Modeling Wildfire Initial Attack Success Rate Based on Machine Learning in Liangshan, China

The initial attack is a critical phase in firefighting efforts, where the first batch of resources are deployed to prevent spread fire. This study aimed analyze and understand factors that impact success attack, used three machine learning models—logistic regression, XGBoost, artificial neural network—to simulate rate specific region. performance each model was evaluated based on accuracy, AUC (Area Under Curve), F1 Score, with results showing XGBoost performed best. In addition, also considered weather conditions by dividing scenario into normal extreme conditions. information can be useful for forest fire managers as they plan resource allocation, goal improving area.