Google: How AI meets Physics to decode extreme weather
- lastmansurfing
- Jan 18
- 1 min read
Google is tackling one of the toughest challenges in global-scale weather and climate modelling: predicting precipitation, with its unpredictable timing, location and intensity.
To address this, Google has unveiled NeuralGCM, an open-source hybrid atmospheric model that merges ML with traditional physics-based simulation.
This fusion enables faster, more precise global atmospheric forecasts at significantly reduced computational cost.
NeuralGCM delivers notable accuracy improvements across key metrics – from average precipitation and extreme rainfall to the daily weather cycle – with standout performance in modelling the most intense 0.1% of rainfall events.
Read the full story | TECHNOLOGY MAGAZINE
