Enhancing Meteorological Drought Modeling Accuracy Using Hybrid Boost Regression Models: A Case Study from the Aegean Region, Türkiye

The impact of climate change has led to significant changes in hydroclimatic patterns and continuous stress on water resources through frequent wet dry spells. Hence, understanding effectively addressing the escalating patterns, especially context meteorological drought, necessitates precise modeling these phenomena. This study focuses assessing accuracy drought using well-established Standard Precipitation Index (SPI) Aegean region Türkiye. utilizes monthly precipitation data from six stations Cesme, Kusadasi, Manisa, Seferihisar, Selcuk Izmir at Kucuk Menderes Basin covering period 1973 2020. dataset is divided into three sets, training (60%), validation (20%), testing (20%) sets. aims determine SPI-3, SPI-6 SPI-12 a multi-station prediction technique. Three boosting regression models (BRMs), namely Extreme Gradient Boosting (XgBoost), Adaptive (AdaBoost), (GradBoost), were employed optimized with help Weighted Mean Vectors (INFO) Model performances then evaluated Root Square Error (RMSE), Absolute (MAE), Percentage (MAPE), Coefficient Determination (R2) Willmott (WI). Results demonstrated distinct superiority XgBoost model over AdaBoost GradBoost terms accuracy. During test phase, achieved RMSEs 0.496, 0.429 0.389 for SPI-12, respectively. WIs 0.899, 0.901 0.825 These are considerably lower than corresponding values obtained by other models. Yet, comparative statistical analysis further underscores effectiveness extended periods