Estimating ensemble likelihoods for the Sentinel-1 based Global Flood Monitoring product of the Copernicus Emergency Management Service
Authors:
- Christian KrullikowskiCKChristian Krullikowski
- Candace ChowCCCandace Chow
- Marc WielandMWMarc Wieland
- Sandro MartinisSMSandro Martinis
- Bernhard Bauer-MarschallingerBBBernhard Bauer-Marschallinger
- Florian RothFRFlorian Roth
- Patrick MatgenPMPatrick Matgen
- Marco ChiniMCMarco Chini
- Renaud HostacheRHRenaud Hostache
- Yu LiYLYu Li
- Peter SalamonPeter Salamon
Preprint
Abstract
The Global Flood Monitoring (GFM) system of the Copernicus Emergency Management Service (CEMS) addresses the challenges and impacts that are caused by flooding. The GFM system provides global, near-real time flood extent masks for each newly acquired Sentinel-1 Interferometric Wide Swath Synthetic Aperture Radar (SAR) image, as well as flood information from the whole Sentinel-1 archive from 2015 on. The GFM flood extent is an ensemble product based on a combination of three independently developed flood mapping algorithms that individually derive the flood information from Sentinel-1 data. Each flood algorithm also provides classification uncertainty information that is aggregated into the GFM ensemble likelihood product as the mean of the individual classification likelihoods. As the flood detection algorithms derive uncertainty information with different methods, the value range of the three input likelihoods must be harmonized to a range from low [0] to high [100] flood likelihood. The ensemble likelihood is evaluated on two test sites in Myanmar and Somalia, showcasing the performance during an actual flood event and an area with challenging conditions for SAR-based flood detection. The Myanmar use case demonstrates the robustness if flood detections in the ensemble step disagree and how that information is communicated to the end-user. The Somalia use case demonstrates a setting where misclassifications are likely, how the ensemble process mitigates false detections and how the flood likelihoods can be interpreted to use such results with adequate caution.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Probabilistic SAR-based water segmentation with adapted Bayesian convolutional neural networkRemote Sensing of Environment, 2022
- Detecting, Extracting, and Monitoring Surface Water From Space Using Optical Sensors: A ReviewReviews of Geophysics, 2018
- Remote Sensing-Derived Water Extent and Level to Constrain Hydraulic Flood Forecasting Models: Opportunities and ChallengesSurveys in Geophysics, 2016
- Mixed aleatory and epistemic uncertainty quantification using fuzzy set theoryInternational Journal of Approximate Reasoning, 2015
- A fully automated TerraSAR-X based flood serviceISPRS Journal of Photogrammetry and Remote Sensing, 2015
- Microwave remote sensing of flood inundationPhysics and Chemistry of the Earth, Parts A/B/C, 2015
- Optimisation of global grids for high-resolution remote sensing dataComputers & Geosciences, 2014
- A synergetic use of satellite imagery from SAR and optical sensors to improve coastal flood mapping in the Gulf of MexicoHydrological Processes, 2011
- Height Above the Nearest Drainage – a hydrologically relevant new terrain modelJournal of Hydrology, 2011
- On the relation between probabilistic inference and fuzzy sets in visual scene analysisPattern Recognition Letters, 2004