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.