the proposed work

The following items are presented as the findings are outcomes of the proposed work

The proposed work performs an exploratory analysis with XAI implementation providing an ability to improve the reliability of machine learning models providing explanation and transparency to the classification process.

The proposed work acquires data from a single dataset, where the performance of classification yields optimized results. This result may vary if the model is subjected to a different dataset constituting different features and instances.

The XAI reveals the most significant features contributing towards classification results and also explains the same.

The best fitting machine learning model is chosen for the explanation through an exhaustive analysis and evaluation of all the models considering the essential performance metrics. Thus the results produced by SHAPELY can be considered as the most reliable and acceptable.

The proposed work also suggests the importance of the subject matter expert, which can extend the usability of the proposed model at the universal level.

The predictions of the proposed work with the support of an explainer, helps end users and consumers to understand the quality of the water they use.

The features related to the classification and explanation, can be further controlled to diminish the levels of chemicals and pollutants in water recycling.

Total dissolvable solids quantification and the feature weights for the same determine the levels of filtration and carbon purification required in the recycling plants.

The proposed work brings insights of pollutants on the seashore and how the explainabilty can support the impurity estimations for such conditions also.

Water quality management impacts almost all aspects of life on earth and clean water is a basic necessity. The proposed work is extremely relevant in this regard wherein an exploratory analysis conducted to analyze and control the factors that deteriorate the quality of the water. The impact of these factors is explained using XAI models. The contribution of the XAI model lies in its ability to explain the role of the underlying parameters towards the classification of water being potable or not, based on their relative importance and unique properties. The XAI model uses SHAPELY considering the probabilistic prediction generated from the Random Forest classifier. This RF model in this regard is chosen as it yields the highest accuracy of 0.999 with sensitivity and specificity of 0.999 and 0.998, which is found to be superior in comparison to the other state-of-the-art models considered in the study. This justifies the reason for the RF to be selected for XAI implementation. The proposed model identifies the parameter “solid” as the most significant in terms of its impact on the potability of water. The proposed model yields optimized and explainable results considering the dataset used in the study. Future work may involve more complex and heterogeneous datasets to generate predictions. In such scenarios, the metric evaluations may differ. The usage of deep learning algorithms could further enhance the examination the solid sediments and generate classification results based on their mass, dimensions, and shape. The use of XAI in such a model would ensure a better explanation of factors relevant to the solid sedimentation in water.

Data availability

The data that support the findings of this study are available from the corresponding author, upon reasonable request.

Zhu, M. et al. A review of the application of machine learning in water quality evaluation. Eco-Environ. Health 1 , 107–116. https://doi.org/10.1016/j.eehl.2022.06.001 (2022).

Article PubMed PubMed Central Google Scholar

Miller, M., Kisiel, A., Cembrowska-Lech, D., Durlik, I. & Miller, T. Iot in water quality monitoring are we really here?. Sensors 23 , 960. https://doi.org/10.3390/s23020960 (2023).

Article ADS PubMed PubMed Central Google Scholar

Akhtar, N. et al. Modification of the water quality index (wqi) process for simple calculation using the multi-criteria decision-making (mcdm) method: A review. Water 13 , 905. https://doi.org/10.3390/w13070905 (2021).

Article CAS Google Scholar

Abolfathi, S. & Pearson, J. Application of smoothed particle hydrodynamics (sph) in nearshore mixing: A comparison to laboratory data. Coastal Eng. Proc. 35 , 1–13 (2017).

Google Scholar

Hájek, M. et al. A European map of groundwater ph and calcium. Earth Syst. Sci. Data 13 , 1089–1105. https://doi.org/10.5194/essd-13-1089-2021 (2021).

Article ADS Google Scholar

Li, L. et al. Interpretable tree-based ensemble model for predicting beach water quality. Water Res. 211 , 118078. https://doi.org/10.1016/j.watres.2022.118078 (2022).

Article CAS PubMed Google Scholar

Lu, J. Can the central environmental protection inspection reduce transboundary pollution? Evidence from river water quality data in china. J. Clean. Prod. 332 , 130030 (2022).

Halder, J. N. & Islam, M. N. Water pollution and its impact on the human health. J. Environ. Hum. 2 , 36–46 (2015).

Article Google Scholar

Wang, Z. et al. Overview assessment of risk evaluation and treatment technologies for heavy metal pollution of water and soil. J. Clean. Prod. 379 , 134043 (2022).

Elehinafe, F. B., Agboola, O., Vershima, A. D. & Bamigboye, G. O. Insights on the advanced separation processes in water pollution analyses and wastewater treatment: A review. S. Afr. J. Chem. Eng. 48 , 188–200 (2022).

Mu, L., Mou, M., Tang, H. & Gao, S. Exploring preference and willingness for rural water pollution control: A choice experiment approach incorporating extended theory of planned behaviour. J. Environ. Manag. 332 , 117408 (2023).

Wang, Y., Ding, X., Chen, Y., Zeng, W. & Zhao, Y. Pollution source identification and abatement for water quality sections in Huangshui River Basin, China. J. Environ. Manag. 344 , 118326 (2023).

Najafzadeh, M. & Niazmardi, S. A novel multiple-kernel support vector regression algorithm for estimation of water quality parameters. Nat. Resour. Res. 30 , 3761–3775 (2021).

Najafzadeh, M., Homaei, F. & Farhadi, H. Reliability assessment of water quality index based on guidelines of national sanitation foundation in natural streams: Integration of remote sensing and data-driven models. Artif. Intell. Rev. 54 , 4619–4651 (2021).

Najafzadeh, M., Ghaemi, A. & Emamgholizadeh, S. Prediction of water quality parameters using evolutionary computing-based formulations. Int. J. Environ. Sci. Technol. 16 , 6377–6396 (2019).

Najafzadeh, M. & Basirian, S. Evaluation of river water quality index using remote sensing and artificial intelligence models. Remote Sens. 15 , 2359 (2023).

