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

The development of a system that monitors social media continuously for general landsliderelated 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. The preliminary model was developed by training a convolutional neural network on the dataset. Quantitative verification of the system's performance during a real-world deployment shows that the system can detect landslide reports with Precision = 76%. The demonstrator model is currently running live https://landslide-aidr.qcri.org/service.php; the next stage of development will incorporate stakeholder and user feedback.

Automated summary

This paper describes and validates the development of a system that continuously monitors social media for landslide-related content and identifies the most relevant information using a landslide classification model. The system has been quantitatively verified to detect landslide reports with a precision of 76% during real-world deployment. The next stage of development will incorporate stakeholder and user feedback.