This paper presents a methodology developed to assess if a potentially critical landslide event is displaying a significant deviation from previously sampled data, or if it could be classified as a false alarm.
Tajikistan’s southern Khatlon region, bordering Afghanistan, is the country’s populated and poorest region. It is home to two major rivers, the Panj and Vakhsh, and their multiple tributaries, making the region vulnerable to seasonal floods and mudflows.
The VIGIRISKS web platform, designed and developed by the French Geological Survey (BRGM), enables storing, scenario design, documentation, access and execution of scientific computations for multi-risks mapping.
The purpose of this preliminary study is to demonstrate that machine learning techniques can be used to analyze monitoring data in order to select the most relevant variables for the triggering of shallow rainfall-induced landslides at regional scale.