Machine Learning the Geostrophic Wind Balance in the Mid-latitudes 30: Graphs, NeuralGCM, ECMWF and HRES

A computer model that combines conventional weather-forecasting technology with machine learning has outperformed other artificial intelligence (AI)-based tools at predicting weather scenarios and long-term climate trends.

The ensemble model is a reference baseline which we use to achieve the best performance across the majority of lead times. We assess accuracy using (1) root-mean-squared error (RMSE), (2) root-mean-squared bias (RMSB), (3) continuous ranked probability score (CRPS) and (4) spread-skill ratio, with the results shown in Fig. 2. scorecards, metrics for additional variables and levels and maps are provided in extended data figs 1 and 2.

We examined the extent to which NeuralGCM, GraphCast and ECMWF-HRES capture the geostrophic wind balance, the near-equilibrium between the dominant forces that drive large-scale dynamics in the mid-latitudes30. There is a recent study that stated that Pangu downplays the vertical structure of the winds and they show a decline in lead times. Similarly, we observe that GraphCast shows an error that worsens with lead time. NeuralGCM depicts the vertical structure of the wind differently than GraphCast does, and it has a better ratio of wind to land compared to the other data. However, ECMWF-HRES still shows a slightly closer alignment to ERA5 data than NeuralGCM does. Within NeuralGCM, the representation of the geostrophic wind’s vertical structure only slightly degrades in the initial few days, showing no noticeable changes thereafter, particularly beyond day 5.

“Traditional climate models need to be run on supercomputers. This is a model you can run in minutes,” says study co-author Stephan Hoyer, who studies deep learning at Google Research in Mountain View, California.

“The issue with pure machine-learning approaches is that you’re only ever training it on data it’s already seen” says Scott Hosking, who researches AI and environmental data at the Alan Turing Institute in London. “The climate is continuously changing, we’re going into the unknown, so our machine-learning models have to extrapolate into that unknown future. By introducing physics into the model, we can ensure that our models aren’t unrealistic.

Hoyer and his colleagues are keen to further refine and adapt NeuralGCM. “We’ve been working on the atmospheric component of modelling the Earth’s system … It’s perhaps the part that most directly affects day-to-day weather,” Hoyer says. He adds that the team wants to incorporate more aspects of Earth science into future versions, to further improve the model’s accuracy.