Deng Rui, Zhu Tianci, Zhou Weilin, Liu Fang, Lin Xiaosong
School of Smart City, Chongqing Jiaotong University, No. 66 Xuefu Road, Nan'an District, Chongqing, 400074, China; Technology Innovation Center for Spatio-temporal Information and Equipment of Intelligent City, Ministry of Natural Resources, No. 6 Qingzhu East Road, Yubei District, Chongqing, 400021, China.
School of Smart City, Chongqing Jiaotong University, No. 66 Xuefu Road, Nan'an District, Chongqing, 400074, China; Chongqing Key Laboratory of Spatio-temporal Information in Mountain Cities, No. 66 Xuefu Road, Nan'an District, Chongqing, 400074, China.
Environ Pollut. 2025 Oct 1;382:126668. doi: 10.1016/j.envpol.2025.126668. Epub 2025 Jun 12.
Quantifying transport and transformation of pollutants in river systems regulated by reservoirs poses a long-standing scientific challenge. This mainly results from complex interactions between hydrodynamic and biogeochemical factors. In this study, we combined 48 months of high-frequency field monitoring data (January 2020 to December 2023) with Sentinel-2 multispectral imagery to explore the spatiotemporal dynamics of water quality parameters (WQPs) in the Yulin River, a crucial tributary of the Three Gorges Reservoir system. Four advanced machine learning algorithms-Extreme Gradient Boosting (XGBoost), Random Forest (RF), Categorical Boosting (CatBoost), and Gradient Boosted Decision Trees (GBDT)-were systematically evaluated regarding their capabilities for retrieving WQPs, including chemical oxygen demand (COD), total phosphorus (TP), total nitrogen (TN), and chlorophyll-a (Chla). The comparative analysis indicated that XGBoost outperformed other algorithms, achieving determination coefficients (R) from 0.9154 to 0.9488 and root mean square errors (RMSE) between 0.0267 and 1.7351 mg/L. These results underscored the robustness of XGBoost for large-scale water quality parameter retrieval. The findings show that hydrological regulation exerts predominant influence on pollutant dynamics. Specifically, the process of reservoir impoundment led to substantial surges in Chla concentrations, with an increase ranging from 100 % to 1000 % across 56.2 % of the study area. In contrast, TN concentrations exhibited relatively minor fluctuations, with a growth of ≤40 % in 70.7% of the area. Hydrological conditions exerted a profound influence on the concentrations of COD and Chla in estuarine regions. Specifically, during the low-flow period, their levels were markedly elevated compared to those in the high-flow periods. In contrast, meteorological factors showed weak correlations with all water quality parameters (|r| < 0.41). The XGBoost-based modeling approach successfully enabled high-precision monitoring at the watershed scale. The mean absolute errors (MAE) ranged from 0.0201 to 1.4277 mg/L, which offered crucial perspectives for the management of river ecosystems influenced by reservoirs.
量化受水库调节的河流系统中污染物的迁移和转化是一项长期存在的科学挑战。这主要源于水动力和生物地球化学因素之间的复杂相互作用。在本研究中，我们将48个月的高频现场监测数据（2020年1月至2023年12月）与哨兵 - 2多光谱图像相结合，以探索三峡水库系统重要支流——榆林河水质参数（WQPs）的时空动态。我们系统地评估了四种先进的机器学习算法——极端梯度提升（XGBoost）、随机森林（RF）、分类提升（CatBoost）和梯度提升决策树（GBDT）——检索水质参数的能力，这些参数包括化学需氧量（COD）、总磷（TP）、总氮（TN）和叶绿素 - a（Chla）。对比分析表明，XGBoost的性能优于其他算法，决定系数（R）在0.9154至0.9488之间，均方根误差（RMSE）在0.0267至1.7351mg/L之间（即RMSE范围为0.0267 - 1.7351mg/L）（中文习惯表述加上“范围为”更清晰）。这些结果强调了XGBoost在大规模水质参数检索方面的稳健性。研究结果表明，水文调节对污染物动态具有主要影响。具体而言，水库蓄水过程导致Chla浓度大幅激增，研究区域56.2%的范围内增幅在100%至1000%之间。相比之下，TN浓度波动相对较小，70.7%区域内的增幅≤40%。水文条件对河口区域COD和Chla的浓度有深远影响。具体来说，在枯水期，它们的值相较于丰水期明显升高。相比之下（此处加“之下”使表述完整），气象因素与所有水质参数显示出较弱的相关性（|r| < 0.41）。基于XGBoost的建模方法成功实现了流域尺度的高精度监测。平均绝对误差（MAE）范围为0.0201至1.4277mg/L，这为受水库影响的河流生态系统管理提供了关键视角。
