we're already able to forecast for 10 days using GraphCast

Researchers with Google DeepMind have built GraphCast, a Graph Neural Net for doing weather forecasting up to 10 days in advance.

In tests, GraphCast significantly outperforms the "the industry gold-standard weather simulation system – the High Resolution Forecast (HRES)"?.

Though not widely deployed yet, it is being experimented with "by weather agencies, including ECMWF, which is running a live experiment of our model’s forecasts on its website," the authors write. 

How GraphCast works:

"GraphCast takes as input the two most recent states of Earth’s weather—the current time and six hours earlier—and predicts the next state of the weather six hours ahead," they write in a research paper about the system. "Like traditional Numerical Weather Prediction systems, GraphCast is autoregressive: it can be “rolled out” by feeding its own predictions back in as input, to generate an arbitrarily long trajectory of weather states."

What GraphCast is

GraphCast is a good reminder that not every AI systems needs to be a mind-bendingly huge resource-dump; GraphCast is a neural net based on Graph neural Networks that has a total of 36.7 million parameters. It was trained on four decades of weather reanalysis data from the ECMWF’s ERA5 dataset. Training GraphCast took about four weeks on 32 TPU v4 devices.

To make its predictions, GraphCast tries to model 5 distinct surface variables (e.g, temperature, precipitation), 6 atmospheric variables (e.g, wind, humidity), and 37 distinct pressure levels.
 

Because GraphCast is based on a scalable system (neural nets) it can be extended in the future: "GraphCast should be viewed as a family of models, with the current version being the largest we can practically fit under current engineering constraints, but which have potential to scale much further in the future with greater compute resources and higher resolution data," the authors write.

• from importAI by Jack Clark.