Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
3.2
Journals
Fire
Special Issues
Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire...
share announcement

Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects

A special issue of Fire (ISSN 2571-6255). This special issue belongs to the section "Fire Science Models, Remote Sensing, and Data".

Deadline for manuscript submissions: 31 May 2024 | Viewed by 7669

Special Issue Editors

Dr. Washington Rocha

E-Mail Website
Guest Editor
Department of Exact Sciences, Center for Earth and Environmental Sciences Modeling, State University of Feira de Santana, Feira de Santana, Brazil
Interests: spatial analysis; environmental monitoring; remote sensing image analysis; innovation
Special Issues, Collections and Topics in MDPI journals
Dr. António Vieira

E-Mail Website
Guest Editor
Department of Geography, University of Minho, Campus de Azurém, 4810-058 Guimarães, Portugal
Interests: geographic information systems and remote sensing and their application to land use planning; geomorphology; geomorphological heritage; erosive processes following forest fires and mitigation measures
Special Issues, Collections and Topics in MDPI journals
Dr. Marcos Francos

E-Mail Website
Guest Editor
Department of Geography, University of Salamanca, C/ Cervantes s/n, 37002 Salamanca, Spain
Interests: soil; wildfire; prescribed fire; forest management; land-use change

Special Issue Information

Dear Colleagues,

We are pleased to invite you to contribute to this Special Issue of Fire entitled “Machine Learning (Ml) and Deep Learning (Dl) Applications in Wildfire Science: Principles, Progress and Prospects”. Artificial Intelligence has been applied in wildfire science for the past 30 years, initially utilizing techniques like neural networks and expert systems. Since then, significant progress has been made, in parallel with the widespread adoption of machine learning (ML) and deep learning (DL) methods in the environmental sciences.

This Special Issue aims to compile the most recent research and advancements in Artificial Intelligence (AI) applications within wildfire science, covering their principles, progress, and prospects. We warmly welcome original research articles, reviews, and perspectives that not only contribute to a better understanding of machine learning (ML) and deep learning (DL) methods among wildfire researchers and managers, but also shed light on the diverse and challenging array of problems in wildfire science that can significantly benefit from the expertise of AI data scientists.

This Special Issue is dedicated to compiling the most recent research and advancements in Artificial Intelligence (AI) applications within wildfire science, covering their principles, progress, and prospects. We warmly welcome original research articles, reviews, and perspectives that not only contribute to a better understanding of machine learning (ML) and deep learning (DL) methods among wildfire researchers and managers, but also shed light on the diverse and challenging array of problems in wildfire science that can significantly benefit from the expertise of AI data scientists.

Papers cover a wide range of topics of interest utilizing AI, which include, but are not limited to:

  • Fuels characterization, fire detection, and mapping;
  • Fire weather and climate change;
  • Fire occurrence, susceptibility, and risk;
  • Fire behavior prediction;
  • Fire effects;
  • Fire management;
  • Mapping fire extent and severity;
  • Machine learning and big data analytics in wildfire analysis;
  • ML and DL methods;
  • Wildfire prevention and early warning systems;
  • Remote sensing and satellite imagery in wildfire monitoring;
  • Firefighting strategies and technologies;
  • Fire ecology and ecosystem management;
  • Socioeconomic impacts and community resilience to wildfires;
  • Integration of AI and drones for wildfire management;
  • Adaptive management and decision support systems in wildfire response;
  • Fire risk assessment and modeling;
  • Innovative approaches to wildfire suppression and containment;
  • Post-fire rehabilitation and restoration techniques;
  • Multi-agency collaboration and coordination in wildfire management;
  • Wildfire policy, governance, and public awareness efforts.

We look forward to your contribution to this Special Issue to the field of wildfire research and management through new advances in machine learning and deep learning methods.

Dr. Washington Rocha
Dr. António Vieira
Dr. Marcos Francos
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.

