利用火灾跟踪卫星观测的基于注意力的野火蔓延模型

IF 3 3区 农林科学 Q2 ECOLOGY Fire-Switzerland Pub Date : 2023-07-29 DOI:10.3390/fire6080289
Y. Zou, M. Sadeghi, Yaling Liu, Alexandra Puchko, Son Le, Yang Chen, N. Andela, P. Gentine
{"title":"利用火灾跟踪卫星观测的基于注意力的野火蔓延模型","authors":"Y. Zou, M. Sadeghi, Yaling Liu, Alexandra Puchko, Son Le, Yang Chen, N. Andela, P. Gentine","doi":"10.3390/fire6080289","DOIUrl":null,"url":null,"abstract":"Modeling the spread of wildland fires is essential for assessing and managing fire risks. However, this task remains challenging due to the partially stochastic nature of fire behavior and the limited availability of observational data with high spatial and temporal resolutions. Herein, we propose an attention-based deep learning modeling approach that can be used to learn the complex behaviors of wildfires across different fire-prone regions. We integrate optimized spatial and channel attention modules with a convolutional neural network (CNN) modeling architecture and train the attention-based fire spread models using a recently derived fire-tracking satellite observational dataset in conjunction with corresponding fuel, terrain, and weather conditions. The evaluation results and their comparison with benchmark models, such as a deeper and more complex autoencoder model and the semi-empirical FARSITE fire behavior model, demonstrate the effectiveness of the attention-based models. These new data-driven fire spread models exhibit promising modeling performances in both the next-step prediction (i.e., predicting fire progression from one timestep earlier) and recursive prediction (i.e., recursively predicting final fire perimeters from initial ignition points) of observed large wildfires in California, and they provide a foundation for further practical applications including short-term active fire spread prediction and long-term fire risk assessment.","PeriodicalId":36395,"journal":{"name":"Fire-Switzerland","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2023-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Attention-Based Wildland Fire Spread Modeling Using Fire-Tracking Satellite Observations\",\"authors\":\"Y. Zou, M. Sadeghi, Yaling Liu, Alexandra Puchko, Son Le, Yang Chen, N. Andela, P. Gentine\",\"doi\":\"10.3390/fire6080289\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Modeling the spread of wildland fires is essential for assessing and managing fire risks. However, this task remains challenging due to the partially stochastic nature of fire behavior and the limited availability of observational data with high spatial and temporal resolutions. Herein, we propose an attention-based deep learning modeling approach that can be used to learn the complex behaviors of wildfires across different fire-prone regions. We integrate optimized spatial and channel attention modules with a convolutional neural network (CNN) modeling architecture and train the attention-based fire spread models using a recently derived fire-tracking satellite observational dataset in conjunction with corresponding fuel, terrain, and weather conditions. The evaluation results and their comparison with benchmark models, such as a deeper and more complex autoencoder model and the semi-empirical FARSITE fire behavior model, demonstrate the effectiveness of the attention-based models. These new data-driven fire spread models exhibit promising modeling performances in both the next-step prediction (i.e., predicting fire progression from one timestep earlier) and recursive prediction (i.e., recursively predicting final fire perimeters from initial ignition points) of observed large wildfires in California, and they provide a foundation for further practical applications including short-term active fire spread prediction and long-term fire risk assessment.\",\"PeriodicalId\":36395,\"journal\":{\"name\":\"Fire-Switzerland\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2023-07-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fire-Switzerland\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.3390/fire6080289\",\"RegionNum\":3,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fire-Switzerland","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.3390/fire6080289","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

模拟野火的蔓延对评估和管理火灾风险至关重要。然而,由于火灾行为的部分随机性和高时空分辨率观测数据的有限可用性,这项任务仍然具有挑战性。在此,我们提出了一种基于注意力的深度学习建模方法,可用于学习不同火灾易发地区野火的复杂行为。我们将优化的空间和通道注意力模块与卷积神经网络(CNN)建模架构集成在一起,并使用最近导出的火灾跟踪卫星观测数据集,结合相应的燃料、地形和天气条件,训练基于注意力的火灾蔓延模型。评估结果及其与基准模型(如更深更复杂的自编码器模型和半经验FARSITE火灾行为模型)的比较,证明了基于注意力的模型的有效性。这些新的数据驱动的火灾蔓延模型在加利福尼亚观测到的大型野火的下一步预测(即提前一个时间步预测火灾进展)和递归预测(即从初始着火点递归预测最终火灾周长)中都表现出了良好的建模性能,并为进一步的实际应用提供了基础,包括短期主动火灾蔓延预测和长期火灾风险评估。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Attention-Based Wildland Fire Spread Modeling Using Fire-Tracking Satellite Observations
Modeling the spread of wildland fires is essential for assessing and managing fire risks. However, this task remains challenging due to the partially stochastic nature of fire behavior and the limited availability of observational data with high spatial and temporal resolutions. Herein, we propose an attention-based deep learning modeling approach that can be used to learn the complex behaviors of wildfires across different fire-prone regions. We integrate optimized spatial and channel attention modules with a convolutional neural network (CNN) modeling architecture and train the attention-based fire spread models using a recently derived fire-tracking satellite observational dataset in conjunction with corresponding fuel, terrain, and weather conditions. The evaluation results and their comparison with benchmark models, such as a deeper and more complex autoencoder model and the semi-empirical FARSITE fire behavior model, demonstrate the effectiveness of the attention-based models. These new data-driven fire spread models exhibit promising modeling performances in both the next-step prediction (i.e., predicting fire progression from one timestep earlier) and recursive prediction (i.e., recursively predicting final fire perimeters from initial ignition points) of observed large wildfires in California, and they provide a foundation for further practical applications including short-term active fire spread prediction and long-term fire risk assessment.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Fire-Switzerland
Fire-Switzerland Multiple-
CiteScore
3.10
自引率
15.60%
发文量
182
审稿时长
11 weeks
期刊最新文献
Fire Risk of Polyethylene (PE)-Based Foam Blocks Used as Interior Building Materials and Fire Suppression through a Simple Surface Coating: Analysis of Vulnerability, Propagation, and Flame Retardancy Experimental Study on Combustion Behavior of U-Shaped Cables with Different Bending Forms and Angles Evaluation of Air Quality inside Self-Contained Breathing Apparatus Used by Firefighters Summer Compound Drought-Heat Extremes Amplify Fire-Weather Risk and Burned Area beyond Historical Thresholds in Chongqing Region, Subtropical China Identification Methodology for Chemical Warehouses Dealing with Flammable Substances Capable of Causing Firewater Pollution
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1