A new model for predicting the probability of post-fire debris flow occurrence in the western United States has been developed based on machine learning techniques, and evaluation with respect to the current state-of-the-art (USGS model) has demonstrated significant improvements in predictive performance (Nikolopoulos et al. 2018).
Figure 1. Locations of post-fire debris flows in the western US (upper left) and results on the predictive performance of the models. Source: Nikolopoulos et al., 2018.
 Nikolopoulos, Efthymios I., Elisa Destro, Md Abul Ehsan Bhuiyan, Marco Borga, and Emmanouil N. Anagnostou. “Evaluation of predictive models for post-fire debris flows occurrence in the western United States.” Natural Hazards and Earth System Sciences 18, no. 9 (2018): 2331-2343.