Deep learning-based prediction of effluent quality of a constructed wetland
Data-driven approaches that make timely predictions about pollutant concentrations in the effluent of constructed wetlands are essential for improving the treatment performance of constructed wetlands. However, the effect of the meteorological condition and flow changes in a real scenario are genera...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-01-01
|
Series: | Environmental Science and Ecotechnology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666498422000631 |
_version_ | 1811159897470926848 |
---|---|
author | Bowen Yang Zijie Xiao Qingjie Meng Yuan Yuan Wenqian Wang Haoyu Wang Yongmei Wang Xiaochi Feng |
author_facet | Bowen Yang Zijie Xiao Qingjie Meng Yuan Yuan Wenqian Wang Haoyu Wang Yongmei Wang Xiaochi Feng |
author_sort | Bowen Yang |
collection | DOAJ |
description | Data-driven approaches that make timely predictions about pollutant concentrations in the effluent of constructed wetlands are essential for improving the treatment performance of constructed wetlands. However, the effect of the meteorological condition and flow changes in a real scenario are generally neglected in water quality prediction. To address this problem, in this study, we propose an approach based on multi-source data fusion that considers the following indicators: water quality indicators, water quantity indicators, and meteorological indicators. In this study, we establish four representative methods to simultaneously predict the concentrations of three representative pollutants in the effluent of a practical large-scale constructed wetland: (1) multiple linear regression; (2) backpropagation neural network (BPNN); (3) genetic algorithm combined with the BPNN to solve the local minima problem; and (4) long short-term memory (LSTM) neural network to consider the influence of past results on the present. The results suggest that the LSTM-predicting model performed considerably better than the other deep neural network-based model or linear method, with a satisfactory R2. Additionally, given the huge fluctuation of different pollutant concentrations in the effluent, we used a moving average method to smooth the original data, which successfully improved the accuracy of traditional neural networks and hybrid neural networks. The results of this study indicate that the hybrid modeling concept that combines intelligent and scientific data preprocessing methods with deep learning algorithms is a feasible approach for forecasting water quality in the effluent of actual engineering. |
first_indexed | 2024-04-10T05:48:30Z |
format | Article |
id | doaj.art-4a8350000d3d480c9d8b916f626de419 |
institution | Directory Open Access Journal |
issn | 2666-4984 |
language | English |
last_indexed | 2024-04-10T05:48:30Z |
publishDate | 2023-01-01 |
publisher | Elsevier |
record_format | Article |
series | Environmental Science and Ecotechnology |
spelling | doaj.art-4a8350000d3d480c9d8b916f626de4192023-03-05T04:25:43ZengElsevierEnvironmental Science and Ecotechnology2666-49842023-01-0113100207Deep learning-based prediction of effluent quality of a constructed wetlandBowen Yang0Zijie Xiao1Qingjie Meng2Yuan Yuan3Wenqian Wang4Haoyu Wang5Yongmei Wang6Xiaochi Feng7State Key Laboratory of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, 518055, PR ChinaState Key Laboratory of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, 518055, PR ChinaShenzhen Shenshui Water Resources Consulting CO, LTD, Shenzhen, Guangdong, 518022, PR ChinaCollege of Biological Engineering, Beijing Polytechnic, Beijing, 10076, PR ChinaState Key Laboratory of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, 518055, PR ChinaState Environmental Protection Key Laboratory of Integrated Surface Water-Groundwater Pollution Control, School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055, ChinaState Key Laboratory of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, 518055, PR ChinaState Key Laboratory of Urban Water Resource and Environment, School of Civil and Environmental Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, 518055, PR China; Corresponding author. Harbin Institute of Technology (Shenzhen), China.Data-driven approaches that make timely predictions about pollutant concentrations in the effluent of constructed wetlands are essential for improving the treatment performance of constructed wetlands. However, the effect of the meteorological condition and flow changes in a real scenario are generally neglected in water quality prediction. To address this problem, in this study, we propose an approach based on multi-source data fusion that considers the following indicators: water quality indicators, water quantity indicators, and meteorological indicators. In this study, we establish four representative methods to simultaneously predict the concentrations of three representative pollutants in the effluent of a practical large-scale constructed wetland: (1) multiple linear regression; (2) backpropagation neural network (BPNN); (3) genetic algorithm combined with the BPNN to solve the local minima problem; and (4) long short-term memory (LSTM) neural network to consider the influence of past results on the present. The results suggest that the LSTM-predicting model performed considerably better than the other deep neural network-based model or linear method, with a satisfactory R2. Additionally, given the huge fluctuation of different pollutant concentrations in the effluent, we used a moving average method to smooth the original data, which successfully improved the accuracy of traditional neural networks and hybrid neural networks. The results of this study indicate that the hybrid modeling concept that combines intelligent and scientific data preprocessing methods with deep learning algorithms is a feasible approach for forecasting water quality in the effluent of actual engineering.http://www.sciencedirect.com/science/article/pii/S2666498422000631LSTMConstructed wetlandsWater quality predictionDeep learningMulti-source data fusion |
spellingShingle | Bowen Yang Zijie Xiao Qingjie Meng Yuan Yuan Wenqian Wang Haoyu Wang Yongmei Wang Xiaochi Feng Deep learning-based prediction of effluent quality of a constructed wetland Environmental Science and Ecotechnology LSTM Constructed wetlands Water quality prediction Deep learning Multi-source data fusion |
title | Deep learning-based prediction of effluent quality of a constructed wetland |
title_full | Deep learning-based prediction of effluent quality of a constructed wetland |
title_fullStr | Deep learning-based prediction of effluent quality of a constructed wetland |
title_full_unstemmed | Deep learning-based prediction of effluent quality of a constructed wetland |
title_short | Deep learning-based prediction of effluent quality of a constructed wetland |
title_sort | deep learning based prediction of effluent quality of a constructed wetland |
topic | LSTM Constructed wetlands Water quality prediction Deep learning Multi-source data fusion |
url | http://www.sciencedirect.com/science/article/pii/S2666498422000631 |
work_keys_str_mv | AT bowenyang deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT zijiexiao deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT qingjiemeng deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT yuanyuan deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT wenqianwang deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT haoyuwang deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT yongmeiwang deeplearningbasedpredictionofeffluentqualityofaconstructedwetland AT xiaochifeng deeplearningbasedpredictionofeffluentqualityofaconstructedwetland |