State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, China; Institute for Water-Carbon Cycles & Carbon Neutrality, Wuhan University, Wuhan 430072, China; Department of Civil and Environmental Engineering, National University of Singapore, 117578, Singapore.
State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, China; Institute for Water-Carbon Cycles & Carbon Neutrality, Wuhan University, Wuhan 430072, China; Key Laboratory of Water Cycle and Related Land Surface Processes, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China.
Water Res. 2024 Oct 1;263:122191. doi: 10.1016/j.watres.2024.122191. Epub 2024 Jul 30.
Pollution control and environmental protection of the Yangtze River have received major attention in China. However, modeling the river's pollution load remains challenging due to limited monitoring and unclear spatiotemporal distribution of pollution sources. Specifically, anthropogenic activities' contribution to the pollution have been underestimated in previous research. Here, we coupled a hydrodynamic-based water quality (HWQ) model with a machine learning (ML) model, namely attention-based Gated Recurrent Unit, to decipher the daily pollution loads (i.e., chemical oxygen demand, COD; total phosphorus, TP) and their sources in the Middle-Lower Yangtze River from 2014 to 2018. The coupled HWQ-ML model outperformed the standalone ML model with KGE values ranging 0.77-0.91 for COD and 0.47-0.64 for TP, while also reducing parameter uncertainty. When examining the relative contributions at the Middle Yangtze River Hankou cross-section, we observed that the main stream and tributaries, lateral anthropogenic discharges, and parameter uncertainty contributed 15, 66, and 19% to COD, and 58, 35, and 7% to TP, respectively. For the Lower Yangtze River Datong cross-section, the contributions were 6, 69, and 25% for COD and 41, 42, and 17% for TP. According to the attention weights of the coupled model, the primary drivers of lateral anthropogenic pollution sources, in descending order of importance, were temperature, date, and precipitation, reflecting seasonal pollution discharge, industrial effluent, and first flush effect and combined sewer overflows, respectively. This study emphasizes the synergy between physical modeling and machine learning, offering new insights into pollution load dynamics in the Yangtze River.
中国高度重视长江流域的污染控制和环境保护。然而，由于监测有限以及污染源的时空分布不明确，对该河流的污染负荷进行建模仍然具有挑战性。具体来说，在以前的研究中，人为活动对污染的贡献被低估了。在这里，我们将基于水动力的水质 (HWQ) 模型与机器学习 (ML) 模型（即基于注意力的门控循环单元）相结合，以破译 2014 年至 2018 年期间长江中下游地区的日污染负荷（即化学需氧量，COD；总磷，TP）及其来源。与独立的 ML 模型相比，耦合的 HWQ-ML 模型的 KGE 值范围为 0.77-0.91（用于 COD）和 0.47-0.64（用于 TP），同时还降低了参数不确定性。在检查汉口中游断面的相对贡献时，我们观察到干流和支流、侧向人为排放以及参数不确定性对 COD 的贡献分别为 15%、66%和 19%，对 TP 的贡献分别为 58%、35%和 7%。对于下游大通的长江断面，COD 的贡献分别为 6%、69%和 25%，TP 的贡献分别为 41%、42%和 17%。根据耦合模型的注意力权重，侧向人为污染源的主要驱动因素（按重要性降序排列）分别是温度、日期和降水，分别反映季节性污染排放、工业废水和初次冲刷效应以及合流制污水溢流。本研究强调了物理建模和机器学习之间的协同作用，为长江流域污染负荷动态提供了新的见解。
