Average Tmin, Tmax, rainfall, malaria incedence in 30 districts were retrieved from the Rwanda Meteorological Agency and Rwanda’s Health Management Information System (HMIS) during 2010–2015. We applied an ensemble learning method, namely, Random Forest Model (RFM), to comprehensively estimate the effect of a changing climate on malaria incidence according to historical observations in Rwanda. Based on this forecasting model, we predict future malaria risk and its spatiotemporal changes under two distinct Shared Socioeconomic Pathways (SSP2-4.5 and SSP5-8.5).