Keywords

  • wildfire research
  • Artificial Intelligence applications
  • wildfire risks
  • wildfire modelling
  • data science

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

23 pages, 14715 KiB  
Article
Predictive Modeling of Fire Incidence Using Deep Neural Networks
by Cheng-Yu Ku and Chih-Yu Liu
Fire 2024, 7(4), 136; https://doi.org/10.3390/fire7040136 - 12 Apr 2024
Viewed by 374
Abstract
To achieve successful prevention of fire incidents originating from human activities, it is imperative to possess a thorough understanding. This paper introduces a machine learning approach, specifically utilizing deep neural networks (DNN), to develop predictive models for fire occurrence in Keelung City, Taiwan. [...] Read more.
To achieve successful prevention of fire incidents originating from human activities, it is imperative to possess a thorough understanding. This paper introduces a machine learning approach, specifically utilizing deep neural networks (DNN), to develop predictive models for fire occurrence in Keelung City, Taiwan. It investigates ten factors across demographic, architectural, and economic domains through spatial analysis and thematic maps generated from geographic information system data. These factors are then integrated as inputs for the DNN model. Through 50 iterations, performance indices including the coefficient of determination (R2), root mean square error (RMSE), variance accounted for (VAF), prediction interval (PI), mean absolute error (MAE), weighted index (WI), weighted mean absolute percentage error (WMAPE), Nash–Sutcliffe efficiency (NS), and the ratio of performance to deviation (RPD) are computed, with average values of 0.89, 7.30 × 10−2, 89.21, 1.63, 4.90 × 10−2, 0.97, 2.92 × 10−1, 0.88, and 4.84, respectively. The model’s predictions, compared with historical data, demonstrate its efficacy. Additionally, this study explores the impact of various urban renewal strategies using the DNN model, highlighting the significant influence of economic factors on fire incidence. This underscores the importance of economic factors in mitigating fire incidents and emphasizes their consideration in urban renewal planning. Full article
(This article belongs to the Special Issue Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects)
►▼ Show Figures

Figure 1

14 pages, 1006 KiB  
Article
Time Series Classification with Multiple Wavelength Scattering Signals for Nuisance Alarm Mitigation
by Kyuwon Han, Soocheol Kim, Hoesung Yang, Kwangsoo Cho and Kangbok Lee
Fire 2024, 7(1), 14; https://doi.org/10.3390/fire7010014 - 29 Dec 2023
Viewed by 1173
Abstract
Smoke detectors are the most widely used fire detectors due to their high sensitivity. However, they have persistently faced issues with false alarms, known as nuisance alarms, as they cannot distinguish smoke particles, and their responsiveness varies depending on the particle size and [...] Read more.
Smoke detectors are the most widely used fire detectors due to their high sensitivity. However, they have persistently faced issues with false alarms, known as nuisance alarms, as they cannot distinguish smoke particles, and their responsiveness varies depending on the particle size and concentration. Although technologies for distinguishing smoke particles have shown promising results, the hardware limitations of smoke detectors necessitate an intelligent approach to analyze scattering signals of various wavelengths and their temporal changes. In this paper, we propose a pipeline that can distinguish smoke particles based on scattering signals of various wavelengths as input. In the data extraction phase, we propose methods for extracting datasets from time series data. We propose a method that combines traditional approaches, early detection methods, and a Dynamic Time Warping technique that utilizes only the shape of the signal without preprocessing. In the learning model and classification phase, we present a method to select and compare various architectures and hyperparameters to create a model that achieves the best classification performance for time series data. We create datasets for six different targets in our presented sensor and smoke particle test environment and train classification models. Through performance comparisons, we identify architecture and parameter combinations that achieve up to 98.7% accuracy. Ablation studies under various conditions demonstrate the validity of the chosen architecture and the potential of other models. Full article
(This article belongs to the Special Issue Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects)
►▼ Show Figures

