Trending and emerging prospects of physics-based and ML-based wildfire spread models: a comprehensive review

Journal of Forestry Research, Journal Year: 2024, Volume and Issue: 35(1)

Published: Sept. 27, 2024

Language: Английский

---

SHAP-Driven Explainable Artificial Intelligence Framework for Wildfire Susceptibility Mapping Using MODIS Active Fire Pixels: An In-Depth Interpretation of Contributing Factors in Izmir, Türkiye

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(15), P. 2842 - 2842

Published: Aug. 2, 2024

Wildfire susceptibility maps play a crucial role in preemptively identifying regions at risk of future fires and informing decisions related to wildfire management, thereby aiding mitigating the risks potential damage posed by wildfires. This study employs eXplainable Artificial Intelligence (XAI) techniques, particularly SHapley Additive exPlanations (SHAP), map Izmir Province, Türkiye. Incorporating fifteen conditioning factors spanning topography, climate, anthropogenic influences, vegetation characteristics, machine learning (ML) models (Random Forest, XGBoost, LightGBM) were used predict wildfire-prone areas using freely available active fire pixel data (MODIS Active Fire Collection 6 MCD14ML product). The evaluation trained ML showed that Random Forest (RF) model outperformed XGBoost LightGBM, achieving highest test accuracy (95.6%). All classifiers demonstrated strong predictive performance, but RF excelled sensitivity, specificity, precision, F-1 score, making it preferred for generating conducting SHAP analysis. Unlike prevailing approaches focusing solely on global feature importance, this fills critical gap employing summary dependence plots comprehensively assess each factor’s contribution, enhancing explainability reliability results. analysis reveals clear associations between such as wind speed, temperature, NDVI, slope, distance villages with increased susceptibility, while rainfall streams exhibit nuanced effects. spatial distribution classes highlights areas, flat coastal near settlements agricultural lands, emphasizing need enhanced awareness preventive measures. These insights inform targeted management strategies, highlighting importance tailored interventions like firebreaks management. However, challenges remain, including ensuring selected factors’ adequacy across diverse regions, addressing biases from resampling spatially varied data, refining broader applicability.

Language: Английский

---

Comparison of Different Models to Simulate Forest Fire Spread: A Case Study

Forests, Journal Year: 2024, Volume and Issue: 15(3), P. 563 - 563

Published: March 20, 2024

With the development of computer technology, forest fire spread simulation using computers has gradually developed. According to existing research on spread, models established in various countries have typical regional characteristics. A model a specific region is only suitable for local area, and there still great deal uncertainty as whether or not same fuel other regions. Although many been established, characteristics applicable each model, such loading, moisture content, combustibility, etc., are similar. It necessary evaluate applicability different models. We combined ground investigation, historical data collection, improvements, statistical analysis establish multi-model method (FIRER) that shows burning time, perimeter, overlap rate sites. This large-scale, high-resolution growth based eight directions regular 30 m grid. could use any one four physical (McArthur, Rothermel, FBP, Wang Zhengfei (China)) behavior. an option represent breaks from roads, rivers, suppression. can which more area. was tested single lightning Daxing’an Mountains. Different scenarios were compared: behavior models, with off, suspected double ignition location fire. The results show Rothermel best Hanma fire; area 5694.4 hm2. Meanwhile, real FIRER 5800.9 hm2; both Kappa Sørensen values exceed 0.8, providing high accuracy simulations. performs well automatic identification break zones multiple ignited points. Compared FARSITE, predicting accuracy. BehavePlus, also advantages simulating large-scale spread. However, complex preparation stage means room improvement. provides practical basis comparison practicability effective tools scientific decision-making management fighting fires.

Language: Английский

---

Virtual modelling based fragility assessment of structures under bushfire propagation

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 245, P. 110000 - 110000

Published: Feb. 9, 2024

Driven by increased human activities in rural-urban interfaces, the construction of residential or commercial buildings these areas is experiencing a notable growing trend. In comparison to those built urban regions, structures, constructed are closer proximity natural vegetation, therefore facing heightened bushfire risk. The timely execution Structural Protection Plans (SPP) utmost importance case threats, where swift response within short timeframe necessary, considering diverse fragility characteristics structural components. To address this, present study introduces novel framework for assessing typical structures under both low and high wind speed conditions, specifically focusing on three key components: window frames, walls, roofs. assessment probability-based performed using newly developed limit state function takes into account influence multiple non-deterministic factors, including vegetative speed, different temperature thresholds components, fire time. Furthermore, enable rapid prediction fireground, virtual modelling (VM) technique, named extended support vector regression (X-SVR), introduced incorporated proposed framework. efficiency accuracy this technique intervals have been investigated validated through comprehensive real Australian house. poised provide valuable insights optimizing SPP swiftly identifying most fragile components practice.

