Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning

Flood is one of the most damaging natural hazards, and timely detection of it is very important to save human lives and assess the level of damage. The occurrence of floods in cloudy weather conditions makes the use of radar-based sensors for real-time flood mapping inevitable. In the present study,...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammadali Abbasi, Reza Shah-Hosseini, Mohammad Aghdami-Nia
Format: Article
Language:English
Published: MDPI AG 2023-02-01
Series:Proceedings
Subjects:
Online Access:https://www.mdpi.com/2504-3900/87/1/14
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091283318571008
author Mohammadali Abbasi
Reza Shah-Hosseini
Mohammad Aghdami-Nia
author_facet Mohammadali Abbasi
Reza Shah-Hosseini
Mohammad Aghdami-Nia
author_sort Mohammadali Abbasi
collection DOAJ
description Flood is one of the most damaging natural hazards, and timely detection of it is very important to save human lives and assess the level of damage. The occurrence of floods in cloudy weather conditions makes the use of radar-based sensors for real-time flood mapping inevitable. In the present study, the ETCI 2021 flood event detection competition dataset, organized by the NASA Advanced Concepts and Implementation Team in collaboration with the IEEE GRSS Geoscience Informatics Technical Committee, has been used. Moreover, we have utilized the U-Net and X-Net architecture as a segmentation model to map flooded regions. This study aimed to identify the optimum polarization of the Sentinel-1 satellite for flood detection. By examining and comparing the obtained results, it was observed that the VV polarization offered better results in both models. Furthermore, U-Net had a better performance than X-Net in both polarizations.
format Article
id doaj-art-4b4be775608d44aa8049568e66d54b40
institution DOAJ
issn 2504-3900
language English
publishDate 2023-02-01
publisher MDPI AG
record_format Article
series Proceedings
spelling doaj-art-4b4be775608d44aa8049568e66d54b402025-08-20T02:42:25ZengMDPI AGProceedings2504-39002023-02-018711410.3390/IECG2022-14069Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep LearningMohammadali Abbasi0Reza Shah-Hosseini1Mohammad Aghdami-Nia2School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran 1417466191, IranSchool of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran 1417466191, IranSchool of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran 1417466191, IranFlood is one of the most damaging natural hazards, and timely detection of it is very important to save human lives and assess the level of damage. The occurrence of floods in cloudy weather conditions makes the use of radar-based sensors for real-time flood mapping inevitable. In the present study, the ETCI 2021 flood event detection competition dataset, organized by the NASA Advanced Concepts and Implementation Team in collaboration with the IEEE GRSS Geoscience Informatics Technical Committee, has been used. Moreover, we have utilized the U-Net and X-Net architecture as a segmentation model to map flooded regions. This study aimed to identify the optimum polarization of the Sentinel-1 satellite for flood detection. By examining and comparing the obtained results, it was observed that the VV polarization offered better results in both models. Furthermore, U-Net had a better performance than X-Net in both polarizations.https://www.mdpi.com/2504-3900/87/1/14flood detectionremote sensingSARSentinel-1deep learningU-Net
spellingShingle Mohammadali Abbasi
Reza Shah-Hosseini
Mohammad Aghdami-Nia
Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning
Proceedings
flood detection
remote sensing
SAR
Sentinel-1
deep learning
U-Net
title Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning
title_full Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning
title_fullStr Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning
title_full_unstemmed Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning
title_short Sentinel-1 Polarization Comparison for Flood Segmentation Using Deep Learning
title_sort sentinel 1 polarization comparison for flood segmentation using deep learning
topic flood detection
remote sensing
SAR
Sentinel-1
deep learning
U-Net
url https://www.mdpi.com/2504-3900/87/1/14
work_keys_str_mv AT mohammadaliabbasi sentinel1polarizationcomparisonforfloodsegmentationusingdeeplearning
AT rezashahhosseini sentinel1polarizationcomparisonforfloodsegmentationusingdeeplearning
AT mohammadaghdaminia sentinel1polarizationcomparisonforfloodsegmentationusingdeeplearning