Weike Li

This study integrates multi-source driving factors from 2005 to 2024, including meteorological elements, fire danger indices, vegetation, topography, and human activities, to comparatively analyze the performance of four machine learning models—RF, LightGBM, XGBoost, and DNN—in the daily scale prediction of forest and grassland fires in Sichuan Province. A Nested Cross-Validation framework, using year as the grouping variable, was employed to evaluate model robustness, and the SHAP method was introduced to quantify the driving mechanisms of the factors. The results indicate that LightGBM is the overall optimal model, with its ROC AUC reaching 0.9193 in nested cross-validation and 0.9411 in independent temporal testing, demonstrating superior predictive capability and cross-year generalization performance. SHAP analysis reveals a hierarchical structure of fire drivers: land type constitutes the a priori physical constraint for fire occurrence, meteorological and drought indicators dominate the differentiation of the risk gradient, while topography and human activities serve as spatial modulators. In an independent sample validation on 9 December 2024, high-fire-risk grids showed high consistency with the distribution of actual fire points. For transmission line application scenarios, a risk distribution map constructed by coupling fire risk values with wind speed thresholds successfully identified actual fire point areas, indicating that this framework can provide a scientific basis for forest and grassland fire prevention and for power grid enterprises to conduct precise early warning and regionalized control.

Near-surface wind field simulation in complex mountainous terrain is essential for predicting wildfire behavior and supporting fire risk management. WindNinja, a widely used diagnostic wind downscaling model, is strongly dependent on its initial input data; however, systematic evaluations of its input sensitivity and simulation accuracy remain limited. In this study, a representative canyon area was selected as the study site. WindNinja was driven by three types of input data: local meteorological station observations, national meteorological station observations, and ERA5-Land reanalysis data. Two indices—the Wind Forcing Intensity (WFI) index and the Thermal Forcing Intensity (TFI) index—were constructed to classify weather-forcing scenarios and evaluate simulation accuracy under different conditions. The results show that differences in the statistical characteristics of the initial wind sources produce pronounced sensitivity in WindNinja simulations. Simulations driven by local meteorological observations generally overestimate wind speed, whereas ERA5-Land-driven simulations systematically underestimate wind speed, with national-station results falling between these two cases. Simulation accuracy varies with terrain position: wind direction errors dominate in valleys, whereas wind speed errors dominate on ridges and hilltops. Weather background conditions significantly influence simulation accuracy. Wind forcing intensity dominates the magnitude and dispersion of simulation errors, while strong thermal forcing leads to an overall decline in simulation accuracy and stability. These findings highlight the sensitivity of WindNinja to initial wind sources and weather background conditions in complex terrain and provide guidance for its application and uncertainty control in wildfire behavior modeling.

This study aimed to systematically characterize the pyrolysis characteristics and combustibility of six typical tree species across different altitude gradients in southwestern Yunnan, providing references for fuel management and selection of potential fire-resistant species in this region. Thermogravimetric analysis (heating rate: 20 °C·min⁻¹, air atmosphere) was employed to obtain TG-DTG curves of bark, branches, and leaves. The Coats–Redfern integral method was applied to calculate kinetic parameters, and principal component analysis was conducted for comprehensive combustibility evaluation. The results demonstrated the following: (1) The pyrolysis process of all species underwent the following four distinct stages: moisture evaporation, holocellulose decomposition, lignin decomposition, and ash formation. Among these, holo-cellulose decomposition constituted the primary mass loss stage. Significant differences in pyrolysis characteristics were observed among different plant parts, with leaves and bark exhibiting lower initial pyrolysis temperatures; (2) The activation energy ranged from 56.05 to 86.41 kJ·mol⁻¹ across different components, with branches requiring the highest energy for pyrolysis; (3) Principal component analysis based on multiple indicators yielded the following comprehensive combustibility ranking: Pinus yunnanensis > Betula alnoides > Lithocarpus henryi > Quercus acutissima > Cunninghamia lanceolata > Myrica rubra; and (4) The combustibility assessment results integrating multiple variables (total mass loss rate, stage-specific mass loss, activation energy, and ash content) showed significant differences from the analysis based solely on activation energy, verifying the necessity of a multi-dimensional comprehensive evaluation.

In the context of climate change, increasingly severe forest fires present a significant threat to lives, property, ecosystem functionality, and the sustainable development of forest resources. As a result, there is an urgent need for rapid, efficient, and environmentally friendly technologies for fire suppression and containment. This paper begins by reviewing the current research on forest fire extinguishing agents and materials that hold promise for effective fire suppression. Among these agents, gaseous and foam extinguishing materials exhibit drawbacks such as low efficiency or significant environmental hazards. In contrast, natural polymer hydrogels, which are high in water content, environmentally friendly, and biodegradable, show significant potential for developing clean and efficient extinguishing materials. Furthermore, this paper discusses existing environmental assessment standards for fire extinguishing agents, as well as the assessment systems proposed in various studies. It finds that, while universal assessment standards are fairly well-established, current research primarily focuses on enhancing fire suppression performance. However, the environmental performance assessment of forest fire extinguishing agents—often used in large quantities—remains inadequate. Therefore, there is an urgent need to establish a comprehensive and systematic environmental assessment system to address this theoretical and practical gap.

This study investigates the latency of lightning-caused fires in the boreal coniferous forests of the Greater Khingan Mountains, employing advanced machine learning techniques to analyze the relationship between meteorological factors, lightning characteristics, and fire ignition and smoldering processes. Using the Random Forest Model (RFM) combined with Recursive Feature Elimination with Cross-Validation (RFECV) and SHapley Additive exPlanations (SHAP), the study identifies key factors influencing fire latency. Two methods, Min distance and Min latency, were used to determine ignition lightning, with the Min distance method proving more reliable. The results show that lightning-caused fires cluster spatially and peak temporally between May and July, aligning with lightning activity. The Fine Fuel Moisture Code (FFMC) and precipitation were identified as the most influential factors. This study underscores the importance of fuel moisture and weather conditions in determining latency of lightning-caused fire, offering valuable insights for enhancing early warning systems. Despite limitations in data resolution and the exclusion of topographic factors, this study advances our understanding of lightning-fire latency mechanisms and provides a foundation for more effective wildfire management strategies under climate change.