May

22

Learning skillful medium-range global weather forecasting, from Google DeepMind:

Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute resources to improve forecast accuracy but does not directly use historical weather data to improve the underlying model. Here, we introduce GraphCast, a machine learning–based method trained directly from reanalysis data. It predicts hundreds of weather variables for the next 10 days at 0.25° resolution globally in under 1 minute. GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclone tracking, atmospheric rivers, and extreme temperatures. GraphCast is a key advance in accurate and efficient weather forecasting and helps realize the promise of machine learning for modeling complex dynamical systems.

Asindu Drileba writes:

I looked and how they split the surface of the earth into tiny meshes in order to form a Graph upon which the rest of the model is built. This technique's description looked familiar to another technique called "Numerical Weather Prediction" or "NWP". The paper by Deep Mind does have several papers referencing "Numerical Weather Prediction" or "NWP".

I learnt about NWP from this PBS Nova documentary, Prediction By The Numbers. The documentary has many descriptions on tools for predicting. Wisdom of the Crowds, Probability Theory, and Numerical Weather Prediction. Meteorologists were interviewed and they showed their NWP programs in action (it is shown how the model generalized with time to predict a more accurate forecast of the in the weather). The meteorologist says it is their best model and also goes ahead to say that "it works so well."


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search