Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection
<p>The frequency and intensity of coastal flooding is expected to accelerate in low-elevation coastal areas due to sea level rise. Coastal flooding due to wave overtopping affects coastal communities and infrastructure; however, it can be difficult to monitor in remote and vulnerable areas. He...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-01-01
|
| Series: | Earth Surface Dynamics |
| Online Access: | https://esurf.copernicus.org/articles/12/1/2024/esurf-12-1-2024.pdf |
| _version_ | 1827391841610235904 |
|---|---|
| author | B. Kang B. Kang R. A. Feagin R. A. Feagin T. Huff O. Durán Vinent |
| author_facet | B. Kang B. Kang R. A. Feagin R. A. Feagin T. Huff O. Durán Vinent |
| author_sort | B. Kang |
| collection | DOAJ |
| description | <p>The frequency and intensity of coastal flooding is expected to accelerate in low-elevation coastal areas due to sea level rise. Coastal flooding due to wave overtopping affects coastal communities and infrastructure; however, it can be difficult to monitor in remote and vulnerable areas. Here we use a camera-based system to measure beach and back-beach flooding as part of the after-storm recovery of an eroded beach on the Texas coast. We analyze high-temporal resolution images of the beach using convolutional neural network (CNN)-based semantic segmentation to study the stochastic properties of flooding events. In the first part of this work, we focus on the application of semantic segmentation to identify water and overtopping events. We train and validate a CNN with over 500 manually classified images and introduce a post-processing method to reduce false positives. We find that the accuracy of CNN predictions of water pixels is around 90 % and strongly depends on the number and diversity of images used for training.</p> |
| first_indexed | 2024-03-08T17:21:12Z |
| format | Article |
| id | doaj.art-d2bf6c8ff6994d2b852485e693bf99d0 |
| institution | Directory Open Access Journal |
| issn | 2196-6311 2196-632X |
| language | English |
| last_indexed | 2024-03-08T17:21:12Z |
| publishDate | 2024-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Earth Surface Dynamics |
| spelling | doaj.art-d2bf6c8ff6994d2b852485e693bf99d02024-01-03T05:10:12ZengCopernicus PublicationsEarth Surface Dynamics2196-63112196-632X2024-01-011211010.5194/esurf-12-1-2024Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detectionB. Kang0B. Kang1R. A. Feagin2R. A. Feagin3T. Huff4O. Durán Vinent5Department of Ocean Engineering, Texas A&M University, College Station, TX, USADepartment of Civil and Environmental Engineering, University of Houston, Houston, TX, USADepartment of Ocean Engineering, Texas A&M University, College Station, TX, USADepartment of Ecology and Conservation Biology, Texas A&M University, College Station, TX, USADepartment of Ecology and Conservation Biology, Texas A&M University, College Station, TX, USADepartment of Ocean Engineering, Texas A&M University, College Station, TX, USA<p>The frequency and intensity of coastal flooding is expected to accelerate in low-elevation coastal areas due to sea level rise. Coastal flooding due to wave overtopping affects coastal communities and infrastructure; however, it can be difficult to monitor in remote and vulnerable areas. Here we use a camera-based system to measure beach and back-beach flooding as part of the after-storm recovery of an eroded beach on the Texas coast. We analyze high-temporal resolution images of the beach using convolutional neural network (CNN)-based semantic segmentation to study the stochastic properties of flooding events. In the first part of this work, we focus on the application of semantic segmentation to identify water and overtopping events. We train and validate a CNN with over 500 manually classified images and introduce a post-processing method to reduce false positives. We find that the accuracy of CNN predictions of water pixels is around 90 % and strongly depends on the number and diversity of images used for training.</p>https://esurf.copernicus.org/articles/12/1/2024/esurf-12-1-2024.pdf |
| spellingShingle | B. Kang B. Kang R. A. Feagin R. A. Feagin T. Huff O. Durán Vinent Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection Earth Surface Dynamics |
| title | Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection |
| title_full | Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection |
| title_fullStr | Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection |
| title_full_unstemmed | Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection |
| title_short | Stochastic properties of coastal flooding events – Part 1: convolutional-neural-network-based semantic segmentation for water detection |
| title_sort | stochastic properties of coastal flooding events part 1 convolutional neural network based semantic segmentation for water detection |
| url | https://esurf.copernicus.org/articles/12/1/2024/esurf-12-1-2024.pdf |
| work_keys_str_mv | AT bkang stochasticpropertiesofcoastalfloodingeventspart1convolutionalneuralnetworkbasedsemanticsegmentationforwaterdetection AT bkang stochasticpropertiesofcoastalfloodingeventspart1convolutionalneuralnetworkbasedsemanticsegmentationforwaterdetection AT rafeagin stochasticpropertiesofcoastalfloodingeventspart1convolutionalneuralnetworkbasedsemanticsegmentationforwaterdetection AT rafeagin stochasticpropertiesofcoastalfloodingeventspart1convolutionalneuralnetworkbasedsemanticsegmentationforwaterdetection AT thuff stochasticpropertiesofcoastalfloodingeventspart1convolutionalneuralnetworkbasedsemanticsegmentationforwaterdetection AT oduranvinent stochasticpropertiesofcoastalfloodingeventspart1convolutionalneuralnetworkbasedsemanticsegmentationforwaterdetection |