Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.1
3.0
Journals
Fire
Special Issues
Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire...
share announcement

Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis

A special issue of Fire (ISSN 2571-6255). This special issue belongs to the section "Mathematical Modelling and Numerical Simulation of Combustion and Fire".

Deadline for manuscript submissions: closed (20 November 2024) | Viewed by 16709

Special Issue Editors

Dr. Yufei Zou

E-Mail Website
Guest Editor
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China
Interests: climate and fire modeling; fire risk assessment; extreme weather events
Dr. Futao Guo

E-Mail
Guest Editor
College of Forestry, Fujian Agriculture and Forestry University, Fuzhou, China
Interests: wildfire prediction; wildfire ecology; fire smoke
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Recent advances in machine learning techniques have revolutionized many fields, and fire modeling is no exception. Machine learning has the potential to significantly enhance the accuracy, efficiency, and predictive capabilities of fire modeling systems. This Special Issue of "Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis" aims to present the latest research and developments in the application of machine learning techniques to wildfire modeling.

Wildfire modeling plays a crucial role in various domains, including risk assessment, emergency response planning, and mitigation strategies. Traditional wildfire modeling approaches often rely on simplified assumptions and limited historical data. However, the complex nature of fire dynamics, evolving environmental conditions, and limited availability of comprehensive fire-related datasets present challenges to achieving an accurate fire simulation and prediction. Machine learning offers promising solutions to overcome these challenges by leveraging vast amounts of multi-source data, learning complex patterns, and making predictions based on learned associations. Recent research has shown that machine learning algorithms, such as support vector machines, random forests, and neural networks, can be effectively applied to wildfire modeling tasks, including but not limited to real-time fire detection, fire behavior prediction, fire susceptibility and risk mapping, and post-fire impact assessment. These techniques have the potential to capture intricate relationships between fire behavior, weather patterns, fuel characteristics, and other relevant factors like human activities.

This Special Issue aims to highlight the state-of-the-art research in machine learning applications in terms of wildfire modeling. It provides a platform for researchers and experts to exchange knowledge, present novel approaches, and discuss the future directions of this rapidly evolving field. We invite authors to submit their original research papers that showcase the innovative use of machine learning in wildfire modeling. Both theoretical and experimental studies are welcome, as well as practical applications in real-world fire scenarios.

Dr. Yufei Zou
Dr. Futao Guo
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fire is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

21 pages, 5465 KiB  
Article
Deep Learning Approaches for Wildfire Severity Prediction: A Comparative Study of Image Segmentation Networks and Visual Transformers on the EO4WildFires Dataset
by Dimitris Sykas, Dimitrios Zografakis and Konstantinos Demestichas
Fire 2024, 7(11), 374; https://doi.org/10.3390/fire7110374 - 23 Oct 2024
Viewed by 922
Abstract
This paper investigates the applicability of deep learning models for predicting the severity of forest wildfires, utilizing an innovative benchmark dataset called EO4WildFires. EO4WildFires integrates multispectral imagery from Sentinel-2, SAR data from Sentinel-1, and meteorological data from NASA Power annotated with EFFIS data [...] Read more.
This paper investigates the applicability of deep learning models for predicting the severity of forest wildfires, utilizing an innovative benchmark dataset called EO4WildFires. EO4WildFires integrates multispectral imagery from Sentinel-2, SAR data from Sentinel-1, and meteorological data from NASA Power annotated with EFFIS data for forest fire detection and size estimation. These data cover 45 countries with a total of 31,730 wildfire events from 2018 to 2022. All of these various sources of data are archived into data cubes, with the intention of assessing wildfire severity by considering both current and historical forest conditions, utilizing a broad range of data including temperature, precipitation, and soil moisture. The experimental setup has been arranged to test the effectiveness of different deep learning architectures in predicting the size and shape of wildfire-burned areas. This study incorporates both image segmentation networks and visual transformers, employing a consistent experimental design across various models to ensure the comparability of the results. Adjustments were made to the training data, such as the exclusion of empty labels and very small events, to refine the focus on more significant wildfire events and potentially improve prediction accuracy. The models’ performance was evaluated using metrics like F1 score, IoU score, and Average Percentage Difference (aPD). These metrics offer a multi-faceted view of model performance, assessing aspects such as precision, sensitivity, and the accuracy of the burned area estimation. Through extensive testing the final model utilizing LinkNet and ResNet-34 as backbones, we obtained the following metric results on the test set: 0.86 F1 score, 0.75 IoU, and 70% aPD. These results were obtained when all of the available samples were used. When the empty labels were absent during the training and testing, the model increased its performance significantly: 0.87 F1 score, 0.77 IoU, and 44.8% aPD. This indicates that the number of samples, as well as their respectively size (area), tend to have an impact on the model’s robustness. This restriction is well known in the remote sensing domain, as accessible, accurately labeled data may be limited. Visual transformers like TeleViT showed potential but underperformed compared to segmentation networks in terms of F1 and IoU scores. Full article
(This article belongs to the Special Issue Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis)
►▼ Show Figures

