Open AccessDeep-learning based approach for forecast of water quality in intensive shrimp culture ponds
Author(s) -
Lin Qi,
Wen Yang,
Zheng Cheng,
Keding Lu,
Zhichao Zheng,
Jianping Wang,
Jun Zhu
Publication year - 2018
Publication title -
indian journal of fisheries
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.216
H-Index - 12
ISSN - 0970-6011
DOI - 10.21077/ijf.2018.65.4.72559-09
Subject(s) - mariculture , water quality , environmental science , aquaculture , shrimp , effluent , quality (philosophy) , deep water , deep belief network , environmental quality , fishery , environmental engineering , computer science , deep learning , artificial intelligence , ecology , engineering , fish <actinopterygii> , marine engineering , biology , philosophy , epistemology
With the enormous development of aquaculture, reducing the impacts of effluent discharge and improving water quality had become a critical global environmental concern. It is important to assess and predict water quality in the environmental management process of shrimp mariculture. Meanwhile, the accurate forecast of water quality is still in the exploration stage at present. In this study, deep belief networks (DBN) model are used to forecast water quality in intensive shrimp culture. This method based on deep learning includes a five-layered structure to extract relationships between the quantitative characteristic of water bodies and water quality variables. The water quality can be forecasted by the Canadian Water Quality Index (WQI) obtained from the output layer of simulated model. The results show that the DBN model has a great potential to predict the water quality and the ability of generalization and accuracy of model are satisfied.