Predicting the Duration of Forest Fires Using Machine Learning Methods DOI Creative Commons

Constantina Kopitsa,

Ioannis G. Tsoulos,

Vasileios Charilogis

et al.

Future Internet, Journal Year: 2024, Volume and Issue: 16(11), P. 396 - 396

Published: Oct. 28, 2024

For thousands of years forest fires played the role a regulator in ecosystem. Forest contributed to ecological balance by destroying old and diseased plant material; but modern era are major problem that tests endurance not only government agencies around world, also have an effect on climate change. become more intense, destructive, deadly; these known as megafires. They can cause economic problems, especially summer months (dry season). However, humanity has developed tool predict fire events, detect them time, their duration. This is artificial intelligence, specifically, machine learning, which one part AI. Consequently, this paper briefly mentions several methods learning used predicting early detection, submitting overall review current models. Our main objective venture into new field: duration ongoing fires. contribution offers way manage fires, using accessible open data, available from Hellenic Fire Service. In particular, we imported over 72,000 data 10-year period (2014–2023) techniques. The experimental validation results than encouraging, with Random achieving lowest value for error range (8–13%), meaning it was 87–92% accurate prediction Finally, some future directions extend research presented.

Language: Английский

Artificial intelligence for modeling and understanding extreme weather and climate events DOI Creative Commons
Gustau Camps‐Valls, Miguel‐Ángel Fernández‐Torres, Kai-Hendrik Cohrs

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: Feb. 24, 2025

In recent years, artificial intelligence (AI) has deeply impacted various fields, including Earth system sciences, by improving weather forecasting, model emulation, parameter estimation, and the prediction of extreme events. The latter comes with specific challenges, such as developing accurate predictors from noisy, heterogeneous, small sample sizes data limited annotations. This paper reviews how AI is being used to analyze climate events (like floods, droughts, wildfires, heatwaves), highlighting importance creating accurate, transparent, reliable models. We discuss hurdles dealing data, integrating real-time information, deploying understandable models, all crucial steps for gaining stakeholder trust meeting regulatory needs. provide an overview can help identify explain more effectively, disaster response communication. emphasize need collaboration across different fields create solutions that are practical, understandable, trustworthy enhance readiness risk reduction. Artificial Intelligence transforming study like helping overcome challenges integration. review article highlights models improve response, communication trust.

Language: Английский

Citations

3
Modeling of Forest Fire Risk Areas of Amazonas Department, Peru: Comparative Evaluation of Three Machine Learning Methods DOI Open Access
Alex J. Vergara, Sivmny V. Valqui-Reina, Dennis Cieza-Tarrillo

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(2), P. 273 - 273

Published: Feb. 5, 2025

Forest fires are the result of poor land management and climate change. Depending on type affected eco-system, they can cause significant biodiversity losses. This study was conducted in Amazonas department Peru. Binary data obtained from MODIS satellite occurrence between 2010 2022 were used to build risk models. To avoid multicollinearity, 12 variables that trigger selected (Pearson ≤ 0.90) grouped into four factors: (i) topographic, (ii) social, (iii) climatic, (iv) biological. The program Rstudio three types machine learning applied: MaxENT, Support Vector Machine (SVM), Random (RF). results show RF model has highest accuracy (AUC = 0.91), followed by MaxENT 0.87) SVM 0.84). In fire map elaborated with model, 38.8% region possesses a very low occurrence, 21.8% represents high-risk level zones. research will allow decision-makers improve forest Amazon prioritize prospective strategies such as installation water reservoirs areas zone. addition, it support awareness-raising actions among inhabitants at greatest so be prepared mitigate control generate solutions event occurring under different scenarios.

Language: Английский

Citations

1
Active wildfire detection via satellite imagery and machine learning: an empirical investigation of Australian wildfires DOI Creative Commons
Harikesh Singh, Li-Minn Ang, Sanjeev Srivastava

et al.

Natural Hazards, Journal Year: 2025, Volume and Issue: unknown

Published: March 6, 2025

Language: Английский

Citations

1
Research on the Simulation Model of Dynamic Shape for Forest Fire Burned Area Based on Grid Paths from Satellite Remote Sensing Images DOI Creative Commons
Xinsheng Ling, Gui Zhang,

Ying Zheng

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(1), P. 140 - 140

Published: Jan. 3, 2025

The formation of forest fire burned area, influenced by a variety factors such as meteorology, topography, vegetation, and human intervention, is dynamic process line burning that develops from the point ignition to boundary area. Accurately simulating predicting this can provide scientific basis for control suppression decisions. In study, five typical fires located in different regions China were used study object. straight path distances grid each on Sentinel-2 imageries target variables. We obtained values 11 independent variables pathway, including wind speed component, Temperature, Relative Humidity, Elevation, Slope, Aspect, Degree Relief, Normalized Difference Vegetation Index, Type, Fire Duration, Gross Domestic Product reflecting intervention capacity fires. value variable its corresponding constituted sample. Four machine learning models, Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Support Vector Machine (SVM), Multilayer Perceptron (MLP), trained using 80% effective samples four fires, 20% verify above models. hyper-parameters model optimized search method. After analyzing validation results models which showed temperature non-significant variable, training was repeated after excluding temperature. show RF optimal with 49.55 m root mean square error (RMSE), 29.19 absolute (MAE) 0.9823 coefficient determination (R2). This construct shape areas lengths all line. dynamically capture development scenes.

