Evaluation of four bias correction methods and random forest model for climate change projection in the Mara River Basin, East Africa

Abstract This study evaluates the performance of four bias correction methods based on CORDEX (coordinated regional climate downscaling experiment) domain six models (RCMs) at Mara River Basin. A suitable method was considered to develop future scenario. The evaluated by various statistical metrics historical period and revealed that distribution mapping (DM) techniques have strong under different climatic conditions. effectiveness DM is found be better capturing coefficient variation standard deviation observed rainfall temperature. Therefore, this considers (2026–2095) from bias-corrected RCMs output using techniques. results bias-adjusted show an increase (+118.3%) temperature (+2.91) in Representative Concentration Pathways (RCPs) 2.6, 4.5 8.5. In addition, tested random forest (RF) determine capacity each for reproducing RCP 8.5 demonstrate RF can reproduce variable with its average correlation (R2) 0.93 0.95