Chowdhury, M. A. Z. et al. Organophosphorus and carbamate pesticide residues detected in water samples collected from paddy and vegetable fields of the Savar and Dhamrai Upazilas in Bangladesh. Int. J. Environ. Res. Public Health 9 , 3318–3329 (2012).

Article CAS PubMed PubMed Central Google Scholar

Ahirvar, B. P., Das, P., Srivastava, V. & Kumar, M. Perspectives of heavy metal pollution indices for soil, sediment, and water pollution evaluation: An insight. Total Environ. Res. Themes 6 , 100039 (2023).

Chen, K., Liu, Q.-M., Peng, W.-H., Liu, Y. & Wang, Z.-T. Source apportionment of river water pollution in a typical agricultural city of Anhui province, Eastern China using multivariate statistical techniques with apcs-mlr. Water Sci. Eng. 16 , 165–174 (2023).

Fan, S. et al. Improved multi-criteria decision making method integrating machine learning for patent competitive potential evaluation: A case study in water pollution abatement technology. J. Clean. Prod. 403 , 136896 (2023).

Wang, Z., Wang, C. & Liu, Y. Evaluation for the nexus of industrial water-energy-pollution: Performance indexes, scale effect, and policy implications. Environ. Sci. Policy 144 , 88–98 (2023).

Asomaku, S. O. Quality assessment of groundwater sourced from nearby abandoned landfills from industrial city in Nigeria: Water pollution indices approach. HydroResearch 6 , 130–137 (2023).

Balaram, V., Copia, L., Kumar, U. S., Miller, J. & Chidambaram, S. Pollution of water resources and application of icp-ms techniques for monitoring and management: A comprehensive review. Geosyst. Geoenviron. 2 , 100210 (2023).

Yuan, F., Huang, Y., Chen, X. & Cheng, E. A biological sensor system using computer vision for water quality monitoring. Ieee Access 6 , 61535–61546 (2018).

Borzooei, S. et al. Impact evaluation of wet-weather events on influent flow and loadings of a water resource recovery facility. In New Trends in Urban Drainage Modelling: UDM 2018 11 706–711 (Springer, 2019).

Noori, R. et al. Decline in Iran’s groundwater recharge. Nat. Commun. 14 , 6674 (2023).

Article ADS CAS PubMed PubMed Central Google Scholar

Yeganeh-Bakhtiary, A., EyvazOghli, H., Shabakhty, N., Kamranzad, B. & Abolfathi, S. Machine learning as a downscaling approach for prediction of wind characteristics under future climate change scenarios. Complexity 2022 , 8451812 (2022).

Jeihouni, M., Toomanian, A. & Mansourian, A. Decision tree-based data mining and rule induction for identifying high quality groundwater zones to water supply management: a novel hybrid use of data mining and gis. Water Resour. Manag. 34 , 139–154 (2020).

Lee, K.-J. et al. The combined use of self-organizing map technique and fuzzy c-means clustering to evaluate urban groundwater quality in Seoul Metropolitan City, South Korea. J. Hydrol. 569 , 685–697 (2019).

Article ADS CAS Google Scholar

Agrawal, P. et al. Exploring artificial intelligence techniques for groundwater quality assessment. Water 13 , 1172 (2021).

Wang, Y. et al. Monthly water quality forecasting and uncertainty assessment via bootstrapped wavelet neural networks under missing data for Harbin, China. Environ. Sci. Pollut. Res. 20 , 8909–8923 (2013).

El Bilali, A., Taleb, A. & Brouziyne, Y. Groundwater quality forecasting using machine learning algorithms for irrigation purposes. Agric. Water Manag. 245 , 106625 (2021).

Arabgol, R., Sartaj, M. & Asghari, K. Predicting nitrate concentration and its spatial distribution in groundwater resources using support vector machines (svms) model. Environ. Model. Assess. 21 , 71–82 (2016).

Sajedi-Hosseini, F. et al. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Sci. Total Environ. 644 , 954–962 (2018).

Article ADS CAS PubMed Google Scholar

Ransom, K. M., Nolan, B. T., Stackelberg, P., Belitz, K. & Fram, M. S. Machine learning predictions of nitrate in groundwater used for drinking supply in the conterminous united states. Sci. Total Environ. 807 , 151065 (2022).

Yadav, B., Gupta, P. K., Patidar, N. & Himanshu, S. K. Ensemble modelling framework for groundwater level prediction in urban areas of India. Sci. Total Environ. 712 , 135539 (2020).

Tomić, A. Š, Antanasijević, D., Ristić, M., Perić-Grujić, A. & Pocajt, V. A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter-and extrapolation performance with inputs’ significance analysis. Sci. Total Environ. 610 , 1038–1046 (2018).

Zhi, W. et al. From hydrometeorology to river water quality: Can a deep learning model predict dissolved oxygen at the continental scale?. Environ. Sci. Technol. 55 , 2357–2368 (2021).

Srinivas, R., Bhakar, P. & Singh, A. P. Groundwater quality assessment in some selected area of Rajasthan, India using fuzzy multi-criteria decision making tool. Aquat. Procedia 4 , 1023–1030 (2015).

Haghibi, A. H., Nasrolahi, A. H. & Parsaie, A. Water quality prediction using machine learning. J. Water Qual. Res. 53 , 3–13 (2018).

Liu, M. & Lu, J. Support vector machine-an alternative to artificial neuron network for water quality forecasting in an agricultural nonpoint source polluted river?. Environ. Sci. Pollut. Res. 21 , 11036–11053 (2014).

Chen, K. et al. Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data. Water Res. 171 , 115454 (2020).

Sagan, V. et al. Monitoring inland water quality using remote sensing: Potential and limitations of spectral indices, bio-optical simulations, machine learning, and cloud computing. Earth-Sci. Rev. 205 , 103187 (2020).

