Editorial illustration for Google Brings WeatherNext 2 Forecast Data to Earth Engine and Vertex AI Platform
Google WeatherNext 2: AI Forecasting Breakthrough
WeatherNext 2 data now in Earth Engine, BigQuery; Vertex AI early access opens
Weather forecasting just got a major upgrade. WeatherNext 2’s forecast data is now live in Earth Engine and BigQuery, and early access on Vertex AI is open for custom model inference. This isn’t a simple tweak.
From a single input, neural networks inject noise in function space, generating hundreds of coherent weather outcomes. That means Google Search, Gemini, Pixel Weather, and Maps Platform’s Weather API already run on this technology. In weeks, Google Maps will follow.
The goal: capture every possibility, especially the worst-case ones you need to plan for.
WeatherNext 2's forecast data is now available in Earth Engine and BigQuery. We’re also launching an early access program on Google Cloud’s Vertex AI platform for custom model inference.
The single forecast is dead. We now walk into a future where uncertainty isn’t a bug, it’s the engine. Hundreds of potential paths, each one a coherent story, born from the same starting point.
That’s the power of injecting noise not into data, but into the very fabric of the model’s thinking. WeatherNext 2 doesn’t just predict the weather. It predicts the weather’s shadow.
Every worst-case scenario, every outlier, every event we’d rather ignore, now laid bare for planning, for resilience, for action. The same technology that sharpens your morning commute also arms a city against a Category 5. This is not an incremental step.
It’s a shift in how we see the atmosphere: not as a single future, but as a field of possibility. And we’ve only just opened the door to Vertex AI. The next era of forecasting isn’t about knowing what will happen.
It’s about being ready for everything that could.
Related Reading
Research & Benchmarks Google's FACTS benchmark shows 70% factuality ceiling across four tests
Research & Benchmarks Databricks finds multi-step agents beat single-turn RAG by 21% to 38% on STaRK
Research & Benchmarks Nvidia's DLSS 4.5 beta adds 6x Multi Frame Generation for RTX 50 GPUs
From Archives Stereogum persists amid streaming, AI and dwindling ad revenue as ads dry up
From Archives DeepEyesV2 Beats Larger Open-Source Models by Leveraging Search Tools
Common Questions Answered
What platforms is Google integrating WeatherNext 2 forecast data into?
Google is integrating WeatherNext 2 forecast data into Earth Engine, BigQuery, and Vertex AI platforms. The technology is also being incorporated into Google Search, Gemini, Pixel Weather, and Google Maps Platform's Weather API.
What is unique about Google's Vertex AI program for WeatherNext 2?
Google is launching an early access program on Vertex AI that allows for custom model inference of weather forecasts. This program provides developers and researchers the opportunity to create and adapt weather prediction models using Google's advanced WeatherNext 2 technology.
How does WeatherNext 2 improve weather forecasting capabilities?
WeatherNext 2 enables more precise climate and meteorological data predictions by using independently trained models to forecast multiple possible scenarios from a single input. The technology represents a significant upgrade in weather prediction accuracy and accessibility across various Google platforms.
Further Reading
- WeatherNext 2: Our most advanced weather forecasting model — Google DeepMind Blog
- A closer look at Earth Engine in BigQuery — Google Cloud Blog
- Google Cloud Brings WeatherNext AI-Powered Weather Predictions to Enterprises — Blue Mountain Eagle
- WeatherNext 2 | Earth Engine Data Catalog — Google for Developers
