RUS  ENG
Full version
JOURNALS // Russian Journal of Cybernetics // Archive

Russian Journal of Cybernetics, 2025 Volume 6, Issue 2, Pages 100–107 (Mi uk223)

Assessment and selection of an optimal model for forecasting the end of the frost period

V. A. Solozobov, S. A. Lysenkova

Surgut State University, Surgut, Russian Federation

Abstract: One of the first steps in developing a mathematical forecasting model is to define the criteria for evaluating and selecting the optimal model from among several candidates. Since modelling objectives can vary, the choice of evaluation method must align with the specific goal of the study. The accuracy and usefulness of the final result depend heavily on how the model is assessed. In this study, we developed a procedure for evaluating and selecting a model to forecast the end of the frost period in the spring–summer season.

Keywords: assessment methods, quality metric, neural network, weather forecast, frost.



© Steklov Math. Inst. of RAS, 2025