Here we present a high-resolution landslide susceptibility model for Guiyang County, China, developed to support sustainable disaster risk management. Our approach couples optimized positive and negative training samples with an ensemble of machine-learning algorithms to maximize predictive fidelity. We compiled a georeferenced inventory of 146 landslides by integrating historical records with systematic field validation. Sample optimization was central to our methodology: landslide presence points were refined via buffer-based dilution, and four classifiers—SVM, LDA, RF, and ET—were trained with identical covariate sets to ensure comparability. Three strategies for selecting pseudo-absences—buffering, low-slope filtering, and coupling with the IOE—were benchmarked. The Slope-IOE-O model, which synergizes low-gradient screening with entropy-weighted sampling, yielded the highest predictive capacity (AUC = 0.965). SHAP-based interpretability revealed that slope, monthly maximum rainfall, surface roughness, and elevation collectively dominate susceptibility, with pronounced non-linearities and interactions. Slope contribution peaks at 20–30°, monthly maximum rainfall exhibits a critical threshold near 225 mm, and the synergy between high roughness and road density amplifies landslide risk. Spatially, susceptibility follows a pronounced north–south gradient, with high-hazard corridors aligned along northern and southern mountain belts and the urban core of southern Guiyang County. By integrating rigorously curated training data with robust machine-learning workflows, this study provides a transferable framework for proactive landslide risk assessment, offering scientific support for sustainable land-use planning and resilient development in mountainous regions.

Scrub typhus has emerged as a life-threatening and increasingly prevalent vector-borne disease. While the spatial and temporal distributions of scrub typhus have been studied by the research community, the main driving factors that influence the spatiotemporal patterns of the disease remain under investigation. Using Guangdong Province as a case study, we combined monthly scrub typhus case data from 2010 to 2019 and environmental and vector-related datasets with a Bayesian hierarchical mixed model to elucidate the spatiotemporal characteristics of the disease. This study revealed that the most highly endemic areas of scrub typhus are concentrated in the western and southern parts of Guangdong Province. A distinct bimodal pattern of scrub typhus was observed, with peaks typically occurring from May to July and October to November. The fitted model indicated that forest, cropland, and chigger mites were positively associated with scrub typhus transmission. Furthermore, climate and vectors were identified as key factors shaping the bimodal seasonal patterns of scrub typhus. Despite data-related limitations, including the treatment of population as a time-invariant variable and the binary simplification of vector suitability, sensitivity analyses confirmed the robustness of the model, offering valuable insights for scrub typhus prevention in Guangdong.

Echinococcosis poses a major public-health challenge and substantial socioeconomic burdens in pastoral regions. Yet the spatial transmission risks in China and their drivers remain insufficiently understood. Using a national cross-sectional survey of human and animal echinococcosis (2012-2016), we applied ensemble machine-learning models to identify environmental determinants of disease distribution, predict infection risk in animal hosts, and project human transmission risk. Model-predicted animal-host infection risk increased under humid, low-temperature conditions. Human cystic echinococcosis (CE) shows positive, non-linear associations with predicted infection risk in dogs and cattle, whereas human alveolar echinococcosis (AE) is positively, non-linearly associated with predicted infection risk in rodents and dogs. High-risk areas for sheep and dog infection are projected mainly in Qinghai, northwestern Tibet, Xinjiang, northern Inner Mongolia, and central Gansu, with broader extent than for cattle or rodents. The Tibetan Plateau emerges as a hotspot for human CE, while human AE risk concentrates along the Qinghai-Sichuan-Tibet border regions. These findings clarify environment-host-human linkages and provide a framework for targeted surveillance and control of echinococcosis under climate change.

China has experienced extensive forest expansion alongside rapid urbanization and large-scale population redistribution over the past three decades, yet how these transformations have reshaped the spatial relationship between people and different forest types remains unclear. Here, we quantified changes in forest–population relationships across China from 1990 to 2020 using forest area per person (FAP), forest-proximate people (FPP), and the forest–human nexus (FHN), for all forests combined and for natural and planted forests separately. Although total forest area increased by 9.3%, population growth resulted in an 11.5% decline in FAP. The share of the population living within 5 km of any forest increased from 57.4% to 62.4%, but divergent trajectories emerged between forest types: proximity to natural forest declined from 56.2% to 51.3%, whereas proximity to planted forest increased from 30.5% to 47.5%. FHN for all forests increased by 26.2% and planted-forest FHN by 59.5%, while natural-forest FHN remained broadly stable (−1.9%). Shapley decomposition further revealed substantial spatial heterogeneity in the contributions of forest change and population redistribution, with forest change contributing most to increases in FHN for all forests and planted forests at the national scale, while the two processes acted in opposing directions for natural forests. These findings provide a more complete, population-explicit perspective on China’s evolving human–forest relationship and offer a spatial basis for sustainable forest management, conservation, restoration, and land-use planning.