loading page

Estimating ensemble likelihoods for the Sentinel-1 based Global Flood Monitoring product of the Copernicus Emergency Management Service
  • +7
  • Christian Krullikowski ,
  • Candace Chow ,
  • Marc Wieland ,
  • Sandro Martinis ,
  • Bernhard Bauer-Marschallinger ,
  • Florian Roth ,
  • Patrick Matgen ,
  • Marco Chini ,
  • Yu Li ,
  • Peter Salamon
Christian Krullikowski
German Aerospace Center (DLR)

Corresponding Author:[email protected]

Author Profile
Candace Chow
Author Profile
Marc Wieland
Author Profile
Sandro Martinis
Author Profile
Bernhard Bauer-Marschallinger
Author Profile
Florian Roth
Author Profile
Patrick Matgen
Author Profile
Marco Chini
Author Profile
Peter Salamon
Author Profile


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.
2023Published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing volume 16 on pages 6917-6930. 10.1109/JSTARS.2023.3292350