Leveraging Citizen Science for Flood Extent Detection using Machine Learning Benchmark Dataset

TL;DR

This paper introduces a large labeled dataset of flood extents derived from Sentinel-1 SAR imagery, leveraging citizen science through an open competition to improve machine learning models for flood detection.

Contribution

The paper presents a new open-source dataset covering 36,000 sq. km, a baseline model, and details of a citizen science competition to advance flood extent detection methods.

Findings

Open-source dataset enables community-driven flood detection research.

The competition spurred development of diverse machine learning approaches.

The dataset improves robustness of flood extent modeling.

Abstract

Accurate detection of inundated water extents during flooding events is crucial in emergency response decisions and aids in recovery efforts. Satellite Remote Sensing data provides a global framework for detecting flooding extents. Specifically, Sentinel-1 C-Band Synthetic Aperture Radar (SAR) imagery has proven to be useful in detecting water bodies due to low backscatter of water features in both co-polarized and cross-polarized SAR imagery. However, increased backscatter can be observed in certain flooded regions such as presence of infrastructure and trees - rendering simple methods such as pixel intensity thresholding and time-series differencing inadequate. Machine Learning techniques has been leveraged to precisely capture flood extents in flooded areas with bumps in backscatter but needs high amounts of labelled data to work desirably. Hence, we created a labeled known water body extent and flooded area extents during known flooding events covering about 36,000 sq. kilometers of regions within mainland U.S and Bangladesh. Further, We also leveraged citizen science by open-sourcing the dataset and hosting an open competition based on the dataset to rapidly prototype flood extent detection using community generated models. In this paper we present the information about the dataset, the data processing pipeline, a baseline model and the details about the competition, along with discussion on winning approaches. We believe the dataset adds to already existing datasets based on Sentinel-1C SAR data and leads to more robust modeling of flood extents. We also hope the results from the competition pushes the research in flood extent detection further.