Wu, Y., Zhang, X., Xiao, Y. & Feng, J. Attention neural network for water image classification under iot environment. Appl. Sci. 10 , 909 (2020).

Pu, F., Ding, C., Chao, Z., Yu, Y. & Xu, X. Water-quality classification of inland lakes using landsat8 images by convolutional neural networks. Remote Sens. 11 , 1674 (2019).

Donnelly, J., Daneshkhah, A. & Abolfathi, S. Forecasting global climate drivers using gaussian processes and convolutional autoencoders. Eng. Appl. Artif. Intell. 128 , 107536 (2024).

Abolfathi, S., Cook, S., Yeganeh-Bakhtiary, A., Borzooei, S. & Pearson, J. Microplastics transport and mixing mechanisms in the nearshore region. Coast. Eng. Proc. https://doi.org/10.9753/icce.v36v.papers.63 (2021).

Stride, B., Abolfathi, S., Odara, M. G. N., Bending, G. D. & Pearson, J. Modeling microplastic and solute transport in vegetated flows. Water Resour. Res. 59 , e2023WR034653. https://doi.org/10.1029/2023WR034653 (2023).

Unacademy (2022).

Başağaoğlu, H. et al. A review on interpretable and explainable artificial intelligence in hydroclimatic applications. Water 14 , 1230 (2022).

Habib, M., O’Sullivan, J., Abolfathi, S. & Salauddin, M. Enhanced wave overtopping simulation at vertical breakwaters using machine learning algorithms. PLoS ONE 18 , e0289318 (2023).

Mpia, H., Mburu, L. & Mwendia, S. Applying data mining in graduates’ employability: A systematic literature review. Int. J. Eng. Pedag. 13 , 86–108. https://doi.org/10.3991/ijep.v13i2.33643 (2023).

Raileanu, L. E. & Stoffel, K. Theoretical comparison between the gini index and information gain criteria. Ann. Math. Artif. Intell. 41 , 77–93. https://doi.org/10.1023/b:amai.0000018580.96245.c6 (2004).

Article MathSciNet Google Scholar

Gulati, P., Sharma, A. & Gupta, M. Theoretical study of decision tree algorithms to identify pivotal factors for performance improvement: A review. Int. J. Comput. Appl. 141 , 19–25. https://doi.org/10.5120/ijca2016909926 (2016).

Tangirala, S. Evaluating the impact of GINI index and information gain on classification using decision tree classifier algorithm. Int. J. Adv. Comput. Sci. Appl. 11 , 110277. https://doi.org/10.14569/ijacsa.2020.0110277 (2020).

Xu, P. Review on studies of machine learning algorithms. J. Phys. 1187 , 052103. https://doi.org/10.1088/1742-6596/1187/5/052103 (2019).

Purwanto, A. D., Wikantika, K., Deliar, A. & Darmawan, S. Decision tree and random forest classification algorithms for mangrove forest mapping in Sembilang National Park, Indonesia. Remote Sens. 15 , 16. https://doi.org/10.3390/rs15010016 (2022).

Huang, H. et al. A new fruit fly optimization algorithm enhanced support vector machine for diagnosis of breast cancer based on high-level features. BMC Bioinform. https://doi.org/10.1186/s12859-019-2771-z (2019).

Ji, Y. & Sun, S. Multitask multiclass support vector machines: Model and experiments. Pattern Recogn. 46 , 914–924. https://doi.org/10.1016/j.patcog.2012.08.010 (2013).

Übeyli, E. D. ECG beats classification using multiclass support vector machines with error correcting output codes. Dig. Signal Process. 17 , 675–684. https://doi.org/10.1016/j.dsp.2006.11.009 (2007).

Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20 , 273–297. https://doi.org/10.1007/bf00994018 (1995).

Ye, F., Lou, X. Y. & Sun, L. F. An improved chaotic fruit fly optimization based on a mutation strategy for simultaneous feature selection and parameter optimization for SVM and its applications. PLoS ONE 12 , e0173516. https://doi.org/10.1371/journal.pone.0173516 (2017).

Peng, C.-Y.J., Lee, K. L. & Ingersoll, G. M. An introduction to logistic regression analysis and reporting. J. Educ. Res. 96 , 3–14. https://doi.org/10.1080/00220670209598786 (2002).

Park, H.-A. An introduction to logistic regression: From basic concepts to interpretation with particular attention to nursing domain. J. Korean Acad. Nurs. 43 , 154. https://doi.org/10.4040/jkan.2013.43.2.154 (2013).

Article PubMed Google Scholar

Chen, H., Hu, S., Hua, R. & Zhao, X. Improved Naive Bayes classification algorithm for traffic risk management. EURASIP J. Adv. Signal Process. https://doi.org/10.1186/s13634-021-00742-6 (2021).

Shen, J. & Fang, H. Human activity recognition using gaussian Naïve Bayes algorithm in smart home. J. Phys. 1631 , 012059. https://doi.org/10.1088/1742-6596/1631/1/012059 (2020).

Gramegna, A. & Giudici, P. SHAP and LIME: An evaluation of discriminative power in credit risk. Front. Artif. Intell. https://doi.org/10.3389/frai.2021.752558 (2021).

Zaremba, L., Zaremba, C. S. & Suchenek, M. Modification of shapley value and its implementation in decision making. Found. Manag. 9 , 257–272. https://doi.org/10.1515/fman-2017-0020 (2017).

Krishnan, S. R. et al. Smart water resource management using artificial intelligence;a review. Sustainability https://doi.org/10.3390/su142013384 (2022).

Download references

Acknowledgements

Acknowledgements should be brief, and should not include thanks to anonymous referees and editors, or effusive comments. Grant or contribution numbers may be acknowledged.

Author information

Authors and affiliations.

