Google DeepMind has introduced WeatherNext 2, its most advanced weather forecasting model to date. The new system is designed to produce global weather predictions that are more efficient, more accurate, and higher in resolution than previous iterations.
According to the company, the model represents a step forward in applying AI to meteorology, offering a tool that could support better preparedness for weather-related events. The improvements in resolution mean forecasts can capture finer-grained atmospheric details, while gains in efficiency and accuracy make the model more practical for real-world use.
WeatherNext 2 builds on DeepMind's ongoing work in AI-driven weather prediction, positioning the model as a significant upgrade in the field. The announcement highlights the potential of machine learning to complement traditional numerical weather prediction methods.