High-precision water quality prediction plays a vital role in preventing and controlling river pollution. However, river water's highly nonlinear and complex spatio-temporal dependencies pose significant challenges to water quality prediction tasks. In order to capture the spatial and temporal characteristics of water quality data simultaneously, this paper combines deep learning algorithms for river water quality prediction in the river network area of Jiangnan Plain, China. A water quality prediction method based on graph convolutional network (GCN) and long short-term memory neural network (LSTM), namely spatio-temporal graph convolutional network model (ST-GCN), is proposed. Specifically, the spatio-temporal graph is constructed based on the spatio-temporal correlation between river stations, the spatial features in the river network are extracted using GCN, and the temporal correlation of water quality data is obtained by integrating LSTM. The model was evaluated using R2, MAE, and RMSE, and the experimental results were 0.977, 0.238, and 0.291, respectively. Compared with traditional water quality prediction models, the ST-GCN model has significantly improved prediction accuracy, better stability, and generalization ability.
Accurately predicting dissolved oxygen is of great significance to the intelligent management and control of river water quality. However, due to the interference of external factors and the irregularity of its changes, this is still a ticklish problem, especially in multi-step forecasting. This article mainly studies two issues: we first analyze the lack of water quality data and propose to use the random forest algorithm to interpolate the missing data. Then, we systematically discuss and compare water quality prediction methods based on attention-based RNN, and develop attention-based RNN into a multi-step prediction for dissolved oxygen. Finally, we applied the model to the canal in Jiangnan (China) and compared eight baseline methods. In the dissolved oxygen single-step prediction, the attention-based GRU model has better performance. Its measure indicators MAE, RMSE, and R2 are 0.051, 0.225, and 0.958, which are better than baseline methods. Next, attention-based GRU was developed into multi-step prediction, which can predict the dissolved oxygen in the next 20 hours with high prediction accuracy. The MAE, RMSE, and R2 are 0.253, 0.306, and 0.918. Experimental results show that attention-based GRU can achieve more accurate dissolved oxygen prediction in single-neural network and multi-step predictions.
26 August 2025 in Environmental Monitoring and Assessment
Agricultural non-point sources, as major sources of organic pollution, continue to flow into the river network area of the Jiangnan Plain, posing a serious threat to the quality of water bodies, the ecological environment, and human health. Therefore, there is an urgent need for a method that can accurately identify various types of agricultural organic pollution to prevent the water ecosystems in the region from significant organic pollution. In this study, a network model called RA-GoogLeNet is proposed for accurately identifying agricultural organic pollution in the river network area of the Jiangnan Plain. RA-GoogLeNet uses fluorescence spectral data of agricultural non-point source water quality in Changzhou Changdang Lake Basin, based on GoogLeNet architecture, and adds an efficient channel attention (ECA) mechanism to its A-Inception module, which enables the model to automatically learn the importance of independent channel features. ResNet are used to connect each A-Reception module. The experimental results show that RA-GoogLeNet performs well in fluorescence spectral classification of water quality, with an accuracy of 96.3%, which is 1.2% higher than the baseline model, and has good recall and F1 score. This study provides powerful technical support for the traceability of agricultural organic pollution.
Due to climatic and hydrological changes and human activities, eutrophication and frequent outbreaks of cyanobacteria are prominent in the Jiangnan Plain basin of China. Therefore, building a suitable model to accurately predict the phosphorus concentration in surface water is of practical significance to prevent the above problems. This study built 10 models to predict the phosphorus element in the surface water of the river network in the Jiangnan Plain. The main water types in the basin include the Yangtze River, the Beijing-Hangzhou Canal, and the Gehu Lake. The 10 models in different datasets have been comprehensively evaluated by the prediction accuracy and interpretability of the model, and the calculation of the partial dependence diagram (PDP) and SHAP has proved that there is a transparent response relationship between phosphorus and different factors. The results show that the Yangtze River, Beijing-Hangzhou Canal, and Gehu Lake are suitable for random forest, linear regression, and random forest models, respectively, under the comprehensive evaluation of the prediction accuracy and interpretability of the model. Models with low prediction accuracy often show strong interpretability. In different water body types, turbidity, water temperature, and chlorophyll-a are the three factors that affect the model in predicting phosphorus.
26 November 2024 in Science of The Total Environment