School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, 632014, India

M. K. Nallakaruppan, M. Lawanya Shri & Sweta Bhattacharya

Department of Computer Science, Loyola College, Chennai, Tamil Nadu, 600034, India

E. Gangadevi

Shiv Nadar University, Delhi-NCR, 201314, India

Balamurugan Balusamy

School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds, LS13HE, UK

Shitharth Selvarajan

Department of Computer Science, Kebri Dehar University, Kebri Dehar, Ethiopia

You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed equally in this research work.

Corresponding author

Correspondence to Shitharth Selvarajan .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Nallakaruppan, M.K., Gangadevi, E., Shri, M.L. et al. Reliable water quality prediction and parametric analysis using explainable AI models. Sci Rep 14 , 7520 (2024). https://doi.org/10.1038/s41598-024-56775-y

Download citation

Received : 21 October 2023

Accepted : 11 March 2024

Published : 29 March 2024

DOI : https://doi.org/10.1038/s41598-024-56775-y

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Water Quality
Explainable AI
Water Quality Prediction

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

Explore articles by subject
Guide to authors
Editorial policies

Water Quality and Contamination

Water safety is a primary concern for many people not only in America but globally. The development of residential and industrial properties in water-catchment areas and close to waterways has triggered widespread water contamination thus limiting access to clean and safe drinking water (Goncharuk, 2014). Consequently, there has been a rise in the number of bottled water companies that offer an alternative source of clean water. The companies apply various methods such as distillation and filtration to produce sufficient quantities of water. The methods are capital intensive thus consumers have to purchase the water they need. Therefore, it becomes necessary to carry out detailed experiments on the bottled and tap water that is made available to consumers to establish whether it is worthwhile to purchase bottled water.

According to Waite (2012), an analysis of the water produced by bottling companies as well as tap water revealed some differences in their mineral composition. While water contains some essential minerals, it may be noted that contamination may occur as the water is being stored or as it is being transported through pipes from their source to the consumers’ houses. Therefore, treatment at a water collection point does not always guarantee that the water is safe for domestic use. Bottled water, on the other hand, is treated, packed, and distributed under hygienic conditions that are usually set and regulated by federal or state agencies to ensure its safety. Therefore, an experiment to test the differences between tap water and bottled water can reveal the differences that exist between the two thus helping to establish whether it worth to pay for bottled water as is the case with bottled water.

The water bottling process involves filtration and other treatment measures that eliminate harmful microorganisms. Conversely, untreated tap water poses several health risks because it is obtained and distributed in its raw form which could be contaminated due to contact with human waste, garbage, and chemicals (Ware, 2012). It is necessary to consider that the contaminants easily seep into the water table in lowlands and other waterlogged areas. Therefore, the experiment seeks to identify whether processed and bottled water is healthier for consumption and whether it is worth paying the price for it (Goncharuk, 2014).

Methodology and Materials

The initial experiment involved testing the pH levels of bottled water and tap water. Samples from two bottled water companies, Dasani and Fiji, and tap water were used. The samples were used to rinse three test tubes while avoiding direct hand-water contact because the bare hands could contaminate the water. 5ml of each sample were also added to each test tube after which drops of indicator solution were added. The observations were then recorded. For the testing of nitrate, acid reagents and nitrate nitrogen comparators were used. Similar tests were carried out to establish the levels of ammonia, chloride, phosphate, iron, chlorine, and hardness.

According to the experiments, it was established that bottled water contained fewer contaminants in their mineral composition. The pH levels were also lower in bottled water compared to tap water thus indicating that water filtration and other procedures used in water bottling were effective in eliminating harmful microorganisms.

The measures established by water bottling companies were regarded as useful in the control of waterborne diseases (Goncharuk, 2014). For example, high levels of chlorine were recorded in the two brands of bottled water thus implying that the chemical is heavily used in water treatment and bottling plants. Therefore, bottled water presents antimicrobial benefits thus helping to prevent the prevalence of waterborne ailments.

Concerns have also been raised over the safety of rainwater as an alternative to bottled and tap water. However, it is worth noting that although rain water does not contain any impurities, it eventually gets contaminated upon hitting the ground due to the presence of contaminants that exist either in the soil or water bodies (Waite, 2012). As such, it is evident that the processes involved in water bottling are useful in eliminating harmful contaminants and softening it for human consumption (Goncharuk, 2014). Regarding the hypothesis, it is possible to conclude that bottled water is safer for use thus it is worth paying the price for a healthy drink.

It is also critical to note that the quality of bottled water varies from one company to another (Ware, 2012). For instance, the level of contaminants including minerals in various brands of bottled water varies depending on a company’s source of raw water and the steps utilized in purifying it. The bottled water industry has experienced tremendous growth in the past few years due to the increasing awareness of the need to consume safe water. The introduction of flavored mineral water has also created a niche for bottling companies through which they can attract and retain more customers and subsequently raising the demand for their products (Goncharuk, 2014).

Despite the rising demand for bottled water, however, concerns have been raised over the safety of water that is packed in plastic containers. Plastics are believed to release carcinogenic elements especially when subjected to high temperatures in enclosed places such as the inside of a vehicle. Although studies are yet to establish a clear standpoint regarding the same, it is necessary for consumers to take precautionary measures to avoid implications which include the growth of cancer cells due to the accumulation of carcinogenic residues in the body.

The experiment focused on identifying the presence of various chemicals in the water. However, it would be necessary to establish the extent to which the chemicals affect normal body functions in humans when ingested in varying quantities (Goncharuk, 2014). Therefore, a future experiment will focus on the ratio of contaminants to water in a given sample and seek the implications of such ratios. The idea is based on the fact that some mineral components were observed to have varying concentrations in the three water samples. For example, high levels of chlorine are regarded as detrimental the bones and other body functions. Therefore, it would be necessary to establish the sample that had the right amount of chlorine and other components. Also, the experiment will utilize different testing techniques to get results that reflect a clearer analysis of the samples to be tested.

