To investigate the pollution characteristics of the surface sediments of the river–reservoir system in the Feiyun River basin, a sediment heavy metal survey was conducted for the first time in the Feiyun River basin. Surface sediments from 21 sampling sites in the Feiyun River basin were collected, and the concentrations and spatial distribution characteristics of 15 heavy metals (Cr, Ni, Cu, Zn, As, Cd, Pb, Mn, V, Co, Mo, Sb, W, Fe, and Se) were analyzed. Three heavy metal ecological risk assessment methods were used to evaluate the potential risks of heavy metals in sediments, and the sources of major heavy metals were traced by correlation analysis and principal component analysis. The results show that (1) the average concentration of heavy metals (As) (212.64 mg/kg) and (Sb) (4.89 mg/kg) in Feiyun River Basin is 33.3 and 6.89 times the background value of Zhejiang Province; the overall spatial distribution of heavy metals is: the mainstream of Feiyun River > Zhaoshandu Reservoir > Shanxi Reservoir, thereby, the pollution is relatively significant; (2) by processing the geo-accumulation index and enrichment index methods, As and Sb are classified as ‘severely polluted’, ‘moderately severely polluted’ and ‘severely polluted’, ‘very severe polluted’ respectively; (3) the potential ecological index evaluates the surface sediments in the Feiyun River Basin as a very high risk level, the main environmental risk factors are As, Sb, Cd and Mo; (4) the principal component analysis results show that the heavy metals in the sediments of the Feiyun River Basin may be mainly affected by human activities such as sewage from domestic and agricultural activities, mining and smelting, and the others are affected by natural factors.

Changes in the hydrological cycle and water resources are inevitable consequences of environmental change, and runoff is an important element of the hydrological cycle. Therefore, the assessment of runoff changes is crucial for water resources management and socio-economic development. As an inland river basin in the arid zone of northwest China, the Shiyang River Basin is very vulnerable to environmental changes. Consequently, this study evaluated the past runoff evolution of the Shiyang River basin using a variety of statistical tools. In addition, the improved Soil and Water Assessment Tool (SWAT) was used to predict runoff trends from 2019 to 2050 under potential future climate change and land use projection scenarios in the future for the Shiyang River Basin. In the inland river basins, water resources mainly come from headwaters of the rivers in the upper mountainous regions, where they are more sensitive. Therefore, this study not only examined the mainstream of the Shiyang River, but also the six tributaries in the upper stream. The results indicate that the mainstream of the Shiyang River Basin and its six upstream tributaries all showed declining trends from the 1950s to 2019, and most of the rivers will continue to insignificantly decrease until 2050. Furthermore, there are two main timescales for runoff in the past as well as future: one is around 40 years and another is 20–30 years. In the meantime, the Shiyang River and its tributaries have relatively consistent change characteristics. The results of this study will provide assistance to basin management agencies in developing more appropriate water resource management plans.

Global climate change and human activities have exacerbated droughts’ environmental and socioeconomic threats. However, there is still a lack of effective techniques to consider their combined impacts on drought identification. Therefore, a new copula-based multivariate standardized drought index (CMSDI) was proposed, which integrates precipitation data and terrestrial water storage anomaly (TWSA) data observed by Gravity Recovery and Climate Experiment (GRACE) satellites. The applicability of the CMSDI was assessed compared with the water storage deficits index (WSDI), the self-calibration Palmer drought severity index (sc-PDSI), the standardized precipitation evapotranspiration index (SPEI), and the standardized precipitation index (SPI) in the Yellow River Basin (YRB) and the Yangtze River Basin (YZRB) for 2002–2020. The assessments were conducted regarding both temporal evolution and spatial distribution. The results showed that the CMSDI was more synchronized with the WSDI and SPI than with the other two indices and presented different trends and correlations in the YRB and YZRB. The CMSDI outperformed the other drought indices due to the limitations of the sc-PDSI, SPEI, and SPI in detecting certain drought events, and the greater inaccuracy of the WSDI in identifying extreme droughts. Furthermore, the CMSDI revealed a clear upward trend in parts of the middle and lower YRB and a clear downward trend in the upper YZRB, emphasizing the need for more attention to droughts in the YRB. This study presents a new perspective on the integrated use of satellite and measured data in drought monitoring across different regions.

In recent years, machine learning, a popular artificial intelligence technique, has been successfully applied to monthly runoff forecasting. Monthly runoff autoregressive forecasting using machine learning models generally uses a sliding window algorithm to construct the dataset, which requires the selection of the optimal time step to make the machine learning tool function as intended. Based on this, this study improved the sliding window algorithm and proposes an interval sliding window (ISW) algorithm based on correlation coefficients, while the least absolute shrinkage and selection operator (LASSO) method was used to combine three machine learning models, Random Forest (RF), LightGBM, and CatBoost, into an ensemble to overcome the preference problem of individual models. Example analyses were conducted using 46 years of monthly runoff data from Jiutiaoling and Zamusi stations in the Shiyang River Basin, China. The results show that the ISW algorithm can effectively handle monthly runoff data and that the ISW algorithm produced a better dataset than the sliding window algorithm in the machine learning models. The forecast performance of the ensemble model combined the advantages of the single models and achieved the best forecast accuracy.