The construction of large reservoirs results in the formation of tributary bays, and tributary bays are inevitably influenced by backwater jacking and intrusions from the main reservoir. In this paper, a typical tributary bay (Tangxi River) of the Three Gorges Reservoir (TGR) was selected to study the hydrodynamic and environmental characteristics of a tributary bay influenced by the jacking and intrusions from the main reservoir. The flow field, water temperature, and water quality of Tangxi River were simulated using the hydrodynamic and water quality model CE-QUAL-W2 (thomas and Scott, 2008), and the eutrophication status of the tributary bay was also evaluated. The results showed that the main reservoir had different effects on its tributary bay in each month. The tributary bay was mainly affected by backwater jacking from the main reservoir when the water level of the main reservoir dropped and by intrusions from the main reservoir when the water level of the main reservoir rose. An obvious water quality concentration boundary existed in the tributary bay, which was consistent with the regional boundary in the flow field. The flow field and water quality on both sides of the boundary were quite different. The results of this study can help us figure out how the backwater jacking and intrusions from the main reservoir influence the hydrodynamic and water environment characteristics of the tributary bay and provide guidance for water environment protection in tributary bays.

The water quality index (WQI) is an important tool for evaluating the water quality status of lakes. In this study, we used the WQI to evaluate the spatial water quality characteristics of Dianchi Lake. However, the WQI calculation is time-consuming, and machine learning models exhibit significant advantages in terms of timeliness and nonlinear data fitting. We used a machine learning model with optimized parameters to predict the WQI, and the light gradient boosting machine achieved good predictive performance. The machine learning model trained based on the entire Dianchi Lake water quality data achieved coefficient of determination (R2), mean square error, and mean absolute error values of 0.989, 0.228, and 0.298, respectively. In addition, we used the Shapley additive explanations (SHAP) method to interpret and analyse the machine learning model and identified the main water quality parameter that affects the WQI of Dianchi Lake as NH4+-N. Within the entire range of Dianchi Lake, the SHAP values of NH4+-N varied from −9 to 3. Thus, in future water environmental governance, it is necessary to focus on NH4+-N changes. These results can provide a reference for the treatment of lake water environments.