Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework
Near realtime flood mapping in densely populated urban areas is critical for emergency response. The strong heterogeneity of urban areas poses a big challenge for accurate near realtime flood mapping. However, previous studies on automatic methods for urban flood mapping perform infeasible in near r...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9309354/ |
| _version_ | 1818901208350326784 |
|---|---|
| author | Bo Peng Qunying Huang Jamp Vongkusolkit Song Gao Daniel B. Wright Zheng N. Fang Yi Qiang |
| author_facet | Bo Peng Qunying Huang Jamp Vongkusolkit Song Gao Daniel B. Wright Zheng N. Fang Yi Qiang |
| author_sort | Bo Peng |
| collection | DOAJ |
| description | Near realtime flood mapping in densely populated urban areas is critical for emergency response. The strong heterogeneity of urban areas poses a big challenge for accurate near realtime flood mapping. However, previous studies on automatic methods for urban flood mapping perform infeasible in near realtime or fail to generalize well to other floods, for several reasons. First, multitemporal pixel-wise flood mapping requires accurate image registration, hindering the efficiency of large-scale processing. Although automatic image registration has been investigated, precisely coregistered multitemporal image sequence requires time-consuming fine tuning. Additionally, the floods may lead to the loss of many corresponding image points across multitemporal images for accurate coregistration. Second, existing unsupervised methods generally rely on hand-crafted features for floodwater detection. Such features may not well represent the patterns of floodwaters in different areas due to inconsistent weather conditions, illumination, and floodwater spectra. This article proposes a self-supervised learning framework for patch-wise urban flood mapping using bitemporal multispectral satellite imagery. Patch-wise change vector analysis is used with patch features learned through a self-supervised autoencoder to produce patch-wise change maps showing potentially flood-affected areas. Postprocessing including spectral and spatial filtering is applied to these patch-wise change maps to remove nonflood related changes. Final flood maps and parameter sensitivities were evaluated using several performance metrics. Two flood events from areas with differing degrees of urbanization were considered: Hurricane Harvey flood (2017) in Houston, Texas, and Hurricane Florence flood (2018) in Lumberton, North Carolina. The proposed method shows strong performance for self-supervised urban flood mapping. |
| first_indexed | 2024-12-19T20:16:06Z |
| format | Article |
| id | doaj.art-c3e933e9ef9f48a1a1864c5110cc793b |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-19T20:16:06Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-c3e933e9ef9f48a1a1864c5110cc793b2022-12-21T20:07:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01142001201610.1109/JSTARS.2020.30476779309354Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning FrameworkBo Peng0https://orcid.org/0000-0003-1514-6881Qunying Huang1Jamp Vongkusolkit2Song Gao3Daniel B. Wright4Zheng N. Fang5Yi Qiang6Department of Geography, Department of Electrical and Computer Engineering, University of Wisconsin - Madison, Madison, WI, USADepartment of Geography, University of Wisconsin - Madison, Madison, WI, USADepartment of Geography, University of Wisconsin - Madison, Madison, WI, USADepartment of Geography, University of Wisconsin - Madison, Madison, WI, USADepartment of Civil and Environmental Engineering, University of Wisconsin - Madison, Madison, WI, USADepartment of Civil Engineering, The University of Texas at Arlington, Arlington, TX, USASchool of Geosciences, University of South Florida, Tampa, FL, USANear realtime flood mapping in densely populated urban areas is critical for emergency response. The strong heterogeneity of urban areas poses a big challenge for accurate near realtime flood mapping. However, previous studies on automatic methods for urban flood mapping perform infeasible in near realtime or fail to generalize well to other floods, for several reasons. First, multitemporal pixel-wise flood mapping requires accurate image registration, hindering the efficiency of large-scale processing. Although automatic image registration has been investigated, precisely coregistered multitemporal image sequence requires time-consuming fine tuning. Additionally, the floods may lead to the loss of many corresponding image points across multitemporal images for accurate coregistration. Second, existing unsupervised methods generally rely on hand-crafted features for floodwater detection. Such features may not well represent the patterns of floodwaters in different areas due to inconsistent weather conditions, illumination, and floodwater spectra. This article proposes a self-supervised learning framework for patch-wise urban flood mapping using bitemporal multispectral satellite imagery. Patch-wise change vector analysis is used with patch features learned through a self-supervised autoencoder to produce patch-wise change maps showing potentially flood-affected areas. Postprocessing including spectral and spatial filtering is applied to these patch-wise change maps to remove nonflood related changes. Final flood maps and parameter sensitivities were evaluated using several performance metrics. Two flood events from areas with differing degrees of urbanization were considered: Hurricane Harvey flood (2017) in Houston, Texas, and Hurricane Florence flood (2018) in Lumberton, North Carolina. The proposed method shows strong performance for self-supervised urban flood mapping.https://ieeexplore.ieee.org/document/9309354/Flood mappingmultispectral (MS) imageryself-supervised learningurban |
| spellingShingle | Bo Peng Qunying Huang Jamp Vongkusolkit Song Gao Daniel B. Wright Zheng N. Fang Yi Qiang Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Flood mapping multispectral (MS) imagery self-supervised learning urban |
| title | Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework |
| title_full | Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework |
| title_fullStr | Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework |
| title_full_unstemmed | Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework |
| title_short | Urban Flood Mapping With Bitemporal Multispectral Imagery Via a Self-Supervised Learning Framework |
| title_sort | urban flood mapping with bitemporal multispectral imagery via a self supervised learning framework |
| topic | Flood mapping multispectral (MS) imagery self-supervised learning urban |
| url | https://ieeexplore.ieee.org/document/9309354/ |
| work_keys_str_mv | AT bopeng urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework AT qunyinghuang urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework AT jampvongkusolkit urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework AT songgao urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework AT danielbwright urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework AT zhengnfang urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework AT yiqiang urbanfloodmappingwithbitemporalmultispectralimageryviaaselfsupervisedlearningframework |