Figure 1

23 pages, 16416 KiB  
Article
Forest Fire Risk Prediction Based on Stacking Ensemble Learning for Yunnan Province of China
by Yanzhi Li, Guohui Li, Kaifeng Wang, Zumin Wang and Yanqiu Chen
Fire 2024, 7(1), 13; https://doi.org/10.3390/fire7010013 - 28 Dec 2023
Cited by 6 | Viewed by 2472
Abstract
Forest fire risk prediction is essential for building a forest fire defense system. Ensemble learning methods can avoid the problem of difficult model selection for disaster susceptibility prediction and can significantly improve modeling accuracy. This study introduces a stacking ensemble learning model for [...] Read more.
Forest fire risk prediction is essential for building a forest fire defense system. Ensemble learning methods can avoid the problem of difficult model selection for disaster susceptibility prediction and can significantly improve modeling accuracy. This study introduces a stacking ensemble learning model for predicting forest fire risks in Yunnan Province by integrating various data types, such as meteorological, topographic, vegetation, and human activity factors. A total of 70,274 fire points and an equal number of randomly selected nonfire points were used to develop the model, with 70% of the data allocated for training and the remaining 30% for testing. The stacking model combined four diverse machine learning methods: random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP). We evaluated the model’s predictive performance using metrics like accuracy, area under the characteristic curve (AUC), and fire density (FD). The results demonstrated that the stacking fusion model exhibited remarkable accuracy with an AUC of 0.970 on the test set, significantly surpassing the performance of individual machine learning models, which had AUC values ranging from 0.935 to 0.953. Furthermore, the stacking fusion model effectively captured the maximum fire density in extremely high susceptibility areas, demonstrating enhanced generalization capabilities. Full article
(This article belongs to the Special Issue Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis)
►▼ Show Figures

Figure 1

20 pages, 8294 KiB  
Article
Modeling Wildland Firefighters’ Assessments of Structure Defensibility
by Alexander J. Heeren, Philip E. Dennison, Michael J. Campbell and Matthew P. Thompson
Fire 2023, 6(12), 474; https://doi.org/10.3390/fire6120474 - 17 Dec 2023
Viewed by 2836
Abstract
In wildland–urban interface areas, firefighters balance wildfire suppression and structure protection. These tasks are often performed under resource limitations, especially when many structures are at risk. To address this problem, wildland firefighters employ a process called “structure triage” to prioritize structure protection based [...] Read more.
In wildland–urban interface areas, firefighters balance wildfire suppression and structure protection. These tasks are often performed under resource limitations, especially when many structures are at risk. To address this problem, wildland firefighters employ a process called “structure triage” to prioritize structure protection based on perceived defensibility. Using a dataset containing triage assessments of thousands of structures within the Western US, we developed a machine learning model that can improve the understanding of factors contributing to assessed structure defensibility. Our random forest models utilized variables collected by wildland firefighters, including structural characteristics and the surrounding ignition zone. The models also used landscape variables not contained within the triage dataset that captured important information about accessibility, vegetation, topography, and structure density. We achieved a high overall accuracy (77.8%) in classifying structures as defensible or non-defensible. The presence of a safety zone was the most important factor in determining structure defensibility. Road proximity, vegetation composition, and topography were also found to have high importance. In addition to improving the understanding of factors considered by wildland firefighters, communities could also gain from this information by enhancing their wildfire response plans, focusing on targeted mitigation, and improving their overall preparedness. Full article
(This article belongs to the Special Issue Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis)
►▼ Show Figures

Figure 1

22 pages, 6678 KiB  
Article
A Machine-Learning Approach to Predicting Daily Wildfire Expansion Rate
by Assaf Shmuel and Eyal Heifetz
Fire 2023, 6(8), 319; https://doi.org/10.3390/fire6080319 - 16 Aug 2023
Cited by 6 | Viewed by 6444
Abstract
Accurate predictions of daily wildfire growth rates are crucial, as extreme wildfires have become increasingly frequent in recent years. The factors which determine wildfire growth rates are complex and depend on numerous meteorological factors, topography, and fuel loads. In this paper, we have [...] Read more.
Accurate predictions of daily wildfire growth rates are crucial, as extreme wildfires have become increasingly frequent in recent years. The factors which determine wildfire growth rates are complex and depend on numerous meteorological factors, topography, and fuel loads. In this paper, we have built upon previous studies that have mapped daily burned areas at the individual fire level around the globe. We applied several Machine Learning (ML) algorithms including XGBoost, Random Forest, and Multilayer Perceptron to predict daily fire growth rate based on meteorological factors, topography, and fuel loads. Our best model on the entire dataset obtained a 1.15 km2 MAE. The ML model obtained a 90% accuracy when predicting whether a fire’s growth rate will increase or decrease the following day, compared to 61% using a logistic regression. We discuss the central factors that determine wildfire growth rate. To the best of our knowledge, this study is the first to perform such analyses on a global dataset. Full article
(This article belongs to the Special Issue Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis)
►▼ Show Figures

Figure 1

20 pages, 4796 KiB  
Article
Attention-Based Wildland Fire Spread Modeling Using Fire-Tracking Satellite Observations
by Yufei Zou, Mojtaba Sadeghi, Yaling Liu, Alexandra Puchko, Son Le, Yang Chen, Niels Andela and Pierre Gentine
Fire 2023, 6(8), 289; https://doi.org/10.3390/fire6080289 - 29 Jul 2023
Cited by 3 | Viewed by 2919
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 [...] Read more.
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. Full article
(This article belongs to the Special Issue Machine Learning-Based Wildfire Modeling: Unveiling Innovative Methodologies for Enhanced Fire Prediction and Analysis)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop