SATELLITE IMAGERY-BASED MONITORING OF ILLEGAL TREE-CUTTING ACTIVITIES FOR ECOLOGICAL INSPECTION AND ENVIRONMENTAL ENFORCEMENT

This study proposes an integrated satellite imagery-based monitoring framework for the rapid detection of illegal tree-cutting activities to support ecological control inspection officers. The proposed system combines multi-temporal optical imagery (Sentinel-2, Landsat 8/9, and PlanetScope) with Synthetic Aperture Radar (SAR) observations from Sentinel-1 to improve monitoring continuity under cloudy conditions. A hybrid methodology involving NDVI, NDFI, Spectral Mixture Analysis (SMA), Object-Based Image Analysis (OBIA), and machine learning classifiers such as Support Vector Machine (SVM), Random Forest (RF), and the 3DC automated approach is examined. Quantitative evaluation demonstrates that the 3DC model achieves the best overall performance with 93.1% accuracy, 90.6% precision, 92.8% recall, and 91.7% F1-score, outperforming classical vegetation-index-based methods.