Li Qiang, Yang Yinqun, Yang Ling, Wang Yonggui
Key Laboratory of Regional Ecology and Environmental Change, School of Geography and Information Engineering, China University of Geosciences, Wuhan, China.
Changjiang Water Resources Protection Institute, Wuhan, 430051, China.
Environ Sci Pollut Res Int. 2023 Jan;30(3):7498-7509. doi: 10.1007/s11356-022-22758-7. Epub 2022 Aug 30.
As the most water shortage and water polluted area in China, the water quality prediction is of utmost needed and important in Haihe River Basin for its water resource management. The long short-term memory (LSTM) has been a widely used tool for water quality forecast in recent years. The performance and adaptability of LSTM for water quality prediction of different indicators needs to be discussed before it adopted in a specific basin. However, literature contains very few studies on the comparative analysis of the various prediction accuracy of different water quality indicators and the causes, especially in Haihe River Basin. In this study, LSTM was employed to predict biochemical oxygen demand (BOD), permanganate index (COD), dissolved oxygen (DO), ammonia nitrogen (NH-N), total phosphorus (TP), hydrogen ion concentration (pH), and chemical oxygen demand digested by potassium dichromate (COD). According to results under 24 different input conditions, it is demonstrated that LSTMs present better predicting on BOD, COD, COD, and TP (median Nash-Sutcliffe efficiency reaching 0.766, 0.835, 0.837, and 0.711, respectively) than NH-N, DO, and pH (median Nash-Sutcliffe efficiency of 0.638, 0.625, and 0.229, respectively). Besides, the performance of LSTM to predict water quality is linearly related to the maximum value of temporal autocorrelation and cross-correlation coefficients of water quality indicators calculated by maximal information coefficient with the coefficients of determination of 0.79 to approximately 0.80. This study would provide new knowledge and support for the practical application and improvement of the LSTM in water quality prediction.
作为中国水资源最为短缺且水污染最为严重的地区，海河流域的水质预测对于其水资源管理而言极为必要且重要。长短期记忆网络（LSTM）近年来已成为水质预测中广泛使用的工具。在将LSTM应用于特定流域之前，需要讨论其对不同指标水质预测的性能和适应性。然而，文献中很少有关于不同水质指标各种预测精度及其成因的对比分析研究，尤其是在海河流域。本研究采用LSTM预测生化需氧量（BOD）、高锰酸盐指数（COD）、溶解氧（DO）、氨氮（NH-N）、总磷（TP）、氢离子浓度（pH）和重铬酸钾消解的化学需氧量（COD）。根据24种不同输入条件下的结果表明，LSTM对BOD、COD、COD和TP的预测效果（中位纳什-萨特克利夫效率分别达到0.766、0.835、0.837和0.711）优于对NH-N、DO和pH的预测（中位纳什-萨特克利夫效率分别为0.638、0.625和0.229）。此外，LSTM预测水质的性能与通过最大信息系数计算的水质指标时间自相关和互相关系数的最大值呈线性相关，决定系数为0.79至约0.80。本研究将为LSTM在水质预测中的实际应用和改进提供新知识和支持。