The consumption of bottled water presents a greater significance as opposed to consuming tap water. The purification processes utilized in bottling plants are designed to ensure that the water retains as many natural components as possible. Therefore, it is advisable for consumers to prefer the bottled water over tap water which could contain contaminants acquired from the soil, underground or surface catchment points. As such, it is evident that purchasing bottled water is beneficial to an individual’s wellness.

Goncharuk, V. V. (2014). Drinking water: Physics, chemistry, and biology .

Waite, T. D. (2012). Principles of Water Quality . Oxford: Elsevier Science.

Ware, G. W. (2012). Reviews of Environmental Contamination and Toxicology: Continuation of Residue Reviews . New York, NY: Springer New York.

Cite this paper

Chicago (N-B)
Chicago (A-D)

StudyCorgi. (2020, September 28). Water Quality and Contamination. https://studycorgi.com/water-quality-and-contamination/

"Water Quality and Contamination." StudyCorgi , 28 Sept. 2020, studycorgi.com/water-quality-and-contamination/.

StudyCorgi . (2020) 'Water Quality and Contamination'. 28 September.

1. StudyCorgi . "Water Quality and Contamination." September 28, 2020. https://studycorgi.com/water-quality-and-contamination/.

Bibliography

StudyCorgi . "Water Quality and Contamination." September 28, 2020. https://studycorgi.com/water-quality-and-contamination/.

StudyCorgi . 2020. "Water Quality and Contamination." September 28, 2020. https://studycorgi.com/water-quality-and-contamination/.

This paper, “Water Quality and Contamination”, was written and voluntary submitted to our free essay database by a straight-A student. Please ensure you properly reference the paper if you're using it to write your assignment.

Before publication, the StudyCorgi editorial team proofread and checked the paper to make sure it meets the highest standards in terms of grammar, punctuation, style, fact accuracy, copyright issues, and inclusive language. Last updated: October 11, 2022 .

If you are the author of this paper and no longer wish to have it published on StudyCorgi, request the removal . Please use the “ Donate your paper ” form to submit an essay.

Essay on Water for Students and Children

500+ words essay on water.

Water is one of the most important substances for life on earth to function. It is equally important for humans as well as animals. Water does not merely help us survive, but it is significant for our day to day functioning. It has numerous uses when we come to think about it. Majority of our earth is covered with water itself, but, not all of it is safe for consumption. Therefore, it makes it essential for us to utilize this transparent substance chemical wisely. Moreover, if we look at the shortage of water happening in our country, it makes it all the more important to conserve it immediately.

Uses of Water

As we have already said that water has numerous uses, we will see where it is used. This part will most importantly help us realize the importance of water . It will make humans aware of what absence of water in the following areas can do to human life. As India’s main occupation is agriculture, water is exhaustively used here. Irrigation and cattle rearing requires a lot of water. Thus, a lot of farmers’ livelihood depends on it.

Further, industries use water for various purposes. It comes in handy when cooling, manufacturing and transporting several goods. For instance, thermal power plants consume quite a substantial amount of water for their running.

Furthermore, the domestic use of water cannot be left behind. In the day to day life of the common man, water plays a vital role. That is to say, from drinking water to washing utensils, we need water every step of the way.

After that, plants need water to survive and make food. It is one of the main elements which help them grow. Hence, water is extremely important for humans, animals, and plants to survive .

Get the huge list of more than 500 Essay Topics and Ideas

Do not Waste Water

While water is quite essential and yet so scarce, however, people fail to realize this fact. They waste water with little or no care for the results of this activity. There are various ways in which one can avoid wasting water . To begin with, all households must get their leaking taps checked. They should fix them immediately as every drop is precious.

Similarly, we must choose buckets instead of showers for bathing. This is a very debatable topic and it needs to be settled. Showers waste a lot of water, so people must prefer buckets. This particular habit is quite commonly found in most of the households. People do not turn off their taps while brushing their teeth and washing utensils. Always remember to keep the tap off when doing so.

In addition, encourage rainwater harvesting system in all homes. This can help conserve water like never before.

In short, water is essential for the survival of mankind. But, it is, unfortunately, being waster rapidly. Every citizen and government must come together to tackle this issue. Governments must ensure all areas get water equally. On the other hand, citizens must keep in mind to use it wisely and not waste it unnecessarily.

FAQs on Water

Q.1 State the importance of water.

A.1 Water is of the utmost importance for human and animal life. It gives us water to drink. It also comes in great use for farmers and industries. Even common man requires water for various purposes like drinking, cleaning, bathing and more.

Q.2 List the ways to avoid wastage of water.

A.2 Everyone must avoid wasting water. We can do so by fixing our leaking taps, avoiding showers for bathing, and turning off taps when brushing. Furthermore, we can adopt rainwater harvesting system to conserve water.

Customize your course in 30 seconds

Which class are you in.

Travelling Essay
Picnic Essay
Our Country Essay
My Parents Essay
Essay on Favourite Personality
Essay on Memorable Day of My Life
Essay on Knowledge is Power
Essay on Gurpurab
Essay on My Favourite Season
Essay on Types of Sports

Download the App

Mobile Menu Overlay

The White House 1600 Pennsylvania Ave NW Washington, DC 20500

FACT SHEET: Biden- ⁠ Harris Administration Takes Critical Action to Protect Communities from PFAS Pollution in Drinking Water

EPA Announces First-Ever National Standard to Address PFAS in Drinking Water, Delivers an Additional $1 Billion through President Biden’s Investing in America Agenda to Combat PFAS Pollution

President Biden believes every community has the right to clean, safe drinking water, free of pollutants that harm people’s health and wellbeing. That is why the President launched a comprehensive action plan and provided billions in funding to protect communities from toxic “forever chemicals” that are linked to a range of severe health problems, including cancers, liver and heart damage, and developmental impacts in children. Found in drinking water, soil, air, and our food supply, per- and polyfluoroalkyl substances (PFAS) persist in the environment for long periods of time, posing a serious health threat across rural, suburban, and urban areas.

