Long-term avalanche hazard assessment with a Bayesian depth-averaged propagation model

While performing statistical dynamical simulations for avalanche predetermination, a propagation model must reach a compromise between precise description of the avalanche flow and computation times. Crucial problems are the choice of appropriate distributions describing the variability of the different inputs/outputs and model identifiability. In this study, a depth-averaged propagation model is used within a hierarchical Bayesian framework. First, the joint posterior distribution is estimated using a sequential Metropolis Hastings algorithm. Details for tuning the estimation algorithm are provided, as well as tests to check convergence. Of particular interest is the calibration of the two coefficients of a Voellmy friction law, with model identifiability ensured by prior information. Second, the point estimates are used to predict the joint distribution of different variables of interest for hazard mapping. Recent developments are employed to compute pressure distributions taking into account the rheology of snow. The different steps of the method are illustrated with a real case study, for which all possible decennial scenarios are simulated. It appears that the marginal distribution of impact pressures is strongly skewed, with possible high values for avalanches characterized by low Froude numbers. Model assumptions and results are discussed.