 This paper presents highly accurate ensemble machine learning models using reduced-error pruning tree, REPT, as a base classifier with bagging, decorate, and random subspace ensemble learning techniques for spatial prediction of rainfall-induced landslides in the Uttarkashi district, India. The results show that the DREPT model with RMSE equals 0.351 and AUC equals 0.907 is the most accurate model, followed by RSS-REPT, BREPT, and the single REPT model. These findings provide insights for engineers and modelers to develop more advanced predictive models for different landslide-susceptible areas around the world. This article was authored by Binti Femme, Bolfhassel Jafari, Trang Nuyendoi, and others.