A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment
An innovative framework for rapid flood detection leverages Synthetic Aperture Radar (SAR) to overcome cloud obstruction and geolocation inaccuracies. SAR-SIFT registration corrects spatial errors in domestic SAR imagery, while a lightweight Modified DeepLabV3 model—trained on multi-polarization SAR...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2025.2512188 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849421692889202688 |
|---|---|
| author | Zhuoyu Zhang Jiaqi Xiong Xiang Li Yu Li Junrong Liu |
| author_facet | Zhuoyu Zhang Jiaqi Xiong Xiang Li Yu Li Junrong Liu |
| author_sort | Zhuoyu Zhang |
| collection | DOAJ |
| description | An innovative framework for rapid flood detection leverages Synthetic Aperture Radar (SAR) to overcome cloud obstruction and geolocation inaccuracies. SAR-SIFT registration corrects spatial errors in domestic SAR imagery, while a lightweight Modified DeepLabV3 model—trained on multi-polarization SAR data (HH/HV) fused with terrain features (elevation, slope, aspect, gradient) and watershed—enhances floodwater extraction accuracy. A DEM gradient strategy mitigates terrain shadow interference, refining detection reliability. Experimental results achieve 0.9840 overall accuracy, 0.9631 precision, 0.882 recall, 0.9207 F1-score, and 0.8483 IoU. Despite Sentinel-1A’s 12-day revisit cycle limitations, integrated domestic SAR data ensures timely flood monitoring. The framework’s scalability and cost-efficiency enable large-scale deployment, outperforming optical sensors in cloud-prone scenarios. By combining advanced georegistration, terrain-adaptive algorithms, and multi-source data fusion, this solution strengthens disaster response capabilities, offering robust real-time flood mapping and early warning systems for improved emergency management. |
| format | Article |
| id | doaj-art-5f567df20f1c4196b0d96efce099d913 |
| institution | Kabale University |
| issn | 1010-6049 1752-0762 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj-art-5f567df20f1c4196b0d96efce099d9132025-08-20T03:31:24ZengTaylor & Francis GroupGeocarto International1010-60491752-07622025-12-0140110.1080/10106049.2025.2512188A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessmentZhuoyu Zhang0Jiaqi Xiong1Xiang Li2Yu Li3Junrong Liu4Xi’an Meihang Remote Sensing Information Co., LTD, Aerial Photogrammetry and Remote Sensing Group Co., LTD of China National Administration of Coal Geology, Xi’an, ChinaXi’an Meihang Remote Sensing Information Co., LTD, Aerial Photogrammetry and Remote Sensing Group Co., LTD of China National Administration of Coal Geology, Xi’an, ChinaSchool of Geosciences, University of South Florida, Tampa, USAXi’an Meihang Remote Sensing Information Co., LTD, Aerial Photogrammetry and Remote Sensing Group Co., LTD of China National Administration of Coal Geology, Xi’an, ChinaXi’an Meihang Remote Sensing Information Co., LTD, Aerial Photogrammetry and Remote Sensing Group Co., LTD of China National Administration of Coal Geology, Xi’an, ChinaAn innovative framework for rapid flood detection leverages Synthetic Aperture Radar (SAR) to overcome cloud obstruction and geolocation inaccuracies. SAR-SIFT registration corrects spatial errors in domestic SAR imagery, while a lightweight Modified DeepLabV3 model—trained on multi-polarization SAR data (HH/HV) fused with terrain features (elevation, slope, aspect, gradient) and watershed—enhances floodwater extraction accuracy. A DEM gradient strategy mitigates terrain shadow interference, refining detection reliability. Experimental results achieve 0.9840 overall accuracy, 0.9631 precision, 0.882 recall, 0.9207 F1-score, and 0.8483 IoU. Despite Sentinel-1A’s 12-day revisit cycle limitations, integrated domestic SAR data ensures timely flood monitoring. The framework’s scalability and cost-efficiency enable large-scale deployment, outperforming optical sensors in cloud-prone scenarios. By combining advanced georegistration, terrain-adaptive algorithms, and multi-source data fusion, this solution strengthens disaster response capabilities, offering robust real-time flood mapping and early warning systems for improved emergency management.https://www.tandfonline.com/doi/10.1080/10106049.2025.2512188Image semantic segmentationSARdeep learningflooded area |
| spellingShingle | Zhuoyu Zhang Jiaqi Xiong Xiang Li Yu Li Junrong Liu A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment Geocarto International Image semantic segmentation SAR deep learning flooded area |
| title | A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment |
| title_full | A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment |
| title_fullStr | A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment |
| title_full_unstemmed | A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment |
| title_short | A SAR-based flood mapping approach: application of SAR-SIFT registration and modified DeepLabV3 segmentation in flood hazard assessment |
| title_sort | sar based flood mapping approach application of sar sift registration and modified deeplabv3 segmentation in flood hazard assessment |
| topic | Image semantic segmentation SAR deep learning flooded area |
| url | https://www.tandfonline.com/doi/10.1080/10106049.2025.2512188 |
| work_keys_str_mv | AT zhuoyuzhang asarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT jiaqixiong asarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT xiangli asarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT yuli asarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT junrongliu asarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT zhuoyuzhang sarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT jiaqixiong sarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT xiangli sarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT yuli sarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment AT junrongliu sarbasedfloodmappingapproachapplicationofsarsiftregistrationandmodifieddeeplabv3segmentationinfloodhazardassessment |