GIS-based spatial modeling of snow avalanches using four novel ensemble models

Abstract Snow avalanches can destroy lives and infrastructure and are very important phenomena in some regions of the world. This study maps snow avalanche susceptibility in Sirvan Watershed, Iran, using a new approach. Two statistical models – belief function (Bel) and probability density (PD) – are combined with two learning models – multi-layer perceptron (MLP) and logistic regression (LR) – to predict avalanche susceptibility using remote sensing data in a geographic information system. A snow avalanche inventory was generated from Google Earth imagery, regional documentation, and field surveys and it was mapped. Of 101 avalanche locations, 71 (70%) were used to train the models and 30 (30%) were used to validate the resulting models. Fourteen snow avalanche conditioning factors were used as independent variables in the predictive modeling process. Bel and PD techniques were applied to each class of factors to map snow avalanche susceptibility by combining these primary models with MLP and LR models. The results were validated using positive predictive values, negative predictive values, sensitivity, specificity, accuracy, root-mean-square error, and area-under-the-curve (AUC) values. Thus, the AUCs for the PD-LR, Bel-LR, Bel-MLP, and PD-MLP hybrid models are 0.941, 0.936, 0.931 and 0.924, respectively. Based on the validation results, the PD-LR hybrid model achieved the best accuracy among the models. This hybrid modeling approach can provide accurate and reliable evaluations of snow avalanche-prone areas for management and decision making.