research paper on prawn farming

Deep Learning for Prawn Farming

Forecasting and Anomaly Detection

Conference paper
First Online: 10 May 2022
Cite this conference paper

Joel Janek Dabrowski 13 ,
Ashfaqur Rahman 13 ,
Andrew Hellicar 13 ,
Mashud Rana 13 &
Stuart Arnold 14

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13282))

Included in the following conference series:

Pacific-Asia Conference on Knowledge Discovery and Data Mining

1775 Accesses

3 Altmetric

We present a decision support system for managing water quality in prawn ponds. The system uses various sources of data and deep learning models in a novel way to provide 24-h forecasting and anomaly detection of water quality parameters. It provides prawn farmers with tools to proactively avoid a poor growing environment, thereby optimising growth and reducing the risk of losing stock. This is a major shift for farmers who are forced to manage ponds by reactively correcting poor water quality conditions. To our knowledge, we are the first to apply Transformer as an anomaly detection model, and the first to apply anomaly detection in general to this aquaculture problem. Our technical contributions include adapting ForecastNet for multivariate data and adapting Transformer and the Attention model to incorporate weather forecast data into their decoders. We attain an average mean absolute percentage error of 12% for dissolved oxygen forecasts and we demonstrate two anomaly detection case studies. The system is successfully running in its second year of deployment on a commercial prawn farm.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save.

Get 10 units per month
Download Article/Chapter or eBook
1 Unit = 1 Article or 1 Chapter
Cancel anytime
Available as PDF
Read on any device
Instant download
Own it forever
Available as EPUB and PDF
Compact, lightweight edition
Dispatched in 3 to 5 business days
Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Temporal fusion transformer-based prediction in aquaponics

A novel application of transformer neural network (TNN) for estimating pan evaporation rate

Attention-driven LSTM and GRU deep learning techniques for precise water quality prediction in smart aquaculture

https://www.ysi.com/exo2 .

https://www.metergroup.com/environment/products/atmos-41-weather-station/ .

https://plot.ly .

Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of International Conference on Learning Representations (2015). http://arxiv.org/abs/1409.0473

Boyd, C.E., Tucker, C.S.: Pond Aquaculture Water Quality Management. Springer, Boston (1998). https://doi.org/10.1007/978-1-4615-5407-3

Dabrowski, J.J., Rahman, A., George, A., Arnold, S., McCulloch, J.: State space models for forecasting water quality variables: an application in aquaculture prawn farming. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, pp. 177–185. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3219819.3219841

Dabrowski, J.J., Zhang, Y.F., Rahman, A.: ForecastNet: a time-variant deep feed-forward neural network architecture for multi-step-ahead time-series forecasting. In: Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H., King, I. (eds.) ICONIP 2020. LNCS, vol. 12534, pp. 579–591. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-63836-8_48

Chapter Google Scholar

Dogo, E.M., Nwulu, N.I., Twala, B., Aigbavboa, C.: A survey of machine learning methods applied to anomaly detection on drinking-water quality data. Urban Water J. 16 (3), 235–248 (2019). https://doi.org/10.1080/1573062X.2019.1637002

Encinas, C., Ruiz, E., Cortez, J., Espinoza, A.: Design and implementation of a distributed IoT system for the monitoring of water quality in aquaculture. In: 2017 Wireless Telecommunications Symposium (WTS), pp. 1–7 (2017). https://doi.org/10.1109/WTS.2017.7943540

Ernst, D.H., Bolte, J.P., Nath, S.S.: Aquafarm: simulation and decision support for aquaculture facility design and management planning. Aquacultural Eng. 23 (1), 121–179 (2000). https://www.sciencedirect.com/science/article/pii/S0144860900000455

Food and Agriculture Organization of the United Nations: Towards sustainability in the shrimp industry, February 2020. http://www.fao.org/in-action/globefish/market-reports/resource-detail/en/c/1261310/

Gamboa, J.C.B.: Deep learning for time-series analysis. arXiv preprint arXiv:1701.01887 (2017)

Mac Coombea, P.N., Pasanena, J., Petersa, C., Sharmana, C., Taylora, P.: Senaps: a platform for integrating time-series with modelling systems. In: Proceedings of the 22nd International Congress on Modelling and Simulation (MODSIM 2017), Hobart, Tasmania, Australia, pp. 438–444 (2017)

