Google’s new AI weather model may make 15-day forecasts more accurate

Google’s new AI-powered weather model could redefine how we forecast and prepare for changing conditions.

Google DeepMind, the company’s AI research division focused on solving scientific problems, on December 4 announced a new AI weather model called Gencastwhich promises to provide more accurate probabilities for different weather conditions up to 15 days in advance.

Although weather forecasting typically involves physics-based models, which can take hours to calculate on massive supercomputers, Google said it aims to achieve greater accuracy in just minutes. GenCast can generate a 15-day forecast scenario in just eight minutes using a Google Cloud Tensor Processing Unit chip, according to the company.

GenCast is part of Google’s expanding suite of AI-powered weather models, which includes improving Google Search and Google Maps with improved prediction of rainfall, wildfires, floods, and extreme heat.

It was the details of her latest tests published In the journal Nature.

Although Google’s AI model provided the best estimate of future weather, GenCast uses probability-based forecasting with 50 or more predictions about how the weather will change and assesses the likelihood of those scenarios. This technology works on a diffusion model, similar to machine learning models used in generative artificial intelligence.

The company explained in a statement: “We trained it on 40 years of historical data from the European Center for Medium-Range Weather Forecasts, which included variables such as temperature, wind speed, and pressure at different altitudes, which enabled it to learn.” tweet.

When forecasting extreme heat, cold and high wind speeds, Google said GenCast outperformed existing forecasting models. It also noted that it provides “superior forecasts” of the path of tropical cyclones up to five days in advance.