Google DeepMind’s GenCast uses AI to predict weather with extreme accuracy up to 15-days ahead. This diffusion model was trained on four decades of historical weather data from ECMWF’s ERA5 archive, which includes such variables as temperature, wind speed, and pressure at various altitudes.
The model managed to learn global weather patterns, at 0.25° resolution, directly from this processed weather data. Compared with hours on a supercomputer, it takes a single Google Cloud TPU v5 just 8 minutes to produce one 15-day forecast using GenCast’s ensemble. Even more impressive is the fact that every forecast in the ensemble can be generated simultaneously, in parallel.
- [Color LCD Screen Weather Station] Newentor temperature & humidity monitor with a large color LCD display shows essential home weather information at...
- [Two Power Modes & Adjustable Backlight] To enjoy a 24/7 continuous always-on vibrant display, simply connect this home weather station to a wall...
- [3-channel Home Weather Stations Wireless Indoor Outdoor] Wireless temperature forecast station supports up to 3 remote sensors to monitor inside...
Better forecasts could also play a key role in other aspects of society, such as renewable energy planning. For example, improvements in wind-power forecasting directly increase the reliability of wind-power as a source of sustainable energy, and will potentially accelerate its adoption,” said Ilan Price and Matthew Wilson, Google DeepMind researchers.
