Usutu virus (USUV) is an emerging flavivirus transmitted by mosquitoes, with an increasing incidence of human infection and a geographic expansion over the past decade, thereby posing a significant threat to public health. In this study, we conducted an extensive literature search and established a comprehensive spatiotemporal database of USUV infections in vectors, animals, and humans worldwide. Based on which, we explored the distribution dynamics of USUV infections and characteristics of human infections. By employing boosted regression trees (BRT) models, we projected the distributions of three main vectors (Culex pipiens, Aedes albopictus, and Culiseta longiareolata) and three main hosts (Turdus merula, Passer domesticus, and Ardea cinerea) to obtain the mosquito index and bird index. These indices were further incorporated as predictors into the USUV infection models, which was conducted by using three different machine learning models, BRT, random forest (RF), and least absolute shrinkage and selection operator (LASSO) logistic regression model. By selecting the best models for BRT, RF, and (LASSO) logistic regression model, and integrating them into ensemble learning model, we achieved a decent model performance with an area under the curve (AUC) of 0.992. The mosquito index contributed significantly, with relative contributions estimated at 25.51%. Our estimations revealed a potential exposure area for USUV spanning 1.80 million km² globally with approximately 1.04 billion people at risk, this would guide future surveillance efforts for USUV infections, especially for countries located within high-risk areas and those that have not yet conducted surveillance activities.

Hemorrhagic fever with renal syndrome (HFRS) poses a significant public health threat in China, yet its endemic distribution remains poorly defined. In this study, we collected HFRS cases and environmental factors from 2014 to 2018 in China and developed a two-stage ecological machine learning model to investigate the drivers, environment suitability, and potential risk areas of HFRS. Finally, we identified three endemic types, with Type I (HTNV-type dominant) accounting for approximately 16.96% of the total potential risk areas (468,000/2,759,000 square kilometers). Meteorological factors, crop fields, grassland, wetland, rural residential land, and normalized difference vegetation index were the main drivers in these endemic areas. Type II (SEOV-type dominant) risk areas, on the other hand, accounted for around 718,100 square kilometers (26.03%), with HFRS epidemics being primarily associated with the percentage of grassland, wetland, open woodland, rural residential land, urban construction rate, and meteorological factors. Type III(Mixed-type) endemic foci spanned large potential risk areas throughout mainland China, covering approximately 1,572,900 square kilometers (57.01% of the total potential endemic areas). Three HFRS-endemic areas in China varied in epidemic features, ecological drivers, and spatial risk areas. Targeted surveillance and intervention strategies were needed for different endemic areas to control the spread of HFRS.