Today the Environmental Protection Agency (EPA) is announcing the first-ever national legally enforceable drinking water standard for PFAS , which will protect 100 million people from PFAS exposure , prevent tens of thousands of serious illnesses, and save lives. This action complements the Biden-Harris Administration’s commitment to combatting PFAS pollution and delivering clean water.

President Biden has secured historic levels of funding to meet this new standard. Today, the Biden-Harris Administration is also announcing an additional $1 billion through President Biden’s Investing in America agenda to help every state and territory fund PFAS detection and treatment systems to meet the new standard . This funding is part of the $9 billion in dedicated funding through the President’s Bipartisan Infrastructure Law to address PFAS and other emerging contaminants in drinking water – the largest-ever investment in tackling PFAS pollution. An additional $12 billion in funding from the Bipartisan Infrastructure Law supports general drinking water investments, including PFAS treatment. The investments are part of the Justice40 Initiative , which aims to ensure that 40 percent of the overall benefits of certain federal investments flow to disadvantaged communities.

These actions will help tackle PFAS pollution that has devastated communities like Oakdale, outside of St. Paul, Minnesota, where decades of PFAS-containing waste dumped by a chemical plant has contaminated the community’s drinking water. In this area, cancer was found to be a far more likely cause of death in children than in neighboring areas. The funding announced today will build on funding from the President’s Bipartisan Infrastructure Law that is already helping communities address PFAS contamination, including a $33 million award for Tucson, Arizona to treat its PFAS-contaminated drinking water wells.

This funding also builds on President Biden’s action plan to address PFAS pollution , safeguard public health, and advance environmental justice – all while advancing the Biden Cancer Moonshot goal of cutting the cancer death rate by at least half by 2047 and preventing cancer before it starts by protecting communities from known risks associated with PFAS exposure.

As the first-ever Safe Drinking Water Act standard for PFAS – and the first for any new contaminants since 1996 – this rule sets health safeguards and will require public water systems to monitor and reduce the levels of PFAS in our nation’s drinking water, and notify the public of any exceedances of those levels. The rule sets drinking water limits for five individual PFAS, including the most frequently found PFOA and PFOS. Because PFAS can often be found together in mixtures, EPA is also setting a limit for any combination of four PFAS, including GenX Chemicals. This standard will reduce PFAS exposure in our drinking water to the lowest levels that are feasible for effective nationwide implementation.

Today’s announcements advance President Biden’s broader commitment to deliver clean water for every American. The President’s Bipartisan Infrastructure Law invests over $50 billion to upgrade water infrastructure – the largest investment in clean water in American history. This includes a historic $15 billion to replace toxic lead pipes and protect children from brain damage, as part of President Biden’s goal of replacing every lead pipe in the country within a decade.

Recent Federal Actions to Protect Communities from PFAS

Under President Biden’s leadership, nearly two dozen federal agencies and offices have made systematic and substantive progress to safeguard public health and protect the environment from PFAS in drinking water and beyond. This work is coordinated by the White House Council on Environmental Quality, which leads the Interagency Policy Committee on PFAS. Other new actions the Biden-Harris Administration has advanced to combat PFAS pollution over the past year include:

Protecting Firefighters from PFAS : The Biden-Harris Administration is committed to protecting firefighters from the harmful effects of PFAS contained in fire suppressing agents and firefighter gear. The Department of Defense is offering PFAS blood tests to military firefighters. The Federal Emergency Management Agency’s U.S. Fire Administration is working to reduce PFAS exposure and promoting access to early cancer screenings and participation in the National Firefighter Registry for Cancer led by the National Institute for Occupational Safety and Health as part of President Biden’s mission to end cancer as we know it.

Reducing PFAS in Fire Suppressants: The Department of Defense (DoD) qualified three fluorine-free foams to replace fluorinated Aqueous Film Forming Foam for shore-based firefighting activities at military installations, which the Federal Aviation Administration (FAA) has authorized for civilian airports. The FAA is assisting airports to transition to these new foams , and funding foam testing systems for airports that prevent environmental discharge. These changes will reduce the release of PFAS in the environment and protect the health of firefighters and local communities.

Supporting Healthcare Providers: The Agency for Toxic Substances and Disease Registry at the Centers for Disease Control and Prevention recently released the PFAS: Information for Clinicians resource guide. This information gives clinicians up-to-date resources and information they need to help patients with questions and concerns about PFAS exposure and health effects.

Phasing Out PFAS in Food Packaging: The Food and Drug Administration (FDA) announced the completion of the voluntary market phase-out of PFAS used on paper and paperboard food packaging, eliminating the primary source of dietary exposure to PFAS . FDA can now also test for 30 PFAS in a variety of foods to further protect people from dietary PFAS exposure.

Testing for and Cleaning Up PFAS Pollution: EPA continues to take key actions to address PFAS . For example, EPA is gathering data on 29 PFAS in the nation’s drinking water systems has collaborated with DoD to develop a method to test for 40 PFAS in various media including biosolids, groundwater, and fish tissue. EPA also updated its interim PFAS disposal and destruction guidance and has released a new method to test for 30 volatile fluorine-containing compounds in air including potential products of incomplete combustion of PFAS. DoD recently identified 40 installations where interim cleanup actions to prevent further PFAS migration are underway or will start in FY2024. These actions will address PFAS in groundwater to protect public health and the environment.

Reducing PFAS in Federal Procurement: EPA and the U.S. General Services Administration announced this week that custodial contracts for federal buildings will now only use cleaning products certified to ecolabels such as EPA’s Safer Choice and certain Green Seal standards, thereby avoiding products that contain intentionally added PFAS. This shift will protect the environment, federal custodial workers, other federal employees, and those visiting government buildings.

Stay Connected

We'll be in touch with the latest information on how President Biden and his administration are working for the American people, as well as ways you can get involved and help our country build back better.

