WeatherNext 2 by Google DeepMind
Google's most advanced and efficient forecasting model
# Research ToolWhat is WeatherNext 2 by Google DeepMind ?
WeatherNext 2 is Google DeepMind’s most advanced AI weather model, delivering forecasts up to 8× faster and at hourly resolution. Using a new Functional Generative Network, it generates hundreds of realistic scenarios to better capture uncertainty and extreme events. WeatherNext 2 now powers forecasts in Search, Gemini, Pixel Weather, and Google Maps, and is available in Earth Engine, BigQuery, and Vertex AI.
Problem
Users rely on traditional weather models that are slower and offer lower resolution, struggling with slower forecast generation (8× slower) and lower resolution (not hourly), leading to less accurate predictions and missed extreme events.
Solution
AI weather forecasting model enabling users to generate weather predictions up to 8× faster with hourly resolution using a Functional Generative Network, producing hundreds of scenarios to capture uncertainty and extreme events. Integrated into Google products like Maps and Vertex AI.
Customers
Meteorologists, data scientists, and developers in climate tech, agriculture, logistics, and disaster management seeking high-resolution, real-time weather forecasts.
Unique Features
Combines AI speed with a novel network architecture to model uncertainty via ensemble forecasting, directly embedded into Google’s ecosystem (Search, Maps, BigQuery).
User Comments
Accurate hourly forecasts for planning
Seamless integration with Google tools
Better extreme event detection
Reduced computational costs
Trust in Google/DeepMind’s AI
Traction
Powers Google Search, Gemini, Pixel Weather, and Maps; available in Earth Engine, BigQuery, and Vertex AI. Part of Google’s infrastructure serving billions of users.
Market Size
The global weather forecasting market was valued at $2.4 billion in 2023, projected to grow at 8.5% CAGR through 2030, driven by climate change and AI adoption.
