Open AccessAvalanches Forecasting Using Machine Learning Methods
Author(s) -
N. A. Radeev
Publication year - 2021
Publication title -
vestnik novosibirskogo gosudarstvennogo universiteta. seriâ: informacionnye tehnologii/vestnik novosibirskogo gosudarstvennogo universiteta. seriâ: informacionnye tehnologii v obrazovanii
Language(s) - English
Resource type - Journals
eISSN - 2410-0420
pISSN - 1818-7900
DOI - 10.25205/1818-7900-2021-19-2-92-101
Subject(s) - snowpack , snow , snow cover , range (aeronautics) , computer science , machine learning , predictive power , cover (algebra) , meteorology , training set , artificial intelligence , environmental science , engineering , geography , mechanical engineering , philosophy , epistemology , aerospace engineering
The occurrence of snow avalanches is mainly influenced by meteorological conditions and the configuration of snow cover layers. Machine learning methods have predictive power and are capable of predicting new events. From the trained machine learning models, an ensemble is obtained that predicts the possibility of avalanches. The model obtained in the article uses avalanche data, meteorological data and generated data on the state of snow cover for training. This allows the resulting solution to be used in more mountainous areas than solutions using a wider range of less available data. Snow data is generated by the SNOWPACK software package.