{"title":"利用深度学习模型从水质和空气质量数据中预测鱼类死亡率。","authors":"Chia-Ching Ting, Ying-Chu Chen","doi":"10.1002/jeq2.20574","DOIUrl":null,"url":null,"abstract":"<p>The high rate of aquatic mortality incidents recorded in Taiwan and worldwide is creating an urgent demand for more accurate fish mortality prediction. Present study innovatively integrated air and water quality data to measure water quality degradation, and utilized deep learning methods to predict accidental fish mortality from the data. Keras library was used to build multilayer perceptron and long short-term memory models for training purposes, and the models’ accuracies in fish mortality prediction were compared with that of the naïve Bayesian classifier. Environmental data from the 5 days before a fish mortality event proved to be the most important data for effective model training. Multilayer perceptron model reached an accuracy of 93.4%, with a loss function of 0.01, when meteorological and water quality data were jointly considered. It was found that meteorological conditions were not the sole contributors to fish mortality. Predicted fish mortality rate of 4.7% closely corresponded to the true number of fish mortality events during the study period, that is, four. A significant surge in fish mortality, from 20% to 50%, was noted when the river pollution index increased from 5.36 to 6.5. Moreover, the probability of fish mortality increased when the concentration of dissolved oxygen dropped below 2 mg/L. To mitigate fish mortality, ammonia nitrogen concentrations should be capped at 5 mg/L. Dissolved oxygen concentration was found to be the paramount factor influencing fish mortality, followed by the river pollution index and meteorological data. Results of the present study are expected to aid progress toward achieving the Sustainable Development Goals and to increase the profitability of water resources.</p>","PeriodicalId":15732,"journal":{"name":"Journal of environmental quality","volume":"53 4","pages":"482-491"},"PeriodicalIF":2.2000,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Forecasting fish mortality from water and air quality data using deep learning models\",\"authors\":\"Chia-Ching Ting, Ying-Chu Chen\",\"doi\":\"10.1002/jeq2.20574\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The high rate of aquatic mortality incidents recorded in Taiwan and worldwide is creating an urgent demand for more accurate fish mortality prediction. Present study innovatively integrated air and water quality data to measure water quality degradation, and utilized deep learning methods to predict accidental fish mortality from the data. Keras library was used to build multilayer perceptron and long short-term memory models for training purposes, and the models’ accuracies in fish mortality prediction were compared with that of the naïve Bayesian classifier. Environmental data from the 5 days before a fish mortality event proved to be the most important data for effective model training. Multilayer perceptron model reached an accuracy of 93.4%, with a loss function of 0.01, when meteorological and water quality data were jointly considered. It was found that meteorological conditions were not the sole contributors to fish mortality. Predicted fish mortality rate of 4.7% closely corresponded to the true number of fish mortality events during the study period, that is, four. A significant surge in fish mortality, from 20% to 50%, was noted when the river pollution index increased from 5.36 to 6.5. Moreover, the probability of fish mortality increased when the concentration of dissolved oxygen dropped below 2 mg/L. To mitigate fish mortality, ammonia nitrogen concentrations should be capped at 5 mg/L. Dissolved oxygen concentration was found to be the paramount factor influencing fish mortality, followed by the river pollution index and meteorological data. Results of the present study are expected to aid progress toward achieving the Sustainable Development Goals and to increase the profitability of water resources.</p>\",\"PeriodicalId\":15732,\"journal\":{\"name\":\"Journal of environmental quality\",\"volume\":\"53 4\",\"pages\":\"482-491\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-05-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of environmental quality\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/jeq2.20574\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of environmental quality","FirstCategoryId":"93","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/jeq2.20574","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Forecasting fish mortality from water and air quality data using deep learning models
The high rate of aquatic mortality incidents recorded in Taiwan and worldwide is creating an urgent demand for more accurate fish mortality prediction. Present study innovatively integrated air and water quality data to measure water quality degradation, and utilized deep learning methods to predict accidental fish mortality from the data. Keras library was used to build multilayer perceptron and long short-term memory models for training purposes, and the models’ accuracies in fish mortality prediction were compared with that of the naïve Bayesian classifier. Environmental data from the 5 days before a fish mortality event proved to be the most important data for effective model training. Multilayer perceptron model reached an accuracy of 93.4%, with a loss function of 0.01, when meteorological and water quality data were jointly considered. It was found that meteorological conditions were not the sole contributors to fish mortality. Predicted fish mortality rate of 4.7% closely corresponded to the true number of fish mortality events during the study period, that is, four. A significant surge in fish mortality, from 20% to 50%, was noted when the river pollution index increased from 5.36 to 6.5. Moreover, the probability of fish mortality increased when the concentration of dissolved oxygen dropped below 2 mg/L. To mitigate fish mortality, ammonia nitrogen concentrations should be capped at 5 mg/L. Dissolved oxygen concentration was found to be the paramount factor influencing fish mortality, followed by the river pollution index and meteorological data. Results of the present study are expected to aid progress toward achieving the Sustainable Development Goals and to increase the profitability of water resources.
期刊介绍:
Articles in JEQ cover various aspects of anthropogenic impacts on the environment, including agricultural, terrestrial, atmospheric, and aquatic systems, with emphasis on the understanding of underlying processes. To be acceptable for consideration in JEQ, a manuscript must make a significant contribution to the advancement of knowledge or toward a better understanding of existing concepts. The study should define principles of broad applicability, be related to problems over a sizable geographic area, or be of potential interest to a representative number of scientists. Emphasis is given to the understanding of underlying processes rather than to monitoring.
Contributions are accepted from all disciplines for consideration by the editorial board. Manuscripts may be volunteered, invited, or coordinated as a special section or symposium.