PreDisM: Pre-Disaster Modelling With CNN Ensembles for At-Risk Communities (Papers Track)

Vishal Anand (Columbia University); Yuki Miura (Columbia University)

Paper PDF Slides PDF Recorded Talk NeurIPS 2021 Poster Cite
Disaster Management and Relief Buildings Computer Vision & Remote Sensing Interpretable ML

Abstract

The machine learning community has recently had increased interest in the climate and disaster damage domain due to a marked increased occurrences of natural hazards (e.g., hurricanes, forest fires, floods, earthquakes). However, not enough attention has been devoted to mitigating probable destruction from impending natural hazards. We explore this crucial space by predicting building-level damages on a before-the-fact basis that would allow state actors and non-governmental organizations to be best equipped with resource distribution to minimize or preempt losses. We introduce PreDisM that employs an ensemble of ResNets and fully connected layers over decision trees to capture image-level and meta-level information to accurately estimate weakness of man-made structures to disaster-occurrences. Our model performs well and is responsive to tuning across types of disasters and highlights the space of preemptive hazard damage modelling.

Recorded Talk (direct link)

Loading…