When
Where
Speaker: Ana Isabel Fernandez Sirgo, Program in Applied Mathematics
Title: Predictive models for postfire debris flow initiation in the Southwest USA
Abstract: Postfire debris flows pose threats to life and infrastructure. They can also be an influential driver of sediment supply for upland channel networks, with implications for water quality, stream habitat, and landscape evolution. Models designed to assess postfire debris-flow likelihood at the watershed scale in response to design or forecast rainstorms are beneficial for identifying and mitigating postfire debris-flow hazards, and for modeling the long-term evolution of steep, fire-prone landscapes. This study used four machine learning (ML) algorithms, logistic regression, linear discriminant analysis, random forest, and XGBoost, to develop classification models for predicting postfire debris-flow likelihood at the watershed scale. We compile a new dataset of postfire debris-flow observations from the southwest USA, specifically from Arizona and New Mexico. The dataset includes information related to rainfall, terrain, fire severity, soil properties, and hydrogeomorphic response (i.e., debris flow or no debris flow) for 3144 rainfall events over 200 watersheds. Using these data, we developed two logistic regression models that can be used for debris-flow likelihood and classification predictions. The two models, which are based on rainfall, terrain, and fire severity metrics, provide spatially explicit predictions of debris-flow likelihood across burned landscapes. Both models use two features: one feature combines 15-minute rainfall accumulation and mean watershed slope, while the other combines 15-minute rainfall accumulation and a fire severity metric. When trained using these features, all four ML algorithms produced models with threat scores ranging from approximately 0.36 to 0.41, with logistic regression achieving the highest threat score. Results improve our ability to assess postfire debris-flow hazards in the southwest USA and provide general insight into how rainfall, terrain, and fire severity influences postfire debris-flow initiation.