Landslide mapping using object-based image analysis and open source tools

Availability of high-resolution optical imagery and advances in image processing technologies have significantly improved our ability to map landslides. In recent years object-based analysis (OBIA) has been gaining popularity for landslide mapping due its incorporate spectral, textural, morphological topographical properties. Many studies conducted based on commercial software. this study, we create an open source Semi-Automatic Landslide Detection (SALaD) system utilizing OBIA machine learning. Configured run Linux environment, it uses various Python packages modules. This was tested 575 km2 area along the Pasang Lhamu Highway, Nepal where large numbers landslides were triggered by 2015 Gorkha earthquake. Comparison with a manual inventory highlighted that able detect 70% area. The speed efficiency which makes viable alternative techniques over areas, when establishing approximate locations is prime importance.