Opt in to send and receive text messages from President Biden.

Watch CBS News

Water charity warns Paris Olympic swimmers face "alarming levels" of dangerous bacteria in Seine River

By Haley Ott

Updated on: April 12, 2024 / 11:56 AM EDT / CBS News

A water charity said Monday that tests of water from the Seine River, where water events are set to take place in less than four months during the Paris 2024 Summer Olympic and Paralympic Games, showed alarming levels of bacteria including E.coli.

A "shadow looms over the quality of the water in the Seine River," the Surfrider Foundation Europe said in a social media post . The group said it performed 14 tests on different samples taken from two spots along the Seine from September 2023 to March 2024, and that all but one of the results showed poor water quality.

French diver slips during Paris Olympic aquatics venue opening ceremony

The samples "reveal alarming levels of bacteriological pollution at the Alexandre III Bridge," the spot it said would be the starting point for Olympic and Paralympic triathlon and marathon swimming events.

TOPSHOT-OLY-2024-FRA-TRIATHLON-TEST-WOMEN

"There are many causes for this pollution, ranging from rainfall to malfunctions in the sewage system, including poorly connected barges and animal waste," Surfrider said.

The group urged stakeholders to take action in the time remaining ahead of the games, which kick off on July 26.

"The consequences of this pollution on health are serious, ranging from common infections such as otitis and conjunctivitis to more severe infections such as staphylococcus," the organization said. "It's also an opportunity to reaffirm how precious health is in all circumstances, but especially when you are an athlete pursuing such a big dream: That of becoming an Olympic champion."

Boat racers warned of E. coli in London's sewage-infused Thames

Paris Mayor Anne Hidalgo has said she intends to create three public bathing areas in the Seine next year, and has made cleaning up the river one of the key legacy achievements of the Paris Olympics, French news agency AFP reported. About $1.5 billion has been spent upgrading storm water treatment and sewage facilities already, AFP said.

"The first quarter of 2024 saw extremely large rainfall (250,000 ml over three months, double the level of 2023) which deteriorated the quality of the water," the Paris prefect's office said in a statement to AFP, adding that water disinfection facilities had not been operating over the winter and would be started ahead of the games.

"There has never been question of opening the Seine for swimming all year round," Marc Guillaume, the top state security official for Paris, told the news agency.

Water quality has been an issue at other Olympic Games, including the 2020 Tokyo Olympics and the 2016 Rio Olympics .

Haley Ott is the CBS News Digital international reporter, based in the CBS News London bureau.

More from CBS News

Lawmakers unveil bill to fund Baltimore bridge reconstruction

Body found of missing teen whose disappearance sparked deadly settler attack

Roberto Cavalli, Italian fashion designer known for his sexy style, dies at 83

Guide dog nicknamed Dogfather retires after fathering over 300 puppies

IMAGES

Save Water Save Life Essay
Water quality essay
Essay on Water
Essay on Importance of Water
Essay on water conservation by johny bahsa
Water Conservation and Importance Free Essay Example

VIDEO

10 lines on water essay in English || Essay on water || 10 lines on water || Few lines on water
Essay On Water || 10 Lines Essay ||
10 Lines On Water In English
Water Conservation || Essay / Paragraph
10 lines on water pollution/water pollution essay in English/water pollution/essay on water pollutio
Water pollution ll short notes ll essay ll cause, effect and solution

