Intersections of Machine Learning and Physical Science: Three Use Cases

Dale Durran
Univ of Washington
  6 Apr, 2pm, in google meet

We compare the performance of an ensemble-weather-prediction system based on a global deep-learning weather-prediction (DLWP) model with reanalysis data and forecasts from the European Center for Medium Range Weather Forecasts (ECMWF) ensemble for subseasonal weather prediction.

The model is trained using ECMWF ReAnalysis 5 (ERA5) data with convolutional neural networks (CNNs) on a cubed-sphere grid using a loss function that minimizes forecast error over a single 24-hour period. The model predicts seven 2D shells of atmospheric data on roughly 150x150 km grids with a quasi-uniform global coverage. Notably, our model can be iterated forward indefinitely to produce forecasts at 6-hour temporal resolution for any lead time. We present case studies showing the extent to which the model is able to reproduce the dynamical evolution of atmospheric systems and its ability to learn "model physics" to forecast two-meter temperature and precipitation. Sources of ensemble spread and the performance of the ensemble are discussed relative to the ECMWF S2S ensemble forecasts.