Abstract
<jats:p>Recent years have witnessed significant climatic changes and increasing environmental pressure globally, including in Uzbekistan, necessitating an objective regional assessment. This research develops an approach for forecasting the Environmental Health Index (EHI) by integrating statistical analysis and machine learning algorithms. Long-term meteorological data from 13 regions (temperature, humidity, wind speed) were normalized to construct the EHI, with the Random Forest regressor applied to model nonlinear dependencies. Model performance was validated using MAE, MSE, and ????2 metrics. For the first time, an EHI based on climatic factors was developed specifically for Uzbekistan using a data-driven approach with automated feature weighting. Results demonstrate a stable correlation between climate variables and environmental status, suggesting potential degradation in certain regions if current trends persist.</jats:p>