COMMENTS

Essay on Water Quality
500 Words Essay on Water Quality Water Quality: The Foundation of Life. Water is the elixir of life, an indispensable resource that sustains all living organisms on Earth. Its quality directly impacts our health, environment, and overall well-being. Understanding water quality and taking steps to preserve it are crucial for ensuring a healthy ...
(PDF) An Introduction to Water Quality Analysis
Water quality analysis is required mainly for monitoring. purpose. Some importance of such assessment includes: (i) To check whether the water quality is in compliance. with the standards, and ...
Drinking Water Quality and Human Health: An Editorial
Drinking water quality is paramount for public health. Despite improvements in recent decades, access to good quality drinking water remains a critical issue. ... 20 papers were recently published on different topics related to drinking water. Eight papers were on microbiological contamination, 11 papers on chemical contamination, and one on ...
67 Water Quality Essay Topic Ideas & Examples
This essay discusses the quality of water as per the report of 2021 obtained from the municipality, the quality issue and the source of pollution, and how the pollution impacts human health and the environment […] Water Quality Importance. In a lot of areas, the water available to the public is contaminated; that is it has substances that can ...
Water quality essay
Water Quality Essay Introduction. Water is an essential part of our lives. Being the known "universal solvent," water has many uses, from using it to clean our house, use in agriculture, use it in our farm animals, and drink it by ourselves. The world is composed of 71% water that covers the earth's surface.
Evaluating Drinking Water Quality Using Water Quality Parameters and
Water is a vital natural resource for human survival as well as an efficient tool of economic development. Drinking water quality is a global issue, with contaminated unimproved water sources and inadequate sanitation practices causing human diseases (Gorchev & Ozolins, 1984; Prüss-Ustün et al., 2019).Approximately 2 billion people consume water that has been tainted with feces ().
Water Quality Importance
Water Quality Importance Essay. Having accessibility to high-quality water is essential for the survival of humans. We all use water, not only for drinking but for other purposes such as cleaning, cooking, bathing, and so forth. We are constantly in contact with water, hence one must ensure that the water does not contain substances harmful to ...
Water Quality
pH is a measure of how acidic/basic water is. The range goes from 0 to 14, with 7 being neutral. pHs of less than 7 indicate acidity, whereas a pH of greater than 7 indicates a base. The pH of water is a very important measurement concerning water quality. September 16, 2019.
PDF Essays in Water Conservation and Water Quality Programs
Essays in Water Conservation and Water Quality Programs Abstract As growing populations continue to drive demand for water, managers of this fundamen-tal resource face the dual challenge of providing both sufﬁcient and clean supplies. In this dissertation, I undertake two analyses exploring a policy aimed at maintaining sufﬁciency
How Soil and Water Conservation Improves Water Quality
Through the lens of soil and water conservation, the journey towards enhancing water quality takes on a profound significance. The principles of cover cropping, conservation tillage, and nutrient management converge to present a comprehensive strategy to mitigate water pollution and protect aquatic ecosystems. Keep in mind: This is only a sample.
Water Quality Essay
Water Quality Essay Jamie Tidwell Grand Canyon University BIO 220: Environmental Science Suzan Allaham December 12, 2021. Given the importance of water in all aspects of life, water quality is one of many people's top priorities. With the advancement of technology and industrialized companies, the world's water supply is under risk, particularly in major cities.
Essays on Water Quality
This essay explores the challenges posed by inadequate drainage systems, the various negative outcomes they engender, and the potential solutions to mitigate these... Water Quality Water Sanitation. Absolutely FREE essays on Water Quality. All examples of topics, summaries were provided by straight-A students. Get an idea for your paper.
Water Quality Essay
Anita Flaa July 28, 2020 BIO- Vivian Hobbins Water Quality Water quality is a very essential topic and knowing where the water comes from and how it is treated to guarantee it is safe for use. Local water municipals offer an annual water quality report to notify the public of the water safety in their area.
Essay on Water Quality and Environmental Health
Essay on Water Quality and Environmental Health In the modern world the problem of the reliable water supply is extremely important because the water resources are widely exploited and water is used in different fields of human activities. In fact, the life of human beings is impossible without water but nowadays water is used not only simply ...
Water Quality Essays & Research Papers
Water Quality Essay Examples 🗨️ More than 20000 essays Find the foremost Water Quality essay to get results! Browse Categories; Essay Examples. Essay Examples ... Water quality for human consumption has recently become a issue topic has recently gathered a lot of attention in the near future. With pollution of freshwater sources, drinking ...
Essay On Water Quality
Essay On Water Quality. 1720 Words7 Pages. The most fundamental human needs of water are for drinking, cooking, bathing and personal hygiene. To meet these needs, the quality of the water used must fix no risk to human health. The quality of the water in nature also has an impact on the condition of ecosystems that all living organisms depend on.
Essay on Water Conservation and Water Quality
Water conservation is the careful use and preservation of water supply, and it includes both the quantity and quality of water utilized. Water is an essential asset for the nourishment of all life. The fundamental demand for all activities appropriates local use to the agricultural industry. With the regular expanding weight of the human ...
Reliable water quality prediction and parametric analysis using
Water is a common and crucial resource shared among all humans, animals, and plants and is a necessity for all species. Each one of these species has its own respective needs for water quality.
Water Quality and Contamination
Samples from two bottled water companies, Dasani and Fiji, and tap water were used. The samples were used to rinse three test tubes while avoiding direct hand-water contact because the bare hands could contaminate the water. 5ml of each sample were also added to each test tube after which drops of indicator solution were added.
Water Quality Assessment: Environmental Impact
This essay sample was donated by a student to help the academic community. Papers provided by EduBirdie writers usually outdo students' samples. Maintaining good water quality is essential to human health; thus, the recent decades have outstandingly worsened the water across communities worldwide by pollution.
Essay on Water for Students and Children
A.1 Water is of the utmost importance for human and animal life. It gives us water to drink. It also comes in great use for farmers and industries. Even common man requires water for various purposes like drinking, cleaning, bathing and more. Q.2 List the ways to avoid wastage of water.
PDF Final PFAS National Primary Drinking Water Regulation
•Drinking water utilities can choose from multiple proven treatment options. •Water treatment technologies exist to remove PFAS chemicals from drinking water, including granular activated carbon, reverse osmosis, and ion exchange systems. •In some cases, systems can close contaminated wells or obtain new uncontaminated source of drinking ...
FACT SHEET: Biden-Harris Administration Takes Critical Action to
Found in drinking water, soil, air, and our food supply, per- and polyfluoroalkyl substances (PFAS) persist in the environment for long periods of time, posing a serious health threat across rural ...
Water quality
Water Quality Essay Water quality is a critical issue that affects communities worldwide. The state of water quality within a community being the issue, with a focus on identifying the water quality issue, its impact, and management practices to minimize water pollution.
EPA announces first-ever national regulations for "forever chemicals
EPA sets new rule for "forever chemicals" in drinking water 02:06. For the first time ever, the Environmental Protection Agency announced Wednesday it is issuing a national regulation limiting the ...
PDF PFAS National Primary Drinking Water Regulation
Water systems must take action to reduce the levels of these PFAS in drinking water if the level of PFAS in their drinking water exceeds regulatory standards. Regulated public water systems have three years to complete their initial monitoring for these chemicals. Systems must include their results in their Annual Water Quality reports to ...
DEQ details next steps for water systems as EPA announces PFAS
The North Carolina Department of Environmental Quality (DEQ) has been working with water systems to assess PFAS levels. Based on all available data, more than 300 water systems in our state have PFAS levels that will exceed the new standards. That includes 42 municipal water systems serving nearly 3 million residents combined, as well as ...
Biden administration sets first national standard to limit ...
The Biden administration finalized the first national standard to limit dangerous "forever chemicals" found in nearly half of the drinking water in the United States. Some environmentalists ...
Water charity warns Paris Olympic swimmers face "alarming levels" of
"The first quarter of 2024 saw extremely large rainfall (250,000 ml over three months, double the level of 2023) which deteriorated the quality of the water," the Paris prefect's office said in a ...
Water quality essay
Water Quality Essay. Ei Pyo College of Humanities and Social Sciences, Grand Canyon University. BIO-225: Environmental Science Elizabeth Lemster December 16th, 2021. Water Quality Essay Water is an essential and natural source for humans and animals. Humans especially, consume large amounts of water whether it is for drinking, showering, or ...