Figure 1

12 pages, 7112 KiB  
Communication
An Image-Based Fire Monitoring Algorithm Resistant to Fire-like Objects
by Fang Xu, Xi Zhang, Tian Deng and Wenbo Xu
Fire 2024, 7(1), 3; https://doi.org/10.3390/fire7010003 - 20 Dec 2023
Viewed by 1509
Abstract
Due to its wide monitoring range and low cost, visual-based fire detection technology is commonly used for fire detection in open spaces. However, traditional fire detection algorithms have limitations in terms of accuracy and speed, making it challenging to detect fires in real [...] Read more.
Due to its wide monitoring range and low cost, visual-based fire detection technology is commonly used for fire detection in open spaces. However, traditional fire detection algorithms have limitations in terms of accuracy and speed, making it challenging to detect fires in real time. These algorithms have poor anti-interference ability against fire-like objects, such as emissions from factory chimneys, clouds, etc. In this study, we developed a fire detection approach based on an improved YOLOv5 algorithm and a fire detection dataset with fire-like objects. We added three Convolutional Block Attention Modules (CBAMs) to the head network of YOLOv5 to improve its feature extraction ability. Meanwhile, we used the C2f module to replace the original C2 module to capture rich gradient flow information. Our experimental results show that the proposed algorithm achieved a mAP@50 of 82.36% for fire detection. In addition, we also conducted a comparison test between datasets with and without labeling information for fire-like objects. Our results show that labeling information significantly reduced the false-positive detection proportion of fire-like objects incorrectly detected as fire objects. Our experimental results show that the CBAM and C2f modules enhanced the network’s feature extraction ability to differentiate fire objects from fire-like objects. Hence, our approach has the potential to improve fire detection accuracy, reduce false alarms, and be more cost-effective than traditional fire detection methods. This method can be applied to camera monitoring systems for automatic fire detection with resistance to fire-like objects. Full article
(This article belongs to the Special Issue Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects)
►▼ Show Figures

Figure 1

20 pages, 11597 KiB  
Article
Desert/Forest Fire Detection Using Machine/Deep Learning Techniques
by Mason Davis and Mohammad Shekaramiz
Fire 2023, 6(11), 418; https://doi.org/10.3390/fire6110418 - 29 Oct 2023
Viewed by 1952
Abstract
As climate change and human activity increase the likelihood of devastating wildfires, the need for early fire detection methods is inevitable. Although, it has been shown that deep learning and artificial intelligence can offer a solution to this problem, there is still a [...] Read more.
As climate change and human activity increase the likelihood of devastating wildfires, the need for early fire detection methods is inevitable. Although, it has been shown that deep learning and artificial intelligence can offer a solution to this problem, there is still a lot of room for improvement. In this research, two new deep learning approaches to fire detection are developed and investigated utilizing pre-trained ResNet-50 and Xception for feature extraction with a detailed comparison against support vector machine (SVM), ResNet-50, Xception, and MobileViT architectures. Each architecture was tuned utilizing hyperparameter searches and trials to seek ideal combinations for performance. To address the under-representation of desert features in the current fire detection datasets, we have created a new dataset. This novel dataset, Utah Desert Fire, was created using controlled fires and aerial imaging with a DJI Mini 3 Pro drone. The proposed modified ResNet-50 architecture achieved the best performance on the Utah Desert Fire dataset, reaching 100% detection accuracy. To further compare the proposed methods, the popular forest fire detection dataset, DeepFire, was deployed with resulting performance analyzed against most recent literature. Here, our proposed modified Xception model outperformed latest publications attaining 99.221% accuracy. The performance of the proposed solutions show an increase in classification accuracy which can be leveraged for the identification of both desert and forest fires. Full article
(This article belongs to the Special Issue Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects)
►▼ Show Figures

Figure 1

22 pages, 26862 KiB  
Article
RepVGG-YOLOv7: A Modified YOLOv7 for Fire Smoke Detection
by Xin Chen, Yipeng Xue, Qingshan Hou, Yan Fu and Yaolin Zhu
Fire 2023, 6(10), 383; https://doi.org/10.3390/fire6100383 - 07 Oct 2023
Cited by 1 | Viewed by 1632
Abstract
To further improve the detection of smoke and small target smoke in complex backgrounds, a novel smoke detection model called RepVGG-YOLOv7 is proposed in this paper. Firstly, the ECA attention mechanism and SIoU loss function are applied to the YOLOv7 network. The network [...] Read more.
To further improve the detection of smoke and small target smoke in complex backgrounds, a novel smoke detection model called RepVGG-YOLOv7 is proposed in this paper. Firstly, the ECA attention mechanism and SIoU loss function are applied to the YOLOv7 network. The network effectively extracts the feature information of small targets and targets in complex backgrounds. Also, it makes the convergence of the loss function more stable and improves the regression accuracy. Secondly, RepVGG is added to the YOLOv7 backbone network to enhance the ability of the model to extract features in the training phase, while achieving lossless compression of the model in the inference phase. Finally, an improved non-maximal suppression algorithm is used to improve the detection in the case of dense smoke. Numerical experiments show that the detection accuracy of the proposed algorithm can reach about 95.1%, which contributes to smoke detection in complex backgrounds and small target smoke. Full article
(This article belongs to the Special Issue Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects)
►▼ 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