Landslides cause severe ecological, human, and economic losses globally, with Fuyuan County in Yunnan Province, China, being a typical case. Accurate landslide susceptibility mapping (LSM) is crucial for disaster prevention and mitigation. Traditional methods struggle to meet contemporary needs, so this study employs advanced integrated machine learning models (LightGBM and XGBoost) to assess landslide susceptibility in the county, comparing them with traditional models. The LightGBM model performed best, achieving an AUC of 0.89, accuracy of 84.10%, and F1-score of 83.17%. It also demonstrated excellent stability—characterized by low uncertainty, narrow confidence intervals, and consistent discriminative ability across multiple resamplings—with outstanding reliability. Frequency ratio analysis identified key factors facilitating landslides: weak mudstone lithology, proximity to rivers (<200 m), and high mining density (0.098–0.149). Dense vegetation and hard limestone, however, reduce landslide risks. SHAP analysis further revealed that mining density is the most significant influencing factor, with a synergistic effect with river proximity that jointly exacerbates landslide susceptibility. The generated susceptibility zoning map identifies most areas of Dahe Town, Yingshang Town, and Zhuyuan Town as very high susceptibility zones, which highly aligns with historical landslide records and field survey results. The study emphasizes the need to strictly restrict mining activities in very high susceptibility zones and riparian areas, while comprehensively implementing slope reinforcement, vegetation restoration, and mine reclamation measures. These findings provide a scientific theoretical framework for global landslide research.

Since the operation of Xiaolangdi (XLD) Water Conservancy Hub, the reservoir area has witnessed significant changes in eco-environment through the impoundment, and some suggestions can be put forward for the future ecological construction of reservoirs by comparing these changes. This article explores the variation of microclimate, soil erosion, forest and grass coverage, regional animal and plant diversity, and ecotourism resources in the past two decades, and summarizes the contributions of XLD to the following aspects: the eco-environment protection and restoration, the construction of an ecological corridor and a biodiversity conservation network, and the eco-economic development of the Yellow River Basin. On this basis, three suggestions were presented for the ecological construction of XLD in the future: (1) carry out the ecological evaluation of XLD reservoir; (2) implement high-quality afforestation and beautification of the reservoir area; and (3) build a smart ecological monitoring system for XLD.

This paper assesses the sustainability impacts in the middle and lower reaches of the Yellow River in China after the Xiaolangdi Dam was constructed. Based on land use data interpreted from Landsat remote sensing images, covering the time period from 2000 to 2020 at 5-year intervals, this research uses a land dynamic attitude index and comprehensive index of land use degree to reveal the degree of land use type change in the study area and analyze the relationship between land use and social economy. The results show that urban and rural construction land is the land use type with the largest annual change rate, and the increase is most obvious from 2005 to 2010, growing by nearly 900 km². The six types of land use in the research area changed sharply from 2000 to 2010, with grassland and unused land showing the most significant change. On the whole, the dynamic attitude of comprehensive land use tends to be stable. The comprehensive index analysis of land use degree indicates that the study area has developed in the direction of urban settlement. Population and GDP are the main driving factors affecting the constant change in land use types in this region, in which population growth and rapid economic development are the main factors leading to the decline of grassland area, and are also the main driving factors for the expansion of construction land. The research results provide a scientific basis for sustainable land use and development in the middle and lower reaches of the Yellow River Basin.

Research on soil moisture estimation models can effectively improve the growth environment of crops. In this paper, the author studied the artificial neural network and variation pattern of soil moisture. Then, application of the model for water diversion estimation was explored based on artificial neural network. On this basis, an optimization algorithm was presented to simulate water diversion. Furthermore, a model for remote sensing of soil moisture dynamics was applied to artificial neural network. It has been proven that the research can optimize the application of the proposed model, laying a solid foundation for future study.

Land-use transformation driven by large-scale water conservancy projects profoundly reshapes regional ecosystem structures and the supply capacity of ecosystem services, yet targeted quantitative assessments linking land-use evolution to ecosystem service values (ESV) in the Xiaolangdi Reservoir resettlement zone remain insufficient, restricting scientific ecological management and territorial spatial governance for reservoir-affected counties and districts. This study draws on the latest ecosystem service valuation theories proposed by domestic and international scholars and applies the value equivalence method to quantify variations in land-use pattern changes and ESV across nine resettlement counties and districts (including the Sanmenxia urban area) affected by the Xiaolangdi Reservoir relocation project. Data collected included historical records (1995–2020), digital elevation models (DEM, 30 m resolution), and land-use information. By applying value equivalence theory and analyzing land-use change impacts, the study calculated changes in ESV and conducted sensitivity analyses across different land types. The findings reveal significant impacts on surrounding counties following the reservoir’s completion. Data indicate that the expansion of water areas drove the total ESV to rise from US$3.3261 billion in 1995 to a peak of US$3.6557 billion in 2010, followed by a decline to US$3.6128 billion in 2020. The most pronounced changes occurred during the first five years post-reservoir filling (2000–2005), marked by elevated water sensitivity indices. This research clarifies the differentiated responses of ecosystem service functions to land-use changes across reservoir-affected counties, provides quantitative decision-making support for coordinated ecological restoration, cultivated land protection, and sustainable land management in the resettlement area of the Xiaolangdi Reservoir, and offers a replicable technical framework for ecosystem service valuation of large sediment-laden river reservoir regions worldwide.