Language: Английский

Citations

0
BGG-REPT and ROF-REPT: ensemble machine learning models for the prediction of compressive strength of concrete DOI
Binh Thai Pham

Innovative Infrastructure Solutions, Journal Year: 2025, Volume and Issue: 10(2)

Published: Jan. 28, 2025

Language: Английский

Citations

0
Identification of forest fire-prone region in Lamington National Park using GIS-based multicriteria technique: validation using field and Sentinel-2-based observations DOI Creative Commons
Harikesh Singh, Sanjeev Srivastava

Geocarto International, Journal Year: 2025, Volume and Issue: 40(1)

Published: Feb. 10, 2025

Lamington National Park in Queensland, Australia, is increasingly threatened by wildfires, intensified climate change. This study integrates remote sensing, GIS, and the Analytical Hierarchy Process (AHP) to identify fire-prone areas within park. Eight parameters were analyzed, with major fuel type being most significant. Multispectral satellite data provided essential insights into landscape changes vegetation stress, enhancing understanding of wildfire risks. Historical records, field observations, sensing utilized develop validate a Forest Fire Risk Index map, highlighting heightened fire susceptibility northern eastern regions due subtropical humid conditions. The findings emphasise importance advanced spatial analysis for proactive management. Combining GIS multicriteria decision-making equips conservationists policymakers critical tools strengthen response strategies, safeguard vital ecosystems, protect surrounding communities. approach valuable managing similar landscapes globally.

Language: Английский

Citations

0
Deep reinforcement learning for optimal firebreak placement in forest fire prevention DOI

Lucas Murray,

Tatiana Castillo,

Isaac Martín de Diego

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: unknown, P. 113043 - 113043

Published: March 1, 2025

Language: Английский

Citations

0
A Comprehensive Review of Empirical and Dynamic Wildfire Simulators and Machine Learning Techniques used for the Prediction of Wildfire in Australia DOI Creative Commons
Harikesh Singh, Li-Minn Ang,

Dipak Paudyal

et al.

Technology Knowledge and Learning, Journal Year: 2025, Volume and Issue: unknown

Published: April 2, 2025

Language: Английский

Citations

0
Fire spread prediction models for surface fuels in subtropical forests of southern China DOI
Junjie Xu, Zhiwei Wu, Pan Zhao

et al.

Forestry An International Journal of Forest Research, Journal Year: 2025, Volume and Issue: unknown

Published: April 10, 2025

Abstract Subtropical forest fires are characterized by relatively small fire areas and high frequency of occurrence, with surface being the primary mode spread. There is limited research on simulating spread in subtropical regions, which hinders development application appropriate models. In this study, we assess suitability accuracy Rothermel model a Random Forest built experimental data for predicting rate (ROS) across different types fine fuel forests. We consider fuels from seven typical region China. A total 288 indoor experiments were conducted to simulate process under no-wind conditions, varying moisture content at four levels (5%, 10%, 15%, 20%) slope angle inclinations (0°, 10°, 20°, 30°). The ROS values obtained these used compare analyze predictive model, modified determine optimal model. Our findings show: (i) prediction conditions low not satisfactory when directly using coefficient determination (R2) 0.795, mean absolute error (MAE) 0.204 m·min−1, relative (MRE) 37.7%); (ii) Both (R2: 0.902, MAE: 0.098 MRE: 20.2%) 0.074 13.7%) demonstrate good performance similar accuracy; (iii) Given, its physical principles therefore potentially increased transportability, be most suitable examined models southern Jiangxi Province, China, slopes ranging 0° 30°. provides valuable guidance management suppression fires.

Language: Английский

Citations

0
Analysing Fire Propagation Models: A Case Study on FARSITE for Prolonged Wildfires DOI Creative Commons
Leonardo Martins, Rui Valente de Almeida,

António Maia

et al.

Fire, Journal Year: 2025, Volume and Issue: 8(5), P. 166 - 166

Published: April 23, 2025

With increasing wildfire severity and duration driven by climate change, accurately predicting fire behavior over extended time frames is critical for effective management mitigation of such wildfires. Fire propagation models play a pivotal role in these efforts, providing simulations that can be used to strategize respond active fires. This study examines the area simulator (FARSITE) model’s performance simulating recent events persisted 24 h with limited firefighting intervention mostly remote access areas across diverse ecosystems. Our findings reveal key insights into prolonged scenarios potentially informing improvements operational long-term predictive accuracy, as comparisons indexes showed reasonable results between detected fires from information resource systems (FIRMSs) first following days. A case Madeira Island highlights integration real-time weather predictions post-event data analysis. analysis underscores potential combining accurate forecasts retrospective validation improve capabilities dynamic environments, which guided development software platform designed analyse ongoing real-time, leveraging image satellite predictions.

Language: Английский

Citations

0