Litcius/Paper detail

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

Catherine Pennington, Rémy Bossu, Ferda Ofli, Muhammad Imran, Umair Qazi, Julien Roch, Vanessa Banks

2022International Journal of Disaster Risk Reduction25 citationsDOIOpen Access PDF

Abstract

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. 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.

Topics & Concepts

LandslideSocial mediaComputer scienceStakeholderConvolutional neural networkSoftware deploymentArtificial neural networkArtificial intelligenceRemote sensingData scienceMachine learningWorld Wide WebEngineeringGeologySoftware engineeringGeotechnical engineeringPolitical sciencePublic relationsLandslides and related hazardsSeismology and Earthquake StudiesFlood Risk Assessment and Management