Google Scholar

Munir, M., Siddiqui, S.A., Dengel, A., Ahmed, S.: DeepAnT: a deep learning approach for unsupervised anomaly detection in time series. IEEE Access 7 , 1991–2005 (2019). https://doi.org/10.1109/ACCESS.2018.2886457

Article Google Scholar

Pang, G., Shen, C., Cao, L., Hengel, A.V.D.: Deep learning for anomaly detection: a review. ACM Comput. Surv. 54 (2), 1–38 (2021). https://doi.org/10.1145/3439950

Robertson, C. (ed.): Australian Prawn Farming Manual: Health Management for Profit. Queensland Department of Primary Industries and Fisheries (QDPI&F) (2006)

Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMS. In: International Conference on Machine Learning, pp. 843–852. PMLR (2015)

Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 3104–3112. Curran Associates, Inc. (2014). http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf

Tobing, F.A.T., Dzulhaq, M.I., Overbeek, M.V., Setiawan, E.A.: Design of decision support system with C4.5 algorithm methods in determining results vaname shrimp cultivation. In: 2019 5th International Conference on New Media Studies (CONMEDIA), pp. 195–200 (2019). https://doi.org/10.1109/CONMEDIA46929.2019.8981848

Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 5998–6008. Curran Associates, Inc. (2017). http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf

Download references

Acknowledgement

Thanks to Pacific Reef Fisheries for providing us with the access to their farm to conduct this study and also for assisting us in deploying and maintaining sensors. This work was supported by the CSIRO Digiscape Future Science Platform.

Author information

Authors and affiliations.

Data61, CSIRO, Canberra, Australia

Joel Janek Dabrowski, Ashfaqur Rahman, Andrew Hellicar & Mashud Rana

Agriculture & Food, CSIRO, Canberra, Australia

Stuart Arnold

You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joel Janek Dabrowski .

Editor information

Editors and affiliations.

Laboratory of Artificial Intelligence and Decision Support, University of Porto, Porto, Portugal

School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China

National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

School of Computer Science and Technology, University of Science and Technology of China, Hefei, China

Enhong Chen

JD iCity, JD Technology & JD Intelligent Cities Research, Beijing, China

Rights and permissions

Reprints and permissions

Copyright information

About this paper

Cite this paper.

Dabrowski, J.J., Rahman, A., Hellicar, A., Rana, M., Arnold, S. (2022). Deep Learning for Prawn Farming. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13282. Springer, Cham. https://doi.org/10.1007/978-3-031-05981-0_3

Download citation

DOI : https://doi.org/10.1007/978-3-031-05981-0_3

Published : 10 May 2022

Publisher Name : Springer, Cham

Print ISBN : 978-3-031-05980-3

Online ISBN : 978-3-031-05981-0

eBook Packages : Computer Science Computer Science (R0)

Share this paper

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

Publish with us

Policies and ethics

Find a journal
Track your research

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

We're Hiring!
Help Center

Download Free PDF

Integrated Freshwater Prawn Farming: State-of-the-Art and Future Potential

2016, Reviews in Fisheries Science & Aquaculture

Related papers

The quality and safety of the freshwater prawn, Macrobrachium rosenbergii, are directly linked to its value to the consumer and ultimately to its ability to compete within the global marketplace. This bulletin details best management practices (BMPs) to optimize production and product quality of M. rosenbergii through husbandry practices (land selection, water resource management, pond design, nutrition management , harvest), postharvest transport and handling, and processing. Low-input production practices are recommended and are based upon a semi-intensive culture strategy that has been demonstrated to be highly suited for the optimization of husbandry of M. rosenbergii. Such a management approach is characterized by efficient use of land resources, comparatively low input as established by the initial number of juveniles that are stocked, the type of feeding strategy, and reduced energy consumption and labor to achieve the lowest cost of production. BMPs broadly refer to those pr...

