Robust Prediction of Wildfire Spread in Australia

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 understa...

Full description

Saved in:
Bibliographic Details
Main Authors: Michael Palk, Katharina Knappmann, Stefan Voss, Raka Jovanovic
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11095684/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245974412656640
author Michael Palk
Katharina Knappmann
Stefan Voss
Raka Jovanovic
author_facet Michael Palk
Katharina Knappmann
Stefan Voss
Raka Jovanovic
author_sort Michael Palk
collection DOAJ
description 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.
format Article
id doaj-art-992c1a6348ba4540bb20cffd3941f15a
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-992c1a6348ba4540bb20cffd3941f15a2025-08-20T03:58:39ZengIEEEIEEE Access2169-35362025-01-011313270313272310.1109/ACCESS.2025.359212411095684Robust Prediction of Wildfire Spread in AustraliaMichael Palk0https://orcid.org/0000-0001-7463-6827Katharina Knappmann1Stefan Voss2https://orcid.org/0000-0003-1296-4221Raka Jovanovic3https://orcid.org/0000-0001-8167-1516Institute of Information Systems, University of Hamburg, Hamburg, GermanyInstitute of Information Systems, University of Hamburg, Hamburg, GermanyInstitute of Information Systems, University of Hamburg, Hamburg, GermanyQatar Environment and Energy Research Institute, Hamad Bin Khalifa University, Doha, QatarWildfires 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.https://ieeexplore.ieee.org/document/11095684/Predictive analyticstime series forecastingdeep learningtransformersrobust predictionHuber loss
spellingShingle Michael Palk
Katharina Knappmann
Stefan Voss
Raka Jovanovic
Robust Prediction of Wildfire Spread in Australia
IEEE Access
Predictive analytics
time series forecasting
deep learning
transformers
robust prediction
Huber loss
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 Predictive analytics
time series forecasting
deep learning
transformers
robust prediction
Huber loss
url https://ieeexplore.ieee.org/document/11095684/
work_keys_str_mv AT michaelpalk robustpredictionofwildfirespreadinaustralia
AT katharinaknappmann robustpredictionofwildfirespreadinaustralia
AT stefanvoss robustpredictionofwildfirespreadinaustralia
AT rakajovanovic robustpredictionofwildfirespreadinaustralia