Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service
The Global Flood Monitoring (GFM) system of the Copernicus Emergency Management Service 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...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10186373/ |
| _version_ | 1797679598725496832 |
|---|---|
| author | Christian Krullikowski Candace Chow Marc Wieland Sandro Martinis Bernhard Bauer-Marschallinger Florian Roth Patrick Matgen Marco Chini Renaud Hostache Yu Li Peter Salamon |
| author_facet | Christian Krullikowski Candace Chow Marc Wieland Sandro Martinis Bernhard Bauer-Marschallinger Florian Roth Patrick Matgen Marco Chini Renaud Hostache Yu Li Peter Salamon |
| author_sort | Christian Krullikowski |
| collection | DOAJ |
| description | The Global Flood Monitoring (GFM) system of the Copernicus Emergency Management Service 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. |
| first_indexed | 2024-03-11T23:17:08Z |
| format | Article |
| id | doaj.art-fb36e64ba7c04ed3b5a692d7f3dcbdb9 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-11T23:17:08Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-fb36e64ba7c04ed3b5a692d7f3dcbdb92023-09-20T23:00:11ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01166917693010.1109/JSTARS.2023.329235010186373Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management ServiceChristian Krullikowski0https://orcid.org/0000-0001-8717-692XCandace Chow1https://orcid.org/0000-0003-3716-0924Marc Wieland2https://orcid.org/0000-0002-1155-723XSandro Martinis3https://orcid.org/0000-0002-6400-361XBernhard Bauer-Marschallinger4https://orcid.org/0000-0001-7356-7516Florian Roth5https://orcid.org/0000-0002-8589-0182Patrick Matgen6Marco Chini7https://orcid.org/0000-0002-9094-0367Renaud Hostache8https://orcid.org/0000-0002-8109-6010Yu Li9Peter Salamon10German Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Oberpfaffenhofen, GermanyGerman Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Oberpfaffenhofen, GermanyGerman Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Oberpfaffenhofen, GermanyGerman Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Oberpfaffenhofen, GermanyRemote Sensing Research Group, Department of Geodesy and Geoinformation, TU Wien, Vienna, AustriaRemote Sensing Research Group, Department of Geodesy and Geoinformation, TU Wien, Vienna, AustriaEnvironmental Research and Innovation Department, Luxembourg Institute of Science and Technology, Esch-sur-Alzette, LuxembourgEnvironmental Research and Innovation Department, Luxembourg Institute of Science and Technology, Esch-sur-Alzette, LuxembourgEnvironmental Research and Innovation Department, Luxembourg Institute of Science and Technology, Esch-sur-Alzette, LuxembourgEnvironmental Research and Innovation Department, Luxembourg Institute of Science and Technology, Esch-sur-Alzette, LuxembourgJoint Research Centre (JRC) of the European Commission, Ispra, ItalyThe Global Flood Monitoring (GFM) system of the Copernicus Emergency Management Service 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.https://ieeexplore.ieee.org/document/10186373/Copernicus Emergency Management Service (CEMS)Earth observationensemble classificationflood monitoringlikelihoodsradar |
| spellingShingle | Christian Krullikowski Candace Chow Marc Wieland Sandro Martinis Bernhard Bauer-Marschallinger Florian Roth Patrick Matgen Marco Chini Renaud Hostache Yu Li Peter Salamon Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Copernicus Emergency Management Service (CEMS) Earth observation ensemble classification flood monitoring likelihoods radar |
| title | Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service |
| title_full | Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service |
| title_fullStr | Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service |
| title_full_unstemmed | Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service |
| title_short | Estimating Ensemble Likelihoods for the Sentinel-1-Based Global Flood Monitoring Product of the Copernicus Emergency Management Service |
| title_sort | estimating ensemble likelihoods for the sentinel 1 based global flood monitoring product of the copernicus emergency management service |
| topic | Copernicus Emergency Management Service (CEMS) Earth observation ensemble classification flood monitoring likelihoods radar |
| url | https://ieeexplore.ieee.org/document/10186373/ |
| work_keys_str_mv | AT christiankrullikowski estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT candacechow estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT marcwieland estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT sandromartinis estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT bernhardbauermarschallinger estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT florianroth estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT patrickmatgen estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT marcochini estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT renaudhostache estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT yuli estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice AT petersalamon estimatingensemblelikelihoodsforthesentinel1basedglobalfloodmonitoringproductofthecopernicusemergencymanagementservice |