Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9

The rapid advancement of deep learning (DL) technology significantly enhances early forest fire detection methods. However, traditional approaches often rely on fixed thresholds and supervised learning techniques, which may fail to account for the complex spatiotemporal dynamics associated with fore...

Full description

Saved in:
Bibliographic Details
Main Authors: Zekun Xu, Zhaoming Zhang, Guojin He, Shuaizhang Zhang, Tengfei Long, Guizhou Wang
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/10938890/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151018828922880
author Zekun Xu
Zhaoming Zhang
Guojin He
Shuaizhang Zhang
Tengfei Long
Guizhou Wang
author_facet Zekun Xu
Zhaoming Zhang
Guojin He
Shuaizhang Zhang
Tengfei Long
Guizhou Wang
author_sort Zekun Xu
collection DOAJ
description The rapid advancement of deep learning (DL) technology significantly enhances early forest fire detection methods. However, traditional approaches often rely on fixed thresholds and supervised learning techniques, which may fail to account for the complex spatiotemporal dynamics associated with forest fire events. To overcome this limitation, an adaptive DL model is proposed and specifically designed for early forest fire monitoring. This model integrates Stacking ConvLSTM to forecast mid-infrared brightness temperatures and employs a nonparametric dynamic thresholding method based on Otsu's algorithm for spatiotemporal anomaly detection, facilitating the identification of potential hotspots. By effectively capturing complex dependencies within spatiotemporal dimensions, this method improves detection accuracy. Furthermore, high-confidence early fire points are determined through dual-band analysis and land cover detection. Comparative experiments utilizing Himawari-8/9 satellite data reveal that the proposed method outperforms traditional techniques as well as the latest temporal methods, achieving an accuracy of 0.995, precision of 0.985, recall of 0.946, and an F1 score of 0.965. In addition, our method demonstrates an average fire detection delay of just 7 min and an average runtime of 71 s, underscoring its effectiveness in early forest fire detection. This approach serves as a robust tool for enhancing forest fire monitoring systems, offering significant implications for reducing response times and mitigating fire-related damages.
format Article
id doaj-art-ca00b6a7240e4c0993566f3fce8299ad
institution OA Journals
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-ca00b6a7240e4c0993566f3fce8299ad2025-08-20T02:26:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01189396940810.1109/JSTARS.2025.355489210938890Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9Zekun Xu0https://orcid.org/0009-0006-7297-0964Zhaoming Zhang1https://orcid.org/0000-0002-8779-2738Guojin He2Shuaizhang Zhang3Tengfei Long4Guizhou Wang5https://orcid.org/0000-0002-2347-8416Aerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing, ChinaAerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing, ChinaAerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing, ChinaAerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing, ChinaAerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing, ChinaAerospace Information Research Institute (AIR), Chinese Academy of Sciences (CAS), Beijing, ChinaThe rapid advancement of deep learning (DL) technology significantly enhances early forest fire detection methods. However, traditional approaches often rely on fixed thresholds and supervised learning techniques, which may fail to account for the complex spatiotemporal dynamics associated with forest fire events. To overcome this limitation, an adaptive DL model is proposed and specifically designed for early forest fire monitoring. This model integrates Stacking ConvLSTM to forecast mid-infrared brightness temperatures and employs a nonparametric dynamic thresholding method based on Otsu's algorithm for spatiotemporal anomaly detection, facilitating the identification of potential hotspots. By effectively capturing complex dependencies within spatiotemporal dimensions, this method improves detection accuracy. Furthermore, high-confidence early fire points are determined through dual-band analysis and land cover detection. Comparative experiments utilizing Himawari-8/9 satellite data reveal that the proposed method outperforms traditional techniques as well as the latest temporal methods, achieving an accuracy of 0.995, precision of 0.985, recall of 0.946, and an F1 score of 0.965. In addition, our method demonstrates an average fire detection delay of just 7 min and an average runtime of 71 s, underscoring its effectiveness in early forest fire detection. This approach serves as a robust tool for enhancing forest fire monitoring systems, offering significant implications for reducing response times and mitigating fire-related damages.https://ieeexplore.ieee.org/document/10938890/ConvLSTMHimawair-8/9spatiotemporal anomaly detectionwildfire
spellingShingle Zekun Xu
Zhaoming Zhang
Guojin He
Shuaizhang Zhang
Tengfei Long
Guizhou Wang
Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ConvLSTM
Himawair-8/9
spatiotemporal anomaly detection
wildfire
title Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9
title_full Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9
title_fullStr Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9
title_full_unstemmed Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9
title_short Adaptive Early Wildfire Monitoring Based on Spatiotemporal Prediction and Himawari 8/9
title_sort adaptive early wildfire monitoring based on spatiotemporal prediction and himawari 8 x002f 9
topic ConvLSTM
Himawair-8/9
spatiotemporal anomaly detection
wildfire
url https://ieeexplore.ieee.org/document/10938890/
work_keys_str_mv AT zekunxu adaptiveearlywildfiremonitoringbasedonspatiotemporalpredictionandhimawari8x002f9
AT zhaomingzhang adaptiveearlywildfiremonitoringbasedonspatiotemporalpredictionandhimawari8x002f9
AT guojinhe adaptiveearlywildfiremonitoringbasedonspatiotemporalpredictionandhimawari8x002f9
AT shuaizhangzhang adaptiveearlywildfiremonitoringbasedonspatiotemporalpredictionandhimawari8x002f9
AT tengfeilong adaptiveearlywildfiremonitoringbasedonspatiotemporalpredictionandhimawari8x002f9
AT guizhouwang adaptiveearlywildfiremonitoringbasedonspatiotemporalpredictionandhimawari8x002f9