paper
2023
Post-processing & calibration
Observations & remote sensing New model or method
CNN / U-Net6 h–3 daysNanjing University of Information Science & Technology (NUIST) Journal
2023-01-01
022
Jan 2023
Jingming Xia, Qiao Liu, Ling Tan
IEEE Geoscience and Remote Sensing Letters
Nanjing University of Information Science & Technology (NUIST)
NFC-Net fuses FY-4A satellite, DEM and ERA5 data with a UNet to correct ECMWF forecasts, cutting 2m temperature and 10m wind speed RMSE by about 50%.
A Deep Learning Method Integrating Multisource Data for ECMWF Forecasting Products Correction
In one sentence. NFC-Net fuses FY-4A satellite, DEM and ERA5 data with a UNet to correct ECMWF forecasts, cutting 2m temperature and 10m wind speed RMSE by about 50%.
Labels
- Topic
- Post-processing & calibration, Observations & remote sensing
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Satellite, ERA5 / reanalysis
- Status
- Research
- Identifiers
- DOI:10.1109/lgrs.2023.3307717 OpenAlex:W4386088303
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.