A scenario-based case study: AI to analyse casualties from landslides in Chittagong Metropolitan Area, Bangladesh

This research uses the landslide inventory of Chittagong Metropolitan Area (CMA) to create a new Artificial Intelligence (AI) based insight system for the town planners and senior disaster recovery strategists of Chittagong, Bangladesh. The system generates dynamic AI-based insights for a range of complex scenarios created from 7 different landslide feature attributes. The users of the system can select a particular kind of scenario out of the exhaustive list of 1.054X1041 possible scenario sets and our AI-based system will immediately predict how many casualties are likely to occur based on the selected kind of scenario. Moreover, an AI-based system shows how landslide attributes (e.g., rainfall, area of mass, elevation, etc.) correlate with landslide casualty by drawing detailed trend lines performing both linear and logistic regressions.

In the future, the researchers will endeavor to work with more records on landslides outside of CMA regions. Using these large-scale records, they hope to deploy more sophisticated AI-based techniques like Convolution Neural Network (CNN) based deep learning to generate useful insights. Other than CNN, they also want to use sophisticated AI based techniques as demonstrated in our recent and past studies.