Fuel Load Models for Different Tree Vegetation Types in Sichuan Province Based on Machine Learning DOI Open Access
Hongrong Wang,

H.F. Chen,

Fan Wu

et al.

Forests, Journal Year: 2024, Volume and Issue: 16(1), P. 42 - 42

Published: Dec. 29, 2024

(1) Objective: To improve forest fire prevention, this study provides a reference for risk assessment in Sichuan Province. (2) Methods: This research focuses on various vegetation types Given data from 6848 sample plots, five machine learning models—random forest, extreme gradient boosting (XGBoost), k-nearest neighbors, support vector machine, and stacking ensemble (Stacking)—were employed. Bayesian optimization was utilized hyperparameter tuning, resulting models predicting fuel loads (FLs) across different types. (3) Results: The FL model incorporates not only characteristics but also site conditions climate data. Feature importance analysis indicated that structural factors (e.g., canopy closure, diameter at breast height, tree height) dominated cold broadleaf, subtropical mixed forests, while mean annual temperature seasonality) were more influential coniferous forests. Machine learning-based outperform the multiple stepwise regression both fitting ability prediction accuracy. XGBoost performed best coniferous, with coefficient of determination (R2) values 0.79, 0.85, 0.81, 0.83, respectively. Stacking excelled achieving an R2 value 0.82. (4) Conclusions: establishes theoretical foundation capacity It is recommended be applied to predict broadleaf suggested FLs Furthermore, offers management, assessment, prevention control

Language: Английский

Interactions Between a High-Intensity Wildfire and an Atmospheric Hydraulic Jump in the Case of the 2023 Lahaina Fire DOI Creative Commons

Clifford Ehrke,

Angel Farguell, Adam K. Kochanski

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1424 - 1424

Published: Nov. 26, 2024

On 8 August 2023, a grass fire that started in the city of Lahaina, Hawai’i, grew into deadliest wildfire United States since 1918. This offers unique opportunity to explore impact high heat output on an atmospheric hydraulic jump and downslope wind event. We conducted two WRF-SFIRE simulations investigate these effects: one incorporating fire–atmosphere feedback other without it. Our findings revealed that, uncoupled simulation, moved inland significantly earlier than coupled simulation. altered pattern near front accelerating its lateral spread. The results suggest interactions their influence near-fire circulation may be more intricate previously understood. Specifically, while fire-induced acceleration is often linked enhanced spread, this study highlights cases where spread dominant, reduce cross-flank flow inhibit growth.

Language: Английский

Citations

0
Fuel Load Models for Different Tree Vegetation Types in Sichuan Province Based on Machine Learning DOI Open Access
Hongrong Wang,

H.F. Chen,

Fan Wu

et al.

Forests, Journal Year: 2024, Volume and Issue: 16(1), P. 42 - 42

Published: Dec. 29, 2024

(1) Objective: To improve forest fire prevention, this study provides a reference for risk assessment in Sichuan Province. (2) Methods: This research focuses on various vegetation types Given data from 6848 sample plots, five machine learning models—random forest, extreme gradient boosting (XGBoost), k-nearest neighbors, support vector machine, and stacking ensemble (Stacking)—were employed. Bayesian optimization was utilized hyperparameter tuning, resulting models predicting fuel loads (FLs) across different types. (3) Results: The FL model incorporates not only characteristics but also site conditions climate data. Feature importance analysis indicated that structural factors (e.g., canopy closure, diameter at breast height, tree height) dominated cold broadleaf, subtropical mixed forests, while mean annual temperature seasonality) were more influential coniferous forests. Machine learning-based outperform the multiple stepwise regression both fitting ability prediction accuracy. XGBoost performed best coniferous, with coefficient of determination (R2) values 0.79, 0.85, 0.81, 0.83, respectively. Stacking excelled achieving an R2 value 0.82. (4) Conclusions: establishes theoretical foundation capacity It is recommended be applied to predict broadleaf suggested FLs Furthermore, offers management, assessment, prevention control

Language: Английский

Citations

0