International Journal of Fisheries and Aquatic Studies, 2022

India contributes about 4% of the world aquaculture prawn production. Prawn farming provides excellent employment opportunities and generates income, particularly to India's coastal villagers. It, however, has caused impact on land and water resources use. India has about 55 prawn species, 11 of which are suitable for coastal culture. With all these, along with available natural resources, favorable climate, greater awareness of prawn farming, availability of trained human resource, and government and research support, India 's prawn farming industry is expected to develop further

Aquaculture Research, 2008

The effects of different stocking densities of freshwater prawn (Macrobrachium rosenbergii) on its growth and production in relation to the presence of small self-recruiting species mola (Amblypharyngodon mola) were investigated in modified rice fields after rice harvest at Mymensingh, Bangladesh. Keeping the stocking density of mola fixed at 20 000 ha−1 in each treatment, four densities of freshwater prawn (treatments) were maintained: 10 000, 15 000, 20 000 and 25 000 ha−1 respectively. The rice plots were limed (CaCO3) and fertilized with urea, triple super phosphate and cowdung regularly. The prawns were fed daily with commercial pellets. Water quality parameters such as temperature, dissolved oxygen, transparency, pH, total alkalinity, inorganic nitrogen (nitrate, nitrite and total ammonia), chlorophyll a and orthophosphate were determined fortnightly. Numerical analysis of plankton communities was performed monthly. All water quality parameters were found to be within the suitable range for freshwater prawn culture, except high temperature, in the peak summer months. There was a homogenous abundance of plankton communities in all treatments throughout the experimental period. Mola started to breed in the second month of the original stocking with partial harvesting after the second month and continued until the final harvest. The total production of mola ranged between 124 and 152 kg ha−1 during the 4-month culture period. The average prawn survival ranged from 49% to 57% without any significant difference among treatments. Freshwater prawn production ranged from 294 to 596 kg ha−1 with significantly higher production in the treatment where 20 000 ha−1 freshwater prawn were stocked. This treatment also resulted in a higher net profit margin (74%), indicating that stocking at a combination of 20 000 ha−1 freshwater prawn and 20 000 ha−1 mola could be the optimum proposition for prawn–mola culture in modified rain-fed rice fields after rice cultivation.

This call for papers invites contributions concerned with the Iberian Peninsula and neighbouring regions in the Mediterranean World. Papers can focus on any period throughout the Middle Ages. The thematic focus is concerned with this year's subject of "Worlds of Learning" (but not strictly limited to it), including, for example, clerical education, the formation of universities, manuscript production, exegetical endeavours, or preaching efforts. Besides this thematic focus, these sessions have the goal to seize the opportunity provided by the IMC to bring together scholars from different scholarly and national communities, since many different groups are working on the Iberian Peninsula, and via these sessions we hope to encourage stronger interaction between these groups. This includes several nationally determined groups such as the strong German scholarship on Iberia (as united in the Arbeitsgemeinschaft Ibero-Mediaevistik) as well as several subject-related groups such as crusade scholars devoted to corresponding phenomena on the Peninsula. These sessions, therefore, have the goal to put various communities into conversation, and to generate new synergies between different scholarly traditions.

I CARDINI DELLA MoDERNITà PENALE DAI CoDICI RoCCo ALLE STAGIoNI DELL’ITALIA REPUBBLICANA, 2024

Atti del Convegno su “I Cardini del penale” a cura dell’Istituto Emilio Betti, Roma, Univ. Roma Tre, 11-12 novembre 2022, a cura di Massimo Donini, Loredana Garlati, Marco Nicola Milettie Renzo Orlandi. Le sei sezioni (anch’esse riproposte nell’ordine del presente volume) sono e intitolate rispettivamente: La funzione costituente del penale; Dal penale dello Stato al penale sovranazionale; Ossessioni inquisitorie; Punire o non punire?; Dalla centralità del codice al primato della giurisprudenza; Dottrine e interpretazione

Walter Benjamin y la crítica de la violencia. Constelaciones actuales e inactuales, 2024

Una lectura de la Crítica de la violencia que introduce un tipo de anarquismo no convencional

Modernism/Modernity 30:3, 2023

ENGLISH FRANCA : Academic Journal of English Language and Education

DEÜ Edebiyat Fakültesi Dergisi , 2024

internationalconference.com.my

Universe, 2018

New Frontiers in Mirror Neurons Research, 2015

Psychosomatic Medicine, 2014

Journal of Legal Studies, 2016

Journal of Peace Research, 2020