Workflow from Scientific Research

Aardvark at deployment time. First, an encoder module uses raw observations as input to estimate the initial state of the atmosphere across key variables at t = 0. Next, a processor module ingests the estimated state to produce a forecast at the next lead time t = t . Forecasts at subsequent lead times are produced autoregressively. Finally, a decoder module is applied to the on the grid states to produce off the grid predictions. The modular design of Aardvark allows for pretraining on large high-quality ERA5 reanalysis data 34. In this figure, the displayed data are the training data used to train each module of Aardvark from the aforementioned sources.

DOI