Understanding long-term hydroclimatic variability in arid and semi-arid regions is essential for sustainable water resource management in the context of accelerating climate change. This study examines historical trends (1950-2024) and data-driven extrapolations to 2040 for precipitation and temperature across 30 secondary river basins in Iran using ERA5 reanalysis dataset and the Light Gradient Boosting Machine (LightGBM) model. Results reveal pronounced spatial heterogeneity in precipitation, with more than two-thirds of basins showing median values of 0 mm, reflecting extreme rainfall intermittency. Long-term analysis indicates significant precipitation increases in northern basins, whereas decadal trends show widespread drying since the early 2000s, particularly in eastern regions (30-60 mm per decade). Mean, maximum, and minimum temperatures exhibit significant upward trends (0.015-0.045 degrees C yr-1), with stronger warming in northern and northwestern basins; however, minimum temperatures increased faster than maximum temperatures, reducing the diurnal temperature range and indicating a shift in regional thermal dynamics. Maximum temperature is negatively correlated with precipitation (R approximate to -0.27 to -0.34), suggesting enhanced evapotranspiration under warming conditions. LightGBM extrapolations to 2040 indicate continued warming (1-3 degrees C) and precipitation declines across more than 80% of Iran, underscoring intensifying hydroclimatic stress and increasing challenges for water resource management in dryland environments.