|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ПсковГУ |
||
AI-based spatial downscaling of surface wind fields over the Barents and Kara Seasстатья Исследовательская статья
- Авторы: Rezvov V.Yu, Krinitskiy M.A., Gavrikov A.V.
- Журнал: Moscow University Physics Bulletin
- Том: 80
- Год издания: 2025
- Издательство: Allerton Press
- Местоположение издательства: New York, N.Y., United States
- Номер статьи: 25
- Аннотация: This study explores the application of the AI-based approach for spatial downscaling of surface wind fields over the Barents and Kara Seas using deep artificial neural networks with skip connections. This method aims to improve spatial resolution while significantly reducing computational costs compared to non-hydrostatic modeling. Low-resolution input data are derived from the ERA5 global reanalysis, while high-resolution reference data are provided by WRF modeling. The results of AI-based downscaling are compared with the baseline bilinear interpolation. The proposed model enhances the mesoscale atmospheric structure and achieves a 50x increase in computational efficiency.
- Добавил в систему: Криницкий Михаил Алексеевич