Deep learning for twelve hour precipitation forecasts
Lasse Espeholt, Shreya Agrawal, Casper Kaae Sønderby, Manoj Kumar, Jonathan Heek, Carla Bromberg, Cenk Gazen, Robert W. Carver, Marcin Andrychowicz, Jason Hickey, Aaron J. Bell, Nal Kalchbrenner
Abstract
Existing weather forecasting models are based on physics and use supercomputers to evolve the atmosphere into the future. Better physics-based forecasts require improved atmospheric models, which can be difficult to discover and develop, or increasing the resolution underlying the simulation, which can be computationally prohibitive. An emerging class of weather models based on neural networks overcome these limitations by learning the required transformations from data instead of relying on hand-coded physics and by running efficiently in parallel. Here we present a neural network capable of predicting precipitation at a high resolution up to 12 h ahead. The model predicts raw precipitation targets and outperforms for up to 12 h of lead time state-of-the-art physics-based models currently operating in the Continental United States. The results represent a substantial step towards validating the new class of neural weather models.