Google DeepMind has launched WeatherNext 2, a new artificial intelligence (AI) system designed to improve the speed and accuracy of global weather forecasts.
According to the company, the system can create forecasts up to eight times faster than traditional methods.
The goal behind WeatherNext 2 is to help governments and organizations prepare more effectively for severe weather events, which are becoming more common as the climate warms.
Did you know?
Subscribe – We publish new crypto explainer videos every week!
What Are Crypto Rollups? ZKSnarks vs Optimistic Rollups (ANIMATED)
The system produces many possible weather outcomes from one starting point, with each scenario generated in less than a minute using Google’s Tensor Processing Unit.
WeatherNext 2 is already part of several Google products, including Search, Gemini, Pixel Weather, and the Google Maps Weather API.
Akib Uddin, Product Manager at Google, said:
We’re working with the Google teams to integrate WeatherNext into our forecasting system. Whether you’re on Search, Android, or Google Maps, weather affects everyone.
Traditional forecasting systems often take hours to process data, which limits how often new updates can be released. DeepMind stated that WeatherNext 2 overcomes this challenge by using AI to deliver results faster while improving accuracy.
WeatherNext 2 builds on an earlier model called WeatherNext Gen, but performs better across nearly all tested measures.
Google DeepMind recently released a research preview of SIMA 2, the updated version of its artificial general intelligence (AGI) agent. How does it work? Read the full story.
