ASSESSMENT OF THE ECOLOGICAL STATUS OF GEOSYSTEMS IN THE SYRDARYA REGION USING GIS TECHNOLOGIES AND ARTIFICIAL INTELLIGENCE

Abstract

The article presents a methodology for the comprehensive assessment of the ecological status of geosystems in the Syrdarya Region using remote sensing, Geographic Information Systems (GIS), and machine learning methods. In the study, Sentinel-2 and Landsat 8/9 data, along with terrain, climate, and soil layers, are processed using Google Earth Engine and QGIS. The ecological status is assessed using the Remote Sensing-based Ecological Index (RSEI) and Analytic Hierarchy Process (AHP)-weighted indices based on vegetation cover, moisture, soil salinity, land surface temperature, and dryness indicators. Random Forest, XGBoost, and U-Net models are employed for classification and prediction, and their performance is evaluated using Overall Accuracy (OA), Kappa, F1-score, Root Mean Square Error (RMSE), and the coefficient of determination (R²).

Keywords

geosystem, ecological status, GIS, remote sensing, artificial intelligence, machine learning, RSEI, soil salinity, Syrdarya Region.