Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery
This study introduces a flood index-enhanced deep learning model for coastal inundation mapping leveraging dual-polarization and bitemporal Sentinel-1 synthetic aperture radar (SAR) imagery. The proposed model, FIE-Net, introduces two key innovations to improve flood mapping accuracy. First, it inte...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843225001979 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850135597394427904 |
|---|---|
| author | Wantai Chen Yinfei Zhou Xiaofeng Li |
| author_facet | Wantai Chen Yinfei Zhou Xiaofeng Li |
| author_sort | Wantai Chen |
| collection | DOAJ |
| description | This study introduces a flood index-enhanced deep learning model for coastal inundation mapping leveraging dual-polarization and bitemporal Sentinel-1 synthetic aperture radar (SAR) imagery. The proposed model, FIE-Net, introduces two key innovations to improve flood mapping accuracy. First, it integrates the Ratio Image (RI), a primary flood index derived from bitemporal SAR data, which provides a reliable reference for precise inundation area delineation. The index offers a clear, flood-specific signal that enhances segmentation precision. Second, the model employs a dual-branch U-Net framework, augmented with specialized modules to enhance feature extraction and better integrate diverse data sources. This combination enables the model to handle complex flood scenarios more effectively, thereby boosting overall performance. Using data from the Copernicus Emergency Management Service, 16 pairs of representative SAR images from Madagascar’s Tropical Cyclones 2018 AVA and 2023 Cheneso were collected under various terrain conditions. After semi-automatic labeling and cropping, 4350 sample pairs were processed, with 2784/696/870 used for model training/validation/testing. The proposed model achieved the highest Intersection over Union (IOU) of 79.44%, outperforming the state-of-the-art models across all evaluation metrics. The experiments also demonstrate that each introduced innovation contributes to improved accuracy, with the flood index making the most significant impact. Furthermore, the model’s applicability was further confirmed with three independent flooded areas (689 samples, not included in training) from the event Cheneso. IOUs in all three scenes consistently exceeded 75%, underscoring the model’s reliability and robustness in real-world scenarios. |
| format | Article |
| id | doaj-art-e2d4954517f2474ca153485736dc9298 |
| institution | OA Journals |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-e2d4954517f2474ca153485736dc92982025-08-20T02:31:22ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-05-0113910455010.1016/j.jag.2025.104550Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imageryWantai Chen0Yinfei Zhou1Xiaofeng Li2Key Laboratory of Ocean Observation and Forecasting and Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, China; College of Marine Sciences, University of Chinese Academy of Sciences, Beijing, China; Qingdao Key Laboratory of Artificial Intelligence Oceanography, Qingdao, ChinaKey Laboratory of Ocean Observation and Forecasting and Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, China; College of Marine Sciences, University of Chinese Academy of Sciences, Beijing, China; Qingdao Key Laboratory of Artificial Intelligence Oceanography, Qingdao, ChinaKey Laboratory of Ocean Observation and Forecasting and Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, China; College of Marine Sciences, University of Chinese Academy of Sciences, Beijing, China; Corresponding author.This study introduces a flood index-enhanced deep learning model for coastal inundation mapping leveraging dual-polarization and bitemporal Sentinel-1 synthetic aperture radar (SAR) imagery. The proposed model, FIE-Net, introduces two key innovations to improve flood mapping accuracy. First, it integrates the Ratio Image (RI), a primary flood index derived from bitemporal SAR data, which provides a reliable reference for precise inundation area delineation. The index offers a clear, flood-specific signal that enhances segmentation precision. Second, the model employs a dual-branch U-Net framework, augmented with specialized modules to enhance feature extraction and better integrate diverse data sources. This combination enables the model to handle complex flood scenarios more effectively, thereby boosting overall performance. Using data from the Copernicus Emergency Management Service, 16 pairs of representative SAR images from Madagascar’s Tropical Cyclones 2018 AVA and 2023 Cheneso were collected under various terrain conditions. After semi-automatic labeling and cropping, 4350 sample pairs were processed, with 2784/696/870 used for model training/validation/testing. The proposed model achieved the highest Intersection over Union (IOU) of 79.44%, outperforming the state-of-the-art models across all evaluation metrics. The experiments also demonstrate that each introduced innovation contributes to improved accuracy, with the flood index making the most significant impact. Furthermore, the model’s applicability was further confirmed with three independent flooded areas (689 samples, not included in training) from the event Cheneso. IOUs in all three scenes consistently exceeded 75%, underscoring the model’s reliability and robustness in real-world scenarios.http://www.sciencedirect.com/science/article/pii/S1569843225001979Synthetic aperture radar (SAR)Coastal inundation mappingDeep learningFlood index |
| spellingShingle | Wantai Chen Yinfei Zhou Xiaofeng Li Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery International Journal of Applied Earth Observations and Geoinformation Synthetic aperture radar (SAR) Coastal inundation mapping Deep learning Flood index |
| title | Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery |
| title_full | Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery |
| title_fullStr | Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery |
| title_full_unstemmed | Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery |
| title_short | Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery |
| title_sort | flood index enhanced deep learning model for coastal inundation mapping in sar imagery |
| topic | Synthetic aperture radar (SAR) Coastal inundation mapping Deep learning Flood index |
| url | http://www.sciencedirect.com/science/article/pii/S1569843225001979 |
| work_keys_str_mv | AT wantaichen floodindexenhanceddeeplearningmodelforcoastalinundationmappinginsarimagery AT yinfeizhou floodindexenhanceddeeplearningmodelforcoastalinundationmappinginsarimagery AT xiaofengli floodindexenhanceddeeplearningmodelforcoastalinundationmappinginsarimagery |