SPATIO-TEMPORAL ANALYSIS OF LAND USE/LAND COVER CHANGES IN THE JIZZAKH REGION USING RANDOM FOREST ALGORITHM AND REMOTE SENSING DATA
Аннотация
This study aims to analyze spatio-temporal changes in land use and land cover (LULC) in the Jizzakh region of Uzbekistan between 2016 and 2022. The research is based on multi-temporal Sentinel-2 multispectral satellite imagery and applies the Random Forest machine learning algorithm for supervised classification. Cloud-free images acquired during the vegetation growing season were processed using QGIS with the Semi-Automatic Classification Plugin. The results indicate that bare land dominates the study area, covering 79.79% of the total area, while vegetation accounts for 17.45%, water bodies 2.72%, and urban areas 0.04%. Comparative analysis reveals an expansion of built-up areas and fluctuations in vegetation cover, reflecting the influence of anthropogenic activities and climatic conditions in a semi-arid environment. The study confirms the effectiveness of integrating remote sensing data with machine learning techniques for accurate LULC mapping and provides a reliable basis for environmental monitoring and sustainable land management.