The common practice of identifying landslides is visual interpretation which, however, is labor-intensive and time-consuming. Thus, this hack will focus on automating the landslide identification process using artificial intelligence techniques, and target at using high-resolution terrain information to perform the terrain-based landslide identification.

The objective of this hackathon is to classify if a landslide occured or not.

There are ~10 000 entries in the train file and ~5 000 in the test file. Data is not neccesarily balanced.

Deep Dive Slides

The slides for the two deep dives, the technical one and the disaster-management related one, will be uploaded after the presentation on Wednesday, the 23rd of March at around 10 PM. However we strongly encourage you to attend these presentations to catch a glimpse of the team and the possibility to ask questions directly after.