Researchers at Google’s AI research lab, Deepmind, have developed a new AI weather forecasting model called GenCast. In an article published in Nature, the company explains that this model provides faster and more accurate forecasts up to 15 days in advance. Google Deep Mind also explained how this new model works in a blog post. Here are all the details
Google DeepMind’s GenCast weather tracking AI model: How it works
This model, which outperforms the current leading system, uses probabilistic ensemble forecast to predict a range of possible weather scenarios, providing a more complete picture of future conditions.
Researchers also make GenCast’s code, weights, and forecasts public for the benefit of the broader weather forecasting community. This new model may be particularly crucial as climate change increases the frequency of extreme weather eventsmaking reliable forecasts more important than ever.
Unlike older models that only gave a single “best guess,” GenCast can provide many possibilities. weather forecastlike having 50 different weather reports. This can help to understand how the weather can change and what different things might happen.
GenCast uses a special type of AI that can create things like images, videos, and music. But instead of creating these elements, GenCast creates different weather possibilities. It’s as if the AI is imagining many ways the weather could change.
To teach GenCast how to do this, scientists showed it 40 years of weather data, such as temperatures, wind speeds and air pressure on objects. This allowed GenCast to learn everything about how weather works around the world.
To check the effectiveness of GenCast, the scientists tested it using weather data from 2019. They compared the model to the best weather forecasting system currently in use and GenCast was better at predicting the weather most of the time.
The researchers looked at many different weather elements, like temperature and wind, and GenCast was more accurate in almost all of them, especially when forecasting for the coming days.
GenCast is also good at knowing when it’s unsure about the weather. Just like when you’re not sure if it’s going to rain, the model will say “maybe” instead of being inaccurate.
The best part is that GenCast is super fast. It can predict the weather for 15 days in just 8 minutes. The old method of weather forecasting usually takes hours.
