mwBTFreddy: A Dataset for Flash Flood Damage Assessment in Urban Malawi

TL;DR

The mwBTFreddy dataset provides paired satellite images and damage annotations to aid machine learning models in assessing urban flood damage in Malawi, supporting disaster response and urban planning.

Contribution

This paper introduces a novel dataset with labeled satellite images for flood damage assessment in Malawi, addressing a gap in African urban disaster datasets.

Findings

Dataset includes pre- and post-disaster satellite images with damage labels.

Supports development of ML models for damage detection and classification.

Facilitates flood impact visualization and spatial analysis.

Abstract

This paper describes the mwBTFreddy dataset, a resource developed to support flash flood damage assessment in urban Malawi, specifically focusing on the impacts of Cyclone Freddy in 2023. The dataset comprises paired pre- and post-disaster satellite images sourced from Google Earth Pro, accompanied by JSON files containing labelled building annotations with geographic coordinates and damage levels (no damage, minor, major, or destroyed). Developed by the Kuyesera AI Lab at the Malawi University of Business and Applied Sciences, this dataset is intended to facilitate the development of machine learning models tailored to building detection and damage classification in African urban contexts. It also supports flood damage visualisation and spatial analysis to inform decisions on relocation, infrastructure planning, and emergency response in climate-vulnerable regions.