A near-real-time global landslide incident reporting tool demonstrator using social media and artificial intelligence

The reporting of landslides and their impacts (damage and loss) varies widely across the globe reflecting a range of physical and socio-economic drivers and contexts and the attention of the mass media is not uniformly distributed across disaster-affected areas. The development of a system that monitors social media continuously for general landslide-related content using a landslide classification model to identify and retain the most relevant information is described and validated. The system harvests photographs in real-time from these data and tags each image as landslide or not-landslide. A training model was developed with input from computer scientists, geologists (landslide specialists) and social media specialists to establish a large image dataset that has then been applied to the live Twitter data stream.

This paper demonstrates the potential application of artificial intelligence for landslide recognition in images harvested from social media. In this study, the researchers aimed to develop a model that can detect landslides in social media image streams automatically and in real-time. For this purpose, the researchers created a large image collection from multiple sources with different characteristics to ensure data diversity. The collected images were assessed by three landslide specialists independently to attain high quality labels with almost substantial inter-annotator agreement.