ISSN 1000-0526
CN 11-2282/P
CN 11-2282/P
Research on Wind Speed Downscaling Correction of Numerical Forecasting Models for Inland Waterway Areas
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
The refinement level of wind forecasting in numerical weather forecasting models cannot meet the needs of inland waterway transportation, and their adaptability to different regions varies. This article takes the western hills and central plains, most of them in Hubei Province, including the Yangtze River waterway, as research areas, Referring to the 10m wind of ART_1KM real-time product, this article analyzes the adaptability of 10m wind forecast of the European Central high-resolution atmospheric model deterministic forecasting product (EC-HRES) and the China Meteorological Administration mesoscale model forecasting product (CMA-MESO) in the research areas. A U-NET++ deep convolutional network model is constructed to achieve downscaling correction of wind speed forecast. The correction model improves the sampling module,and incorporates waterway item and terrain item into the loss function, enhancing the model"s expressive power and robustness, and improving the correction effect on the waterway. The verification shows that this method can effectively reduce the prediction error of wind speed on numerical forecasting models in the waterway area。
Keywords:
Project Supported:
Clc Number:
Mobile website
