Four hybrid machine learning algorithms to predict forest fire susceptibility

Huayu Zhang; Xiao Huang; Yi Ouyang; Xinyu Pi; Fuzhou Duan; Shiwan Zhao; Xiaoqin Luo

doi:10.1117/12.3020956

19 January 2024 Four hybrid machine learning algorithms to predict forest fire susceptibility

Huayu Zhang, Xiao Huang, Yi Ouyang, Xinyu Pi, Fuzhou Duan, Shiwan Zhao, Xiaoqin Luo

Proceedings Volume 12980, Fifth International Conference on Geoscience and Remote Sensing Mapping (ICGRSM 2023); 129801Z (2024) https://doi.org/10.1117/12.3020956
Event: Fifth International Conference on Geoscience and Remote Sensing Mapping (ICGRSM 2023), 2023, Lianyungang, China

Abstract

Forest fires are extremely hazardous, and forest fire sensitivity mapping can provide managers and planners with spatial information on forest fire susceptibility, which can help improve mountain fire prevention systems. In this study, 620 historical fire point data and 12 influence factors were selected, and multiple covariance analysis was used to analyse the correlation between the influence factors, eliminate the influence factors with high correlation and unfavourable to modeling, and normalize the influence factors using the frequency ratio method. In this paper, four different machine learning models, random forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGboost) and Boosted regression tree (BRT), are constructed, and the grid search or Bayesian optimization algorithm is applied to each model for hyper-parameter optimization, and the best parameters are selected and applied to the model. Finally, the model accuracy is evaluated using ROC curve and AUC. The results show that among the four hybrid machine learning models, the FR-RF model (AUC=0.88) and the FR-BRT model (AUC=0.97) perform better in forest fire risk assessment in Hunan Province.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Huayu Zhang, Xiao Huang, Yi Ouyang, Xinyu Pi, Fuzhou Duan, Shiwan Zhao, and Xiaoqin Luo "Four hybrid machine learning algorithms to predict forest fire susceptibility", Proc. SPIE 12980, Fifth International Conference on Geoscience and Remote Sensing Mapping (ICGRSM 2023), 129801Z (19 January 2024); https://doi.org/10.1117/12.3020956

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available