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.