Search for: All records

Predicting where runoff‐generated debris flows might occur during rainfall on steep, recently burned terrain is challenging. Studies of mass‐movement processes in unburned areas indicate that event locations are well‐predicted by rainfall anomaly,R*, in which peak observed rainfall is normalized by local rainfall climatology. Here, we use remote and field methods to map debris flows triggered within the 2020 Dolan Fire burn area in coastal California, demonstrate that a short‐durationR*metric predicts debris‐flow occurrence more effectively than absolute peak intensity or longer‐duration rainfall metrics, and show that incorporating anR*criterion into an existing debris‐flow likelihood model can reduce false positive predictions and improve accuracy. We testR* at three other climatically distinct fires in California, demonstrating its utility for mapping likely debris‐flow locations in different climates. We also consider howR*can benefit postfire debris‐flow prediction given recent increases in climatological variability within individual burn perimeters. 

Abstract Empirical thresholds for landslide warning systems have benefitted from the incorporation of soil‐hydrologic monitoring data, but the mechanistic basis for their predictive capabilities is limited. Although physically based hydrologic models can accurately simulate changes in soil moisture and pore pressure that promote landslides, their utility is restricted by high computational costs and nonunique parameterization issues. We construct a deep learning model using soil moisture, pore pressure, and rainfall monitoring data acquired from landslide‐prone hillslopes in Oregon, USA, to predict the timing and magnitude of hydrologic response at multiple soil depths for 36‐hr intervals. We find that observation records as short as 6 months are sufficient for accurate predictions, and our model captures hydrologic response for high‐intensity rainfall events even when those storm types are excluded from model training. We conclude that machine learning can provide an accurate and computationally efficient alternative to empirical methods or physical modeling for landslide hazard warning.