Language: Английский

---

Comprehensive Experimental Studies on Smoldering Characteristics of Forest Soil from pinus sylvestris Vegetation

Fire and Materials, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 8, 2025

ABSTRACT Smoldering combustion, often linked with forest fires in coniferous forests, pose significant health and environmental risks, particularly densely populated countries like Germany, where these commonly occur wildland–urban interface (WUI) areas. This study investigates the combustion characteristics of Pinus sylvestris soil, focusing on underlying processes thermal behavior. The aim is to provide a comprehensive analysis smoldering pine specific focus fire‐exposed soil horizons. research integrates characterization, elemental analysis, heat determination, thermogravimetric (TGA) fractions ranging from < 0.063 > 4 mm, conducted under both air nitrogen atmospheres. derivative thermogravimetry (DTG) curves reveal that fastest mass loss occurs during pyrolysis, peak temperatures between 240°C 280°C. Activation energies ( E ) were calculated using Kissinger–Akahira–Sunose (KAS) Flynn–Wall–Ozawa (FWO) methods. highest activation observed conversion rates 0.2 0.4. at for all determined Kissinger method. Residue reveals variations organic content, 22.6% 92.7%. findings demonstrate German‐typical prone highlighting as preheating, drying, oxidation. As part German Pilot EUs TREEADS project, this provides essential data numerical simulations, emphasizing need consider physical chemical properties mitigate impact ecosystems.

Language: Английский

---

Simulation Study and Proper Orthogonal Decomposition Analysis of Buoyant Flame Dynamics and Heat Transfer of Wind-Aided Fires Spreading on Sloped Terrain

Fire, Journal Year: 2025, Volume and Issue: 8(4), P. 139 - 139

Published: March 31, 2025

The wind and slope are deemed to be the determinant factors driving extreme or erratic spread behavior of wildfire, which, however, has not been fully investigated, especially elaborate mechanism fire associated with heat transfer fluid dynamics. A systematic study is therefore carried out based on a physical-based simulation proper orthogonal decomposition (POD) analysis. Results show that compared wind, plays more profound effect structure; increase in slope, line undergoes transition from W-shape U- pointed V-shape, accompanied by stripe burning zones, indicating faster but incomplete combustion. distinguished mainly inducing turbulent backflow ahead front, while promotes convective heating via enhanced slant plume. Different mechanisms also identified for line, i.e., radiative affected combined effects flame length view angle, contrast, part flux dominated action attachment, which demonstrated play crucial role acceleration at higher slopes (>20°). POD analysis shows distinct pattern pulsating respective effects, sheds light modeling unsteady features spreading reconfirms necessity considering different these two environmental factors.

Language: Английский

---

Widespread negative impact of daytime warming on vegetation productivity

One Earth, Journal Year: 2025, Volume and Issue: unknown, P. 101284 - 101284

Published: April 1, 2025

Language: Английский

---

Nonballistic transport of particles in a canopy-plume system

Physical Review Fluids, Journal Year: 2025, Volume and Issue: 10(5)

Published: May 6, 2025

Language: Английский

---

Vulnerability Assessment of Industrial Sites to Interface Fires and Wildfires

Reliability Engineering & System Safety, Journal Year: 2023, Volume and Issue: 243, P. 109895 - 109895

Published: Dec. 17, 2023

In the framework of climate change, hazard caused by wildfires approaching anthropic settlements is raising an increasing concern.Fatalities and relevant damage to properties were recently affecting Wildland-Urban Wildland-Industrial Interfaces.Industrial sites storing large quantities hazardous materials are vulnerable interface fires, which have potential trigger specific cascading events such as Natech scenarios followed domino effects.The present study aims at providing a methodology for quantitative assessment vulnerability industrial exposed wildfires.The approach provides novel identification quantification all chains failures that may occur due or fires sites.The accounts thermal radiation from in both primary triggered dynamic features synergistic effects multiple also taken into account.The results case demonstrated importance considering behavior wildfire, strongly affects structures.The evidence emergency management first response on overall figures.

Language: Английский

---

Designing Climate Change (CC)-Resilient Asphalt Pavement Structures: A Comprehensive Literature Review on Adaptation Measures and Advanced Soil Constitutive Models

Results in Engineering, Journal Year: 2024, Volume and Issue: 24, P. 103648 - 103648

Published: Dec. 1, 2024

Language: Английский

---