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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.