A global landslide incident reporting demonstrator using AI to interpret social media imagery in near-real-time

This research has developed a system that monitors social media continuously for landslide-related content, using a landslide classification model to identify and retain the most relevant information. The system harvests photographs in real-time and interprets each image as landslide or not-landslide.  To achieve this, a training model was developed and tested through independent and collaborative working to establish a large image dataset that has then been applied to the live Twitter data stream.  This paper presents results from interdisciplinary research carried out by computer scientists at the Qatar Computing Research Institute (QCRI), earthquakes and social media specialists at the European-Mediterranean Seismological Centre (EMSC) and landslide hazard expertise from the British Geological Survey (BGS).