Deep learning-based prediction of effluent quality of a constructed wetland

• Published in: Environmental science and ecotechnology Vol. 13; p. 100207
• Main Authors: Yang, Bowen, Xiao, Zijie, Meng, Qingjie, Yuan, Yuan, Wang, Wenqian, Wang, Haoyu, Wang, Yongmei, Feng, Xiaochi
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2023; Elsevier
• Subjects: algorithms; Constructed wetlands; Deep learning; LSTM; meteorological parameters; Multi-source data fusion; neural networks; Original Research; pollutants; prediction; regression analysis; water quality; Water quality prediction; water quantity; Deep learning; LSTM; Water quality prediction; Constructed wetlands; Multi-source data fusion
• ISSN: 2666-4984; 2096-9643; 2666-4984
• DOI: 10.1016/j.ese.2022.100207

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. [Display omitted] •Four prediction models are successfully established through multisource data fusion.•The LSTM shows a satisfactory forecast accuracy.•The moving average method can obviously improve the accuracy of the GA-BPNN.