This study focuses on reducing uncertainty in flood susceptibility mapping using random forest (RF) and extreme gradient boosting (XGB) algorithms in two tropical desert cities, Shibam and Marib, Yemen. The research addresses the challenges of limited data, uncertainty due to confidence bounds, and overfitting, which are critical for improving model accuracy. The study created a spatial repository containing historical flooding data and twelve topographic and geo-environmental variables. The RF and XGB algorithms were applied to map flood susceptibility, incorporating a variable drop-off loop function to resolve model uncertainty. The results showed that the drop-off loop function effectively resolved model uncertainty associated with conditioning factors. Approximately 8.42% to 9.89% of Marib City and 9.93% to 15.69% of Shibam City areas were identified as highly vulnerable to floods. The study contributes to global efforts to reduce natural disaster risks and provides valuable insights and strategies for flood risk management in Yemen.This study focuses on reducing uncertainty in flood susceptibility mapping using random forest (RF) and extreme gradient boosting (XGB) algorithms in two tropical desert cities, Shibam and Marib, Yemen. The research addresses the challenges of limited data, uncertainty due to confidence bounds, and overfitting, which are critical for improving model accuracy. The study created a spatial repository containing historical flooding data and twelve topographic and geo-environmental variables. The RF and XGB algorithms were applied to map flood susceptibility, incorporating a variable drop-off loop function to resolve model uncertainty. The results showed that the drop-off loop function effectively resolved model uncertainty associated with conditioning factors. Approximately 8.42% to 9.89% of Marib City and 9.93% to 15.69% of Shibam City areas were identified as highly vulnerable to floods. The study contributes to global efforts to reduce natural disaster risks and provides valuable insights and strategies for flood risk management in Yemen.