Developing an ensemble machine learning framework for enhanced climate projections using CMIP6 data in the Middle East

Abstract Climate change in the Middle East has intensified with rising temperatures, shifting rainfall patterns, and more frequent extreme events. This study introduces the Stacking-EML framework, which merges five machine learning models three meta-learners to predict maximum temperature, minimum temperature, and precipitation using CMIP6 data under SSP1-2.6, SSP2-4.5, and SSP5-8.5. The results indicate that Stacking-EML not only significantly improves prediction accuracy compared to individual models and traditional CMIP6 outputs but also enhances climate projections by integrating multiple ML models, offering more reliable, regionally refined forecasts. Findings show R² improvements to 0.99 for maximum temperature, 0.98 for minimum temperature, and 0.82 for precipitation. Under SSP5-8.5, summer temperatures in southern regions are expected to exceed 45 °C, exacerbating drought conditions due to reduced rainfall. Spatial analysis reveals that Saudi Arabia, Oman, Yemen, and Iran face the greatest heat and drought impacts, while Turkey and northern Iran may experience increased precipitation and flood risks.