[Pwnguinz]

What's the granularity of the prediction (I'm not sure if that's the correct word? I'm not a meteorologist)? Region level (100s km)? City level (a few 10s of kms)? Block level (a few kms)?

When you say it's on par with global weather models, how is "weather prediction accuracy" measured?

Cool, none-the-less!

[sureklix]

Very good question! These models are trained on ~40 years of ERA5 data –you can think of past forecasts from numerical models integrated with real observational data to have a continuous distribution of weather parameters (temperature, wind etc.) Therefore model resolution is 0.25 degrees (28km x 28km at the equator).

The way accuracy is measured is through picking targets (say temperature at 2 meters, at x,y lat & lon and forecasted 24h ago) and comparing them on RMSE and ACC (anomaly correlation co-efficient). For instance, in Google Graphcast paper they pick 1380 targets and the model out performs NWPs in 90% of them.

[m13uz]

To add to this, there are other ML models with higher resolution. For example, Google's MetNet-3 uses satellite radar images and ground measurements, and its resolution is 1km x 1km. And we are currently working on training a "nano" version of this!

Metnet-3: https://news.ycombinator.com/item?id=38122631