This work is devoted to the study and application of methods of intellectual analysis for the implementation of the scheme of the nowcasting of dangerous phenomena. In the course of the work, data sets were formed with differ in the methods of information processing for their preparation. For each set, a number of mathematical models were constructed for classifying cloud cells according to the degree of danger of tornadoes forming from them. The Python programming language has been chosen as the main development language. The work is of great practical importance in the field of forecasting weather events. Its novelty lies in the use of modern machine learning methodology, instead of the traditional approach to data extrapolation, widely used in various schemes of nowcasting.
Шершакова А.О., Пархоменко В.П. Методы интеллектуального анализа данных в модели наукастинга опасных явлений. Математическое моделирование и численные методы, 2021, № 3, с. 88–104.