Surface displacement detection using object-based image analysis, Tashkent region, Uzbekistan

Landslides can be listed as a major natural hazard for the Bostanlik district, Uzbekistan characterized by its mountain terrain. Currently, monitoring system is not in place, which mitigate numerous negative effects of landslides. The current study presents first Earth Observation-based landslide inventory Uzbekistan. We applied random forest Object-Based Image Analysis (OBIA) on very high-resolution GeoEye-1 observation data to detect surface displacement. While performing 10-fold cross-validation assess classification accuracy. Our results indicate high overall accuracy (0.93) and user’s (0.87) producer’s (0.91) displacement class. determined that 5.5% area was classified obtained are highly valuable local authorities management landslides, prevention, land use planning.