{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T04:30:24Z","timestamp":1769574624140,"version":"3.49.0"},"reference-count":28,"publisher":"AIP Publishing","issue":"2","funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/50011\/2020"],"award-info":[{"award-number":["UIDB\/50011\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDP\/50011\/2020"],"award-info":[{"award-number":["UIDP\/50011\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,1]]},"abstract":"<jats:p>Aquaculture presents itself as one of the most rapidly developing means of sustainable production of animal protein to feed ever-growing populations. Recirculating aquaculture systems offer higher control and fewer inconveniences than traditional systems, making them an attractive option for fish production. Although the sector\u2019s digitalization is in its early stages, its application should increase its rentability while conserving the environment. This paper aims to promote the sector\u2019s evolution by assessing parameter importance in mortality with tree-based machine learning models, verifying the method\u2019s natural robustness and how it compares to a specially devised one, and at the same time evaluating the concept\u2019s relevance in predicting categorical mortality values. In particular, to better understand the aquaculture production process through a systematic data evaluation, an exploration based on real-time data acquisition is fully needed. Moreover, algorithm robustness is a key ingredient in this application since measurements are greatly affected by errors. This invalidates the application of traditional machine learning methods, where models are sensitive to production data variations and sensor noise. The study found the parameters that play relevant roles in the production phases, such as pH and nitrate concentration. While the obtained predictive metrics are still sub-optimal, further enhancements could be achieved through rigorous analysis of feature engineering, fine-tuning model hyperparameters, and exploring more advanced algorithms. Additionally, incorporating larger and more diverse datasets, refining data pre-processing techniques, and iteratively optimizing the model architecture may contribute to significant improvements in predictive performance. Despite that, the impact costs of using adjusted machine learning metrics are clear, as are the importance of data rounding in pre-processing and directions for improvement regarding data acquisition and transformation.<\/jats:p>","DOI":"10.1063\/5.0196248","type":"journal-article","created":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T13:41:35Z","timestamp":1707658895000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":2,"title":["Robust mortality prediction on a recirculating aquaculture system"],"prefix":"10.1063","volume":"95","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-7914","authenticated-orcid":false,"given":"Vasco","family":"Costa","sequence":"first","affiliation":[{"name":"CICECO - Aveiro Institute of Materials and Physics Department and CIDMA, University of Aveiro 1 , 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3628-6795","authenticated-orcid":false,"given":"Eug\u00e9nio","family":"Rocha","sequence":"additional","affiliation":[{"name":"Center for Research and Development in Mathematics and Applications and Department of Mathematics, University of Aveiro 2 , 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8596-5092","authenticated-orcid":false,"given":"Carlos","family":"Marques","sequence":"additional","affiliation":[{"name":"CICECO - Aveiro Institute of Materials and Physics Department 3 , University of Aveiro, 3810-193 Aveiro, Portugal"}]}],"member":"317","published-online":{"date-parts":[[2024,2,8]]},"reference":[{"key":"2024021113413325000_c1","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.ejar.2018.06.006","article-title":"Characteristics of fish farming practices and agrochemicals usage therein in four regions of Cameroon","volume":"44","year":"2018","journal-title":"Egypt. J. Aquat. Res."},{"key":"2024021113413325000_c2","doi-asserted-by":"publisher","first-page":"112271","DOI":"10.1016\/j.jenvman.2021.112271","article-title":"Aquaculture industry: Supply and demand, best practices, effluent and its current issues and treatment technology","volume":"287","year":"2021","journal-title":"J. Environ. Manage."},{"key":"2024021113413325000_c3","unstructured":"United Nations, Population\u2014United Nations\u2014un.org, at https:\/\/www.un.org\/en\/global-issues\/population, URL:%5Curl%7Bhttps:\/\/www.un.org\/en\/global-issues\/population%7D (Accessed 31 Dec 2023)."},{"key":"2024021113413325000_c4","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aquaeng.2018.03.003","article-title":"Energy use in recirculating aquaculture systems (RAS): A review","volume":"81","year":"2018","journal-title":"Aquacult. Eng."},{"key":"2024021113413325000_c5","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1080\/10641262.2011.573597","article-title":"Aquaculture industry in China: Current state, challenges, and outlook","volume":"19","year":"2011","journal-title":"Rev. Fish. Sci."},{"key":"2024021113413325000_c6","unstructured":"Jr. Joel K. Bourne and Photographs by Brian Skerry, How to farm a better fish, National Geographic at https:\/\/www.nationalgeographic.com\/foodfeatures\/aquaculture\/ (accessed 31 Dec 2023)."},{"key":"2024021113413325000_c7","unstructured":"Instituto Nacional de Estat\u00edstica, Estat\u00edsticas da Pesca - 2017, ISBN 978-989-25-0393-6 at\n          https:\/\/www.ine.pt\/xurl\/pub\/320384843, 2018 (accessed 31 Dec 2023)."},{"key":"2024021113413325000_c8","unstructured":"Instituto Nacional de Estat\u00edstica, Estat\u00edsticas da Pesca - 2021, ISBN 978-989-25-0602-9 at\n          https:\/\/www.ine.pt\/xurl\/pub\/36828280 (2022) (accessed 31 Dec 2023)."