Evaluation of Key Remote Sensing Features for Bushfire Analysis

This study evaluates remote sensing features to resolve problems associated with feature redundancy, low efficiency, and insufficient input feature analysis in bushfire detection. It calculates spectral features, remote sensing indices, and texture features from Sentinel-2 data for the Blue Mountain...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyi Yang, Husam Al-Najjar, Ghassan Beydoun, Bahareh Kalantar, Mohsen Zand, Naonori Ueda
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/11/1823
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722317447364608
author Ziyi Yang
Husam Al-Najjar
Ghassan Beydoun
Bahareh Kalantar
Mohsen Zand
Naonori Ueda
author_facet Ziyi Yang
Husam Al-Najjar
Ghassan Beydoun
Bahareh Kalantar
Mohsen Zand
Naonori Ueda
author_sort Ziyi Yang
collection DOAJ
description This study evaluates remote sensing features to resolve problems associated with feature redundancy, low efficiency, and insufficient input feature analysis in bushfire detection. It calculates spectral features, remote sensing indices, and texture features from Sentinel-2 data for the Blue Mountains region of New South Wales, Australia. Feature separability was evaluated with three measures: J-M distance, discriminant index, and mutual information, leading to an assessment of the best remote sensing features. The results show that for post-fire smoke detection, the best features are the normalized difference vegetation index (NDVI), the B1 band, and the angular second moment (ASM) in the B1 band, with respective scores of 0.900, 0.900, and 0.838. For burned land detection, the best features are NDVI, the B2 band, and correlation (Corr) in the B5 band, with corresponding scores of 1.000, 0.9436, and 0.9173. These results demonstrate the effectiveness of NDVI, the B1 and B2 bands, and specific texture features in the post-fire analysis of remote sensing data. These findings provide valuable insights for the monitoring and analysis of bushfires and offer a solid foundation for future model construction, fire mapping, and feature interpretation tasks.
format Article
id doaj-art-7b2d28d4e4814af0a28a19726c82e2bf
institution DOAJ
issn 2072-4292
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-7b2d28d4e4814af0a28a19726c82e2bf2025-08-20T03:11:22ZengMDPI AGRemote Sensing2072-42922025-05-011711182310.3390/rs17111823Evaluation of Key Remote Sensing Features for Bushfire AnalysisZiyi Yang0Husam Al-Najjar1Ghassan Beydoun2Bahareh Kalantar3Mohsen Zand4Naonori Ueda5School of Computer Science, Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, AustraliaSchool of Computer Science, Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, AustraliaSchool of Computer Science, Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, AustraliaRIKEN Center for Advanced Intelligence Project, Disaster Resilience Science Team, Tokyo 103-0027, JapanResearch Computing Center, University of Chicago, Chicago, IL 60637, USARIKEN Center for Advanced Intelligence Project, Disaster Resilience Science Team, Tokyo 103-0027, JapanThis study evaluates remote sensing features to resolve problems associated with feature redundancy, low efficiency, and insufficient input feature analysis in bushfire detection. It calculates spectral features, remote sensing indices, and texture features from Sentinel-2 data for the Blue Mountains region of New South Wales, Australia. Feature separability was evaluated with three measures: J-M distance, discriminant index, and mutual information, leading to an assessment of the best remote sensing features. The results show that for post-fire smoke detection, the best features are the normalized difference vegetation index (NDVI), the B1 band, and the angular second moment (ASM) in the B1 band, with respective scores of 0.900, 0.900, and 0.838. For burned land detection, the best features are NDVI, the B2 band, and correlation (Corr) in the B5 band, with corresponding scores of 1.000, 0.9436, and 0.9173. These results demonstrate the effectiveness of NDVI, the B1 and B2 bands, and specific texture features in the post-fire analysis of remote sensing data. These findings provide valuable insights for the monitoring and analysis of bushfires and offer a solid foundation for future model construction, fire mapping, and feature interpretation tasks.https://www.mdpi.com/2072-4292/17/11/1823bushfireremote sensing indicestexture featurefeature separabilityJ-M distancediscriminant index
spellingShingle Ziyi Yang
Husam Al-Najjar
Ghassan Beydoun
Bahareh Kalantar
Mohsen Zand
Naonori Ueda
Evaluation of Key Remote Sensing Features for Bushfire Analysis
Remote Sensing
bushfire
remote sensing indices
texture feature
feature separability
J-M distance
discriminant index
title Evaluation of Key Remote Sensing Features for Bushfire Analysis
title_full Evaluation of Key Remote Sensing Features for Bushfire Analysis
title_fullStr Evaluation of Key Remote Sensing Features for Bushfire Analysis
title_full_unstemmed Evaluation of Key Remote Sensing Features for Bushfire Analysis
title_short Evaluation of Key Remote Sensing Features for Bushfire Analysis
title_sort evaluation of key remote sensing features for bushfire analysis
topic bushfire
remote sensing indices
texture feature
feature separability
J-M distance
discriminant index
url https://www.mdpi.com/2072-4292/17/11/1823
work_keys_str_mv AT ziyiyang evaluationofkeyremotesensingfeaturesforbushfireanalysis
AT husamalnajjar evaluationofkeyremotesensingfeaturesforbushfireanalysis
AT ghassanbeydoun evaluationofkeyremotesensingfeaturesforbushfireanalysis
AT baharehkalantar evaluationofkeyremotesensingfeaturesforbushfireanalysis
AT mohsenzand evaluationofkeyremotesensingfeaturesforbushfireanalysis
AT naonoriueda evaluationofkeyremotesensingfeaturesforbushfireanalysis