paper
2023
Downscaling & super-resolution
Probabilistic & ensemble forecasting New model or method
CNN / U-NetJapan Meteorological Agency (JMA) Journal
2023-06-06
018
Jun 2023
Tsuyoshi Thomas Sekiyama, Syugo Hayashi, Ryo Kaneko et al.
Artificial Intelligence for the Earth Systems
Japan Meteorological Agency (JMA)
A 20-member SRCNN ensemble downscales 5 km surface winds to 1 km around Tokyo, with the ensemble mean beating the input winds all year.
Downscaling & super-resolution
Surrogate Downscaling of Mesoscale Wind Fields Using Ensemble Superresolution Convolutional Neural Networks
In one sentence. A 20-member SRCNN ensemble downscales 5 km surface winds to 1 km around Tokyo, with the ensemble mean beating the input winds all year.
Labels
- Topic
- Downscaling & super-resolution, Probabilistic & ensemble forecasting
- Type
- New model or method
- Method
- CNN / U-Net
- Domain
- Regional
- Data
- km-scale or high-res simulation
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-23-0007.1 OpenAlex:W4379521063
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.