Environment Canada said that over the past year, its “scientists and meteorologists have been carrying out extensive testing on the hybrid model, running it in parallel with our traditional model to evaluate its performance for predicting weather conditions in Canada.”
The department added it will continue to rely on its meteorologists, whose is judgment is “critical” to interpreting results and communicating them to the public.
Scientists for years have been using “AI” neural network models for approximating differential equations and parts of complex models. The transformer architecture is just the next step in that, which allows us to scale up training and get more capabilities out of neural nets.
As an example, Google just released TimesFM, which is an AI model for timeseries which is pretty cool
The reality is, when you’re working with large scale physical models there are differential equations involved which no human can properly parameterize and implement based on raw theory alone. These models let us use large amounts of data to infill that step.