Endeavours into a more automated workflow for regional scale landslide and flash flood event detection in the tropics using IMCLASS

<p>Geomorphic hazards such as landslides and flash floods (hereafter called GH) often co-occur<br>and interact imposing significant impacts in the landscape. Particularly in the tropics, where<br>GH are under-researched while impact is disproportionally high, establishing regional-scale<br>inventories of GH events is essential to better understand the behaviour and the patterns in<br>GH event occurrence. Robust AI-based detection tools such as the IMCLASS classifier<br>provide an excellent solution to accurately determine the location of GH events. However,<br>they rely on accurate training samples and require some knowledge on the timing of the event.<br>This information is regularly unavailable when exploring for new GH events in inaccessible<br>areas such as the tropics. Here we present our first endeavours into an automated workflow<br>for detecting unknown events in the tropics using the IMCLASS detection tool associated to<br>an unsupervised building of training samples using time series of Copernicus Sentinel 2<br>imagery. Per pixel, we investigate the cumulative difference from the mean over time for a<br>multitude of spectral index time series (e.g. NDVI, BI, SAVI) and their related z-score time<br>series. The method allows us to distinguish GH-affected and non-affected pixels based on the<br>prominence of the peak, and determine an approximate timing based on the location of the<br>peak within the timeseries. Both information are then used as input for the IMCLASS<br>classifier. The method is highly optimized in terms of computation time allowing to process<br>large regions of interest. Preliminary results over Uvira, DRC and the Mahale Mountains,<br>Tanzania, have shown to be encouraging and provide insight into a more automated workflow<br>applicable on the regional scale where event occurrence and timing is yet unknown. Further<br>steps will consist of adapting the workflow to different landscape, topography and climatic<br>regions.</p>