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

TL;DR

Addresses the scarcity of locally relevant data for flash flood damage assessment in Malawi. Presents mwBTFreddy, a dataset built from pre- and post-Cyclone Freddy satellite imagery of Blantyre, with building-level damage annotations. A pipeline using Google Earth Pro imagery, grid tiling, and QGIS-based annotation following the xBD damage scale yields 696 annotated instances across 348 pre- and 348 post-disaster images. The accompanying datasheet documents data provenance, exclusion criteria, and licensing, and the dataset is publicly available on Zenodo. The resource enables development of context-aware damage detection models and supports visualization and planning for flood risk reduction in climate-vulnerable African cities.

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.