Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data
Urban flooding significantly impacts populations and often coincides with heavy rainfall, making optical satellite observation challenging due to cloud cover. This study proposes a novel approach using synthetic aperture radar (SAR) sensors, which can penetrate clouds, to classify flooded urban area...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10805564/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592916250361856 |
|---|---|
| author | Dodi Sudiana Indra Riyanto Mia Rizkinia Rahmat Arief Anton Satria Prabuwono Josaphat Tetuko Sri Sumantyo Ketut Wikantika |
| author_facet | Dodi Sudiana Indra Riyanto Mia Rizkinia Rahmat Arief Anton Satria Prabuwono Josaphat Tetuko Sri Sumantyo Ketut Wikantika |
| author_sort | Dodi Sudiana |
| collection | DOAJ |
| description | Urban flooding significantly impacts populations and often coincides with heavy rainfall, making optical satellite observation challenging due to cloud cover. This study proposes a novel approach using synthetic aperture radar (SAR) sensors, which can penetrate clouds, to classify flooded urban areas. The framework employs a 3-D convolutional neural network (3-D CNN) to process multitemporal SAR data from Sentinel-1 (S-1). The dataset included 24 S-1 scenes with Dual VV and VH polarization from March 2019 to February 2020, divided into two co-event images, 18 preevent images, and four postevent images. The 3-D CNN achieved an average overall accuracy of 70.3% and a peak accuracy of 71.8%. These results demonstrate the 3-D CNN's potential to accurately estimate flood extent and identify flood-prone areas, supporting early detection and flood prevention in other cities. |
| format | Article |
| id | doaj-art-37c2225bb9444456ba898d7fa3d2e5c0 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-37c2225bb9444456ba898d7fa3d2e5c02025-01-21T00:00:48ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183198320710.1109/JSTARS.2024.351952310805564Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image DataDodi Sudiana0https://orcid.org/0000-0001-8062-0901Indra Riyanto1https://orcid.org/0000-0002-4565-2702Mia Rizkinia2https://orcid.org/0000-0003-3197-1611Rahmat Arief3Anton Satria Prabuwono4https://orcid.org/0000-0003-3337-6605Josaphat Tetuko Sri Sumantyo5https://orcid.org/0000-0002-4036-6854Ketut Wikantika6Department of Electrical Engineering, and Artificial Intelligence Data Engineering (AIDE) Research Center, Faculty of Engineering, Universitas Indonesia, Depok, IndonesiaCenter for Environmental Studies, Universitas Budi Luhur, Jakarta, IndonesiaDepartment of Electrical Engineering, and Artificial Intelligence Data Engineering (AIDE) Research Center, Faculty of Engineering, Universitas Indonesia, Depok, IndonesiaResearch Center for Geoinformatics of National Research and Innovation Agency (BRIN), Cibinong, IndonesiaDepartment of Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaCenter for Environmental Remote Sensing, Chiba University, Chiba, JapanGeodesy and Geomatics Engineering and Center for Remote Sensing, Institut Teknologi Bandung, Bandung, IndonesiaUrban flooding significantly impacts populations and often coincides with heavy rainfall, making optical satellite observation challenging due to cloud cover. This study proposes a novel approach using synthetic aperture radar (SAR) sensors, which can penetrate clouds, to classify flooded urban areas. The framework employs a 3-D convolutional neural network (3-D CNN) to process multitemporal SAR data from Sentinel-1 (S-1). The dataset included 24 S-1 scenes with Dual VV and VH polarization from March 2019 to February 2020, divided into two co-event images, 18 preevent images, and four postevent images. The 3-D CNN achieved an average overall accuracy of 70.3% and a peak accuracy of 71.8%. These results demonstrate the 3-D CNN's potential to accurately estimate flood extent and identify flood-prone areas, supporting early detection and flood prevention in other cities.https://ieeexplore.ieee.org/document/10805564/3-D convolutional neural network (3-D CNN)machine learning (ML)multitemporal datasynthetic aperture radar (SAR)temporal variationurban flood |
| spellingShingle | Dodi Sudiana Indra Riyanto Mia Rizkinia Rahmat Arief Anton Satria Prabuwono Josaphat Tetuko Sri Sumantyo Ketut Wikantika Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 3-D convolutional neural network (3-D CNN) machine learning (ML) multitemporal data synthetic aperture radar (SAR) temporal variation urban flood |
| title | Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data |
| title_full | Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data |
| title_fullStr | Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data |
| title_full_unstemmed | Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data |
| title_short | Performance Evaluation of 3-D Convolutional Neural Network for Multitemporal Flood Classification Framework With Synthetic Aperture Radar Image Data |
| title_sort | performance evaluation of 3 d convolutional neural network for multitemporal flood classification framework with synthetic aperture radar image data |
| topic | 3-D convolutional neural network (3-D CNN) machine learning (ML) multitemporal data synthetic aperture radar (SAR) temporal variation urban flood |
| url | https://ieeexplore.ieee.org/document/10805564/ |
| work_keys_str_mv | AT dodisudiana performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata AT indrariyanto performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata AT miarizkinia performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata AT rahmatarief performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata AT antonsatriaprabuwono performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata AT josaphattetukosrisumantyo performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata AT ketutwikantika performanceevaluationof3dconvolutionalneuralnetworkformultitemporalfloodclassificationframeworkwithsyntheticapertureradarimagedata |