XGBoost-Based Active Learning for Wildfire Risk Prediction

Machine learning has emerged as a key approach in wildfire risk prediction research. However, in practical applications, the scarcity of data for specific regions often hinders model performance, with models trained on region-specific data struggling to generalize due to differences in data distributions. While traditional methods based on expert knowledge tend to generalize better across regions, they are limited in leveraging multi-source data effectively, resulting in suboptimal predictive accuracy. This paper addresses this challenge by exploring how accumulated domain expertise in wildfire prediction can reduce model reliance on large volumes of high-quality data. An active learning algorithm is proposed based on XGBoost for wildfire risk assessment that autonomously identifies low-confidence predictions and seeks re-labeling through a human-in-the-loop or physics-based correction approach. This corrected data is reintegrated into the model, effectively preventing catastrophic forgetting. Experimental results demonstrate that the proposed human-in-the-loop approach significantly enhances labeling accuracy, predictive performance, and preserves the model’s ability to generalize. These findings highlight the value of incorporating human expertise into machine learning models, offering a practical solution to mitigate data quality challenges and improve model reliability in wildfire risk prediction.