摘要：Rainfall-induced debris flows in recently burned mountainous areas cause significant economic losses and human casualties. Currently, prediction of post-fire debris flows is widely based on the use of power-law thresholds and logistic regression models. While these procedures have served with certain success in existing operational warning systems, in this study we investigate the potential to improve the efficiency of current predictive models with machine-learning approaches. Specifically, the performance of a predictive model based on the random forest algorithm is compared with current techniques for the prediction of post-fire debris flow occurrence in the western United States. The analysis is based on a database of post-fire debris flows recently published by the United States Geological Survey. Results show that predictive models based on random forest exhibit systematic and considerably improved performance with respect to the other models examined. In addition, the random-forest-based models demonstrated improvement in performance with increasing training sample size, indicating a clear advantage regarding their ability to successfully assimilate new information. Complexity, in terms of variables required for developing the predictive models, is deemed important but the choice of model used is shown to have a greater impact on the overall performance.
