Google's WeatherNext 3 Revolutionizes Ad Targeting with Hourly Predictions

Google has introduced WeatherNext 3, an advanced AI weather forecasting model that generates predictions every hour using live satellite data. This is a significant improvement from previous models, which relied on government-produced datasets updated every six hours.

The new model allows Google to target ads based on micro-climates, such as a sudden rainstorm in one specific neighborhood while a neighboring suburb remains sunny. Weather influences billions of decisions daily, and weather events like heatwaves and droughts have cascading impacts across agriculture, global supply chains, clean energy production, and national economies.

Developers and researchers can access real-time data via BigQuery, Earth Engine, and Google Cloud Storage (GCS). The forecast model includes real-time satellite data, with higher resolution, precise precipitation forecasting, and clean energy variables. This provides a global weather picture five times sharper than the previous model, WeatherNext 2.