ainewsblitz.com

Breaking

Google DeepMind's WeatherNext AI adds a day's lead time to cyclone forecasts

  • Foundation Models
  • Research & Papers
  • Open Source

Google DeepMind researchers say their WeatherNext AI models can forecast tropical cyclones with roughly an extra day of useful lead time, turning work that once needed building-sized supercomputers into 15-day runs that finish on a Tensor Processing Unit (TPU). In a Nature paper and a Google DeepMind technical account, Google DeepMind and Google Research report that three-day forecasts of a storm's track, intensity, and wind structure match the accuracy that leading operational models previously reached only two days out, an improvement they liken to about a decade of conventional meteorological progress.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,468 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year