Water quality ensemble prediction model for the urban water reservoir based on the hybrid long short-term memory (LSTM) network analysis

Abstract

The water quality of drinking water reservoirs directly impacts the water supply safety for urban residents. This study focuses on the Da Jing Shan Reservoir, a crucial drinking water source for Zhuhai City and the Macau Special Administrative Region. The aim is to establish a prediction model for the water quality of drinking water reservoirs, which can serve as a vital reference for water plants when formulating their water supply plans. In this research, after smoothing the data using the Hodrick-Prescott filter, we utilized the long short-term memory (LSTM) network model to create a water quality prediction model for the Da Jing Shan Reservoir. Simulation calculations reveal that the model's fitting degree is consistently above 60%. Specifically, the prediction accuracy for pH, dissolved oxygen (DO), and biochemical oxygen demand (BOD) in the water quality prediction model aligns with actual results by more than 70%, effectively simulating the reservoir's water quality changes. Moreover, for parameters like pH, DO, BOD, and total phosphorus, the relative forecasting error of the LSTM model is less than 10%, confirming the model's validity. The results of this study offer an essential model reference for predicting water quality for the Da Jing Shan Reservoir.