paper
2022
Nowcasting
Observations & remote sensing New model or method
CNN / U-Net0–6 h Preprint
2022-09-19
008
Sep 2022
Cong Feng
OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)
Occlusion-perturbed CNN forecasts 10-minute-ahead irradiance from sky images, reaching 5.62% nRMSE and a 2.77% nCRPS for probabilistic forecasts.
Occlusion-Perturbed Deep Learning for Probabilistic Solar Forecasting via Sky Images: Preprint
In one sentence. Occlusion-perturbed CNN forecasts 10-minute-ahead irradiance from sky images, reaching 5.62% nRMSE and a 2.77% nCRPS for probabilistic forecasts.
Labels
- Topic
- Nowcasting, Observations & remote sensing
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 0–6 h
- Domain
- Local / station
- Data
- Other
- Status
- Research
- Identifiers
- OpenAlex:W4296421826
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.