Traditional river quality models struggle to accurately predict river water quality in watersheds dominated by non-point source pollution due to computational complexity and uncertain inputs. This study addresses this by developing a novel coupling model integrating a gradient boosting algorithm (Light GBM) and a long short-term memory network (LSTM). The method leverages Light GBM for spatial data characteristics and LSTM for temporal sequence dependencies. Model outputs are reciprocally recalculated as inputs and coupled via linear regression, specifically tackling the lag effects of rainfall runoff and upstream pollutant transport. Applied to predict the concentrations of chemical oxygen demand digested by potassium permanganate index (COD) in South China’s Jiuzhoujiang River basin (characterized by rainfall-driven non-point pollution from agriculture/livestock), the coupled model outperformed individual models, increasing prediction accuracy by 8–12% and stability by 15–40% than conventional models, which means it is a more accurate and broadly applicable method for water quality prediction. Analysis confirmed basin rainfall and upstream water quality as the primary drivers of 5-day water quality variation at the SHJ station, influenced by antecedent conditions within 10–15 days. This highly accurate and stable stack coupling method provides valuable scientific support for regional water management.
Zhang et al. (Wed,) studied this question.