An Interpretable Deep Learning Framework for River Water Quality Prediction—A Case Study of the Poyang Lake Basin
Water · 21.08.2025 · 17 (16) · 2496
DOI: 10.3390/w17162496 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water, online erschienen am 21.08.2025. Verfasst von Ying Yuan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Fujian Province, China, Xiamen Natural Science Foundation Project.
Abstract (Originalsprache)
Accurate prediction of water quality involves early identification of future pollutant concentrations and water quality indicators, which is an important prerequisite for optimizing water environment management. Although deep learning algorithms have demonstrated considerable potential in predicting water quality parameters, their broader adoption remains hindered by limited interpretability. This study proposes an interpretable deep learning framework integrating an artificial neural network (ANN) model with Shapley additive explanations (SHAP) analysis to predict spatiotemporal variations in water quality and identify key influencing factors. A case study was conducted in the Poyang Lake Basin, utilizing multi-dimensional datasets encompassing topographic, meteorological, socioeconomic, and land use variables. Results indicated that the ANN model exhibited strong predictive performance for dissolved oxygen (DO), total nitrogen (TN), total phosphorus (TP), permanganate index (CODMn), ammonia nitrogen (NH3N), and turbidity (Turb), achieving R2 values ranging from 0.47 to 0.77. Incorporating land use and socioeconomic factors enhanced prediction accuracy by 37.8–246.7% compared to models using only meteorological data. SHAP analysis revealed differences in the dominant factors influencing various water quality parameters. Specifically, cropland area, forest cover, air temperature, and slope in each sub-basin were identified as the most important variables affecting water quality parameters in the case area. These findings provide scientific support for the intelligent management of the regional water environment.
Förderung
- Natural Science Foundation of Fujian Province, China
- Xiamen Natural Science Foundation Project
Zitieren
APA
Yuan, Y., Zhou, C., Wu, J., Deng, F., Liu, W., Sun, M., & Li, L. (2025). An Interpretable Deep Learning Framework for River Water Quality Prediction—A Case Study of the Poyang Lake Basin. Water, 17(16), 2496. https://doi.org/10.3390/w17162496
Vancouver
Yuan Y, Zhou C, Wu J, Deng F, Liu W, Sun M, et al. An Interpretable Deep Learning Framework for River Water Quality Prediction—A Case Study of the Poyang Lake Basin. Water. 2025;17(16):2496. doi:10.3390/w17162496
BibTeX
@article{Yuan2025,
author = {Yuan, Ying and Zhou, Chunjin and Wu, Jingwen and Deng, Fuliang and Liu, Wei and Sun, Mei and Li, Lanhui},
title = {An Interpretable Deep Learning Framework for River Water Quality Prediction—A Case Study of the Poyang Lake Basin},
journal = {Water},
year = {2025},
volume = {17},
number = {16},
pages = {2496},
doi = {10.3390/w17162496}
}
EUVIMED