Urban Flood Observations (UFO): A hand-labeled training and validation dataset of post-flood inundation

TL;DR

UFO is a globally curated, hand-labeled dataset of post-flood urban inundation from satellite imagery, designed to improve flood mapping methods and evaluate existing surface water products.

Contribution

The paper introduces UFO, a novel, publicly available dataset with detailed annotations for urban flood mapping from high-resolution satellite images.

Findings

Segmentation model trained on UFO achieved 77.3 IoU.

UFO effectively evaluates surface water products, revealing their limitations.

The dataset supports development of urban flood detection algorithms.

Abstract

Urban flooding affects lives and infrastructure worldwide. Mapping inundation in complex urban environments from satellite imagery remains challenging due to limited spatial resolution, infrequent acquisitions, and cloud cover. We present Urban Flood Observations (UFO), a global, hand-labeled dataset of post-flood inundation in diverse urban settings. UFO comprises 215 image chips (1024 by 1024 pixels) from 14 flood events between 2017 and 2021, derived from 3 m PlanetScope imagery. Each chip is annotated with two classes: 'inundated' (all visible surface water, including floodwater and pre-existing water bodies (permanent or seasonal)) and 'non-inundated'. To demonstrate the dataset's utility, we trained a segmentation model using leave-one-event-out cross-validation, achieving a mean Intersection over Union (IoU) of 77.3. We also used UFO to evaluate two widely used surface water products, the Sentinel-1-based NASA IMPACT model and Google's 10 m Dynamic World water class, which yielded IoUs of 44.1 and 48.1, respectively. UFO is publicly available to support the development and validation of urban inundation mapping methods.