Deep learning for twelve hour precipitation forecasts
oleh: Lasse Espeholt, Shreya Agrawal, Casper Sønderby, Manoj Kumar, Jonathan Heek, Carla Bromberg, Cenk Gazen, Rob Carver, Marcin Andrychowicz, Jason Hickey, Aaron Bell, Nal Kalchbrenner
| Format: | Article |
|---|---|
| Diterbitkan: | Nature Portfolio 2022-09-01 |
Deskripsi
Can AI learn from atmospheric data and improve weather forecasting? The neural network MetNet-2 achieves this by forecasting the fast changing variable of precipitation up to 12 h ahead more accurately and efficiently than traditional models based on hand-coded physics.