Augmented Statistics for Hydroclimatic Extremes: Spearman, Mann–Kendall, and AI Classification for Drought Risk Mapping

The effects of climate change are now evident on all scales, both global and local. Extreme events linked to climate change, such as heat islands and water bombs, are occurring with increasing frequency, causing significant harm to humans. Furthermore, rising temperatures also cause significant drought and desertification, which must be carefully assessed and analyzed. For this reason, with a view to evaluating environmentally sustainable development, the following research focuses on the variables that contribute to the reduction in local water availability in the province of Reggio Calabria, considering air temperature, evapotranspiration, precipitation, and available water resources. The Mann–Kendall test revealed a statistically significant increasing trend in air temperature (Z = +2.5, p < 0.01) and a decreasing tendency in precipitation, while the NDWI analysis indicated a reduction of about 34% in surface water resources between 2019 and 2023. The Spearman test showed strong negative correlations between temperature and water availability (ρ = −0.68) and between evapotranspiration and water availability (ρ = −0.66). Lastly, four artificial intelligence (AI) classifiers were compared: Random Forest, XGBoost, Gradient Boosting Decision Tree, and Logistic Regression. Random Forest performed the best, with 93% accuracy and 90% precision. The results confirm the strong negative dependence of temperature and evapotranspiration on water resources and identify Random Forest as the most reliable model for determining the area’s most at risk of drought.