Robust Prediction of Wildfire Spread in Australia

<p dir="ltr">Wildfires can have devastating effects on urban infrastructure and natural ecosystems, making wildfire management an important, but yet complex and difficult task. The systematic collection of data, increased computing power, and the development of physical models made i...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Michael Palk (17947841) (author)
مؤلفون آخرون: Katharina Knappmann (22928317) (author), Stefan Voss (17947844) (author), Raka Jovanovic (17947838) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513531471200256
author Michael Palk (17947841)
author2 Katharina Knappmann (22928317)
Stefan Voss (17947844)
Raka Jovanovic (17947838)
author2_role author
author
author
author_facet Michael Palk (17947841)
Katharina Knappmann (22928317)
Stefan Voss (17947844)
Raka Jovanovic (17947838)
author_role author
dc.creator.none.fl_str_mv Michael Palk (17947841)
Katharina Knappmann (22928317)
Stefan Voss (17947844)
Raka Jovanovic (17947838)
dc.date.none.fl_str_mv 2025-07-31T09:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2025.3592124
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Robust_Prediction_of_Wildfire_Spread_in_Australia/30971335
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological sciences
Ecology
Environmental sciences
Climate change impacts and adaptation
Ecological applications
Environmental management
Predictive analytics
time series forecasting
deep learning
transformers
robust prediction
Huber loss
Australian wildfires
Data models
Computational modeling
Forests
Time series analysis
Machine learning
Deep learning
dc.title.none.fl_str_mv Robust Prediction of Wildfire Spread in Australia
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Wildfires can have devastating effects on urban infrastructure and natural ecosystems, making wildfire management an important, but yet complex and difficult task. The systematic collection of data, increased computing power, and the development of physical models made it possible to get an understanding of the dynamics of wildfire spread. As exact computational simulations of wildfires are not feasible yet, several subtasks such as the estimation of the spread rate were analyzed with various methods in the literature. In this paper, different types of predictive models are evaluated to forecast the spread of wildfires on a daily and weekly basis in a comparative study. These models are tested on real-world data of wildfires from the seven Australian regions New South Wales, Northern Territory, Queensland, South Australia, Tasmania, Victoria, and Western Australia from 2005 to 2020, including weather, vegetation, and land cover class data, in a univariate and multivariate setting. Furthermore, relevant features are identified and discussed which can have an important influence on wildfire spread. We find that robust models, which are less sensitive to outliers, capture the dynamics of wildfire spread most accurately.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3592124" target="_blank">https://dx.doi.org/10.1109/access.2025.3592124</a></p>
eu_rights_str_mv openAccess
id Manara2_c2869c2b7f5662adeada7f025d6e3a83
identifier_str_mv 10.1109/access.2025.3592124
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30971335
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Robust Prediction of Wildfire Spread in AustraliaMichael Palk (17947841)Katharina Knappmann (22928317)Stefan Voss (17947844)Raka Jovanovic (17947838)Biological sciencesEcologyEnvironmental sciencesClimate change impacts and adaptationEcological applicationsEnvironmental managementPredictive analyticstime series forecastingdeep learningtransformersrobust predictionHuber lossAustralian wildfiresData modelsComputational modelingForestsTime series analysisMachine learningDeep learning<p dir="ltr">Wildfires can have devastating effects on urban infrastructure and natural ecosystems, making wildfire management an important, but yet complex and difficult task. The systematic collection of data, increased computing power, and the development of physical models made it possible to get an understanding of the dynamics of wildfire spread. As exact computational simulations of wildfires are not feasible yet, several subtasks such as the estimation of the spread rate were analyzed with various methods in the literature. In this paper, different types of predictive models are evaluated to forecast the spread of wildfires on a daily and weekly basis in a comparative study. These models are tested on real-world data of wildfires from the seven Australian regions New South Wales, Northern Territory, Queensland, South Australia, Tasmania, Victoria, and Western Australia from 2005 to 2020, including weather, vegetation, and land cover class data, in a univariate and multivariate setting. Furthermore, relevant features are identified and discussed which can have an important influence on wildfire spread. We find that robust models, which are less sensitive to outliers, capture the dynamics of wildfire spread most accurately.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3592124" target="_blank">https://dx.doi.org/10.1109/access.2025.3592124</a></p>2025-07-31T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3592124https://figshare.com/articles/journal_contribution/Robust_Prediction_of_Wildfire_Spread_in_Australia/30971335CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/309713352025-07-31T09:00:00Z
spellingShingle Robust Prediction of Wildfire Spread in Australia
Michael Palk (17947841)
Biological sciences
Ecology
Environmental sciences
Climate change impacts and adaptation
Ecological applications
Environmental management
Predictive analytics
time series forecasting
deep learning
transformers
robust prediction
Huber loss
Australian wildfires
Data models
Computational modeling
Forests
Time series analysis
Machine learning
Deep learning
status_str publishedVersion
title Robust Prediction of Wildfire Spread in Australia
title_full Robust Prediction of Wildfire Spread in Australia
title_fullStr Robust Prediction of Wildfire Spread in Australia
title_full_unstemmed Robust Prediction of Wildfire Spread in Australia
title_short Robust Prediction of Wildfire Spread in Australia
title_sort Robust Prediction of Wildfire Spread in Australia
topic Biological sciences
Ecology
Environmental sciences
Climate change impacts and adaptation
Ecological applications
Environmental management
Predictive analytics
time series forecasting
deep learning
transformers
robust prediction
Huber loss
Australian wildfires
Data models
Computational modeling
Forests
Time series analysis
Machine learning
Deep learning