A Synergetic Analysis of Sentinel-1 and -2 for Mapping Historical Landslides Using Object-Oriented Random Forest in the Hyrcanian Forests

A synergetic analysis of Sentinel-1 and -2 data, combined with digital elevation model (DEM) derivatives, demonstrates high sensitivity—86.6% and 80.3% respectively—in mapping historical landslides in the Hyrcanian Forests using an object-oriented random forest approach. The study highlights that Sentinel-2A features and topographic indices are the most influential for distinguishing old landslides, while textural, spectral, contextual, and topographic features collectively predict new landslides more effectively. This research advances the use of remote sensing in detecting historical landslides, though it notes variability across different forest areas.

Shirvani, Z., Abdi, O., & Buchroithner, M. (2019). A Synergetic Analysis of Sentinel-1 and -2 for Mapping Historical Landslides Using Object-Oriented Random Forest in the Hyrcanian Forests. Remote Sensing, 11(19), 2300. https://doi.org/10.3390/rs11192300