---
id: engines/weathernext-nvidia-earth-2
about:
  label: WeatherNext / NVIDIA Earth-2
  description: >-
    Weather prediction and supporting components, with different distribution
    and developer options.
tool:
  form: Forecast models and services
  group: Weather and climate
  audiences:
    - corporate
    - government
    - research
  homepage: >-
    https://blog.google/innovation-and-ai/models-and-research/google-deepmind/introducing-weathernext-3/
domains:
  - climate
relations:
  - predicate: answers
    target: questions/weather-and-climate
provenance:
  origin: survey
  sources:
    - title: 'Google: introducing WeatherNext 3, 3 September 2026'
      url: >-
        https://blog.google/innovation-and-ai/models-and-research/google-deepmind/introducing-weathernext-3/
    - title: 'Rasp et al.: WeatherNext 3 preprint, September 2026'
      url: 'https://arxiv.org/abs/2609.03582'
    - title: 'NVIDIA: Earth-2 open weather models, January 2026'
      url: 'https://blogs.nvidia.com/blog/nvidia-earth-2-open-models/'
  reviewed: 2026-09
  reviewed_by: 'survey draft, not yet rechecked'
  status: draft
import:
  source: openai-linkedin-scrape 2026-10-17
  id: DT017
  kind: forecast_model
  family: models_simulations_and_forecasts
  priority: high
  verified: true
  posts:
    - P003
    - P131
    - P146
  posters:
    - Yossi Matias
    - Emma Scharfmann
    - David Carlin
---
Inputs to weather-sensitive operations, risk and planning.

Forecast models and services. Listed in the survey under "Weather and climate". Audiences named there: corporate, government, research.