},{"key":"2024021113413325000_c9","unstructured":"F. A.\n            Pereira Gon\u00e7alves\n          , \u201cAquacultura em Portugal - Principais fatores que contribu\u00edram para a sua estagna\u00e7\u00e3o e perspetivas futuras,\u201d M.A. thesis, Instituto de Ci\u00eancias Biom\u00e9dicas de Abel Salazar da Universidade do Porto, 2018, URL: https:\/\/hdl.handle.net\/10216\/118677."},{"key":"2024021113413325000_c10","unstructured":"Dire\u00e7\u00e3o-Geral de Pol\u00edtica do Mar, Estrat\u00e9gia nacional para o mar 2013\u20132020 at\n          https:\/\/www.dgpm.mm.gov.pt\/enm, 2014 (accessed 31 Dec 2023)."},{"key":"2024021113413325000_c11","doi-asserted-by":"publisher","first-page":"2076","DOI":"10.1111\/raq.12559","article-title":"Sustainable aquaculture development: A review on the roles of cloud computing, internet of things and artificial intelligence (CIA)","volume":"13","year":"2021","journal-title":"Rev. Aquacult."},{"key":"2024021113413325000_c12","doi-asserted-by":"publisher","first-page":"100061","DOI":"10.1016\/j.atech.2022.100061","article-title":"Applications of data mining and machine learning framework in aquaculture and fisheries: A review","volume":"2","year":"2022","journal-title":"Smart Agric. Technol."},{"key":"2024021113413325000_c13","doi-asserted-by":"publisher","first-page":"736724","DOI":"10.1016\/j.aquaculture.2021.736724","article-title":"Application of machine learning in intelligent fish aquaculture: A review","volume":"540","year":"2021","journal-title":"Aquaculture"},{"key":"2024021113413325000_c14","unstructured":"E.\n            Wong\n           and J.Zico Kolter, \u201cLearning perturbation sets for robust machine learning,\u201d CoRR arXiv:abs\/2007.08450(2020)."},{"key":"2024021113413325000_c15","unstructured":"L.\n            Grinsztajn\n          , E.Oyallon, and G.Varoquaux, \u201cWhy do treebased models still outperform deep learning on typical tabular data?,\u201d URL:https:\/\/openreview.net\/forum?id=Fp7__phQszn (2022)."},{"key":"2024021113413325000_c16","doi-asserted-by":"publisher","first-page":"735931","DOI":"10.1016\/j.aquaculture.2020.735931","article-title":"Fast decision-making tool for monitoring recirculation aquaculture systems based on a multivariate statistical analysis","volume":"530","year":"2021","journal-title":"Aquaculture"},{"key":"2024021113413325000_c17","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.biosystemseng.2023.03.003","article-title":"Dynamic and explainable fish mortality prediction under low-concentration ammonia nitrogen stress","volume":"228","year":"2023","journal-title":"Biosyst. Eng."},{"key":"2024021113413325000_c18","doi-asserted-by":"publisher","first-page":"441","DOI":"10.21608\/EJABF.2020.85857","article-title":"Environmental issues of aquaculture development","volume":"24","year":"2020","journal-title":"Egypt. J. Aquat. Biol. Fish."},{"key":"2024021113413325000_c19","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/S0044-8486(02)00652-X","article-title":"Salinity and pH effect on the colloidal properties of suspended particles in super intensive aquaculture systems","volume":"218","year":"2003","journal-title":"Aquaculture"},{"key":"2024021113413325000_c20","article-title":"API design for machine learning software: Experiences from the scikit-learn project"},{"key":"2024021113413325000_c21","unstructured":"scikit-learn, 3.2.3. Searching for optimal parameters with successive halving, 3.2. Tuning the hyper-parameters of an estimator at https:\/\/scikit-learn.org\/stable\/modules\/grid_search.html#successivehalving-user-guide (accessed 31 Dec 2023)."},{"key":"2024021113413325000_c22","first-page":"785","article-title":"XGBoost: A scalable tree boosting system","year":"2016"},{"key":"2024021113413325000_c23","unstructured":"A.\n            Kantchelian\n          , J. D.Tygar, and A. D.Joseph, \u201cEvasion and hardening of tree ensemble classifiers,\u201d arXiv: 1509.07892 [cs.LG] (2016)."},{"key":"2024021113413325000_c24","unstructured":"H.\n            Chen\n          , H.Zhang, D.Boning, and C.-J.Hsieh, \u201cRobust decision trees against adversarial examples,\u201d arXiv:1902.10660 (2019).10.48550\/ARXIV.1902.10660"},{"key":"2024021113413325000_c25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","year":"2001","journal-title":"Mach. Learn."},{"key":"2024021113413325000_c26","first-page":"1304","article-title":"Cognito: Automated feature engineering for supervised learning","year":"2016"},{"key":"2024021113413325000_c27","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.aquaculture.2018.12.051","article-title":"Investigating risk factors for mortality and reovirus infection in aquaculture production of soft-shell blue crabs (Callinectes sapidus)","volume":"502","year":"2019","journal-title":"Aquaculture"},{"key":"2024021113413325000_c28","unstructured":"Vanda Cardoso Pinheiro, Destaques - compete2020, Compete2020 (Nov. 2016), at\n          https:\/\/www.compete2020.gov.pt\/destaques\/detalhe\/Industria_4ponto0 (accessed 31 Dec 2023)."}],"container-title":["Review of Scientific Instruments"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/rsi\/article-pdf\/doi\/10.1063\/5.0196248\/19586741\/025102_1_5.0196248.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/rsi\/article-pdf\/doi\/10.1063\/5.0196248\/19586741\/025102_1_5.0196248.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T13:41:39Z","timestamp":1707658899000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/rsi\/article\/95\/2\/025102\/3262766\/Robust-mortality-prediction-on-a-recirculating"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2,1]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0196248","relation":{},"ISSN":["0034-6748","1089-7623"],"issn-type":[{"value":"0034-6748","type":"print"},{"value":"1089-7623","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,2,1]]},"published":{"date-parts":[[2024,2,1]]},"article-number":"025102"}}