Understanding the spatiotemporal characteristics of water yield and its influencing factors is important for water resources management. In this study, we used the seasonal water yield model (SWYM) to assess the spatiotemporal water yield changes of the Lhasa River Basin from 1990 to 2015, and analyzed its influencing factors by focusing on precipitation, land cover, and normalized difference vegetation index (NDVI) change. We first examined the model through Morris screening sensitivity analysis and validated it with the observed flow data. Spatiotemporal variation of three indices of water yield, baseflow, quick flow, and local recharge were then assessed. Results showed that from 1990 to 2015, the baseflow, local recharge, and quick flow decreased by 67.03%, 80.21%, and 37.03%, respectively. The spatial pattern of water yield remained mostly unchanged. According to the contribution analysis, precipitation and NDVI change were the main factors affecting water yield in the Lhasa River Basin, while land cover change began to exert greater influence after 2010. A combination of climate change and human activities therefore drive water yield change, especially through vegetation change. Water resources management strategies should thus take into account the combination of rapidly changing climate and human activities.

Water quality plays a pivotal role in human health and environmental sustainability. However, traditional water quality prediction models are limited by high model complexity and long computation time, whereas AI models often struggle with high-dimensional time series and lack physical interpretability. This paper proposes a two-dimensional water quality surrogate model that couples physical numerical models and AI. The model employs physical simulation results as input, applies spectral proper orthogonal decomposition to reduce the dimensionality of the simulation results, utilizes a long short-term memory neural network for matrix forecasting, and reconstructs the two-dimensional concentration field. The simulation and predictive performance of the surrogate model were systematically evaluated through four design scenarios and three sampling dataset lengths, with a particular focus on the convection–diffusion zone and high-concentration zone. The results indicated that the model achieves high prediction accuracy for up to 7 h into the future, with sampling dataset lengths ranging from 20 to 80 h. Specifically, the model achieved an average R² of 0.92, a MAE of 0.38, and a MAPE of 1.77%, demonstrating its suitability for short-term water quality predictions. The methodology and findings of this study demonstrate the significant potential of integrating spectral proper orthogonal decomposition and deep learning for water quality prediction. By overcoming the limitations of traditional models, the proposed surrogate model provides high-accuracy predictions with enhanced physical interpretability, even in complex, dynamic environments. This work offers a practical tool for rapid responses to water pollution incidents and supports improved watershed water quality management by effectively capturing pollutant diffusion dynamics. Furthermore, the model’s scalability and adaptability make it a valuable resource for addressing intelligent management in environmental science.

To meet the demand for water temperature prediction in the ecological operation of reservoirs, this study presents a long-term water temperature forecasting model based on machine learning algorithms using the Yidu spawning grounds, located downstream of the Three Gorges Reservoir (TGR), as a case study. The results demonstrated that the transfer learning model outperformed conventional models in terms of prediction accuracy, forecast duration, and computational efficiency. Specifically, the transfer learning model achieved an average error of 0.16–0.35 °C, outperforming the conventional model (with an error range of 0.15–0.6 °C), and exhibited superior capability in capturing complex water temperature variations. Regarding computational efficiency, the transfer learning model required significantly less training time and adapted rapidly to new data, enhancing the practical applicability of the model. During the critical ecological operation period (May–June), the transfer learning model’s average absolute error was 0.2–0.3 °C, effectively supporting optimal selection of the reservoir’s ecological operation timing. The findings provide a scientific basis for decision making in the integrated operation of reservoirs.

As a political, economic and cultural center of the Tibet Autonomous Region, the Lhasa River needs to take planning and management of the basin. In the past 60 years, the temperature of Lhasa River Basin has been increasing gradually at an annual rate of 0.047 ° C, which leads to the water cycle variation of the river basin and its associated aquatic ecology and environment continue to change and evolve, and ecological environmental protection is affected by more uncertain factors. Based on the assessment of the ecological environment of the Lhasa River Basin, the comprehensive planning suggestions for the Lhasa River Basin were proposed from the aspects of water environment, land use, ecological pattern, and economic and social development. These suggestions are drawn on the examples of integrated planning and management of catchment in foreign countries and are referred to as the comprehensive planning of the seven major river basins in China.