GenCast predicts weather and the risk of extreme conditions with state-of-the-art accuracy

New AI model advances the prediction of weather uncertainties and risks, delivering faster and more accurate forecasts up to 15 days ahead

Weather affects us all – shaping our decisions, our safety and our lifestyles. As climate change drives more extreme weather events, accurate and reliable forecasts are more important than ever. Still, weather cannot be predicted perfectly, and forecasts are particularly uncertain beyond a few days.

Because a perfect weather forecast is not possible, scientists and weather agencies use probabilistic ensemble forecasts, in which the model predicts a range of likely weather scenarios. Such ensemble forecasts are more useful than relying on a single forecast, as they give decision makers a more complete picture of possible weather conditions in the coming days and weeks and how likely each scenario is.

Today in a newspaper published in Natureintroducing GenCast, our new high-resolution (0.25°) AI ensemble model. GenCast provides better forecasts of both daily weather and extreme events than the top operational system, the European Center for Medium-Range Weather Forecasts’ (ECMWF) ENS, up to 15 days in advance. We will release our model’s code, weights and forecasts to support the wider forecasting community.

The development of AI weather models

GenCast marks a critical advance in AI-based weather forecasting, building on our previous weather model, which was deterministic and provided a single, best estimate of future weather. In contrast, a GenCast forecast comprises an ensemble of 50 or more predictions, each representing a possible weather trajectory.

GenCast is a diffusion model, the type of generative AI model that supports the latest, rapid advances in image, video, and music generation. However, GenCast differs from these in that it is adapted to the Earth’s spherical geometry and learns to generate the complex probability distribution of future weather scenarios accurately when given the latest weather state as input.

To train GenCast, we provided it with four decades of historical weather data from ECMWFs ERA5 archive. This data includes variables such as temperature, wind speed and pressure at different altitudes. The model learned global weather patterns, at 0.25° resolution, directly from this processed weather data.

Sets a new standard for weather forecasting

To closely evaluate GenCast’s performance, we trained it on historical weather data up to 2018 and tested it on data from 2019. GenCast showed better forecasting skill than ECMWF’s ENS, the best operational ensemble forecasting system on which many national and local decisions depend every day.

We tested both systems thoroughly, looking at forecasts for different variables at different delivery times – 1320 combinations in total. GenCast was more accurate than ENS on 97.2% of these targets and on 99.8% for delivery times greater than 36 hours.

An ensemble forecast expresses uncertainty by making multiple predictions representing different possible scenarios. If most predictions show a cyclone hitting the same area, the uncertainty is low. But if they predict different places, the uncertainty is greater. GenCast finds the right balance and avoids both exaggerating or underestimating its confidence in its forecasts.

It takes a single Google Cloud TPU v5 only 8 minutes to produce a 15-day forecast in GenCast’s ensemble, and each forecast in the ensemble can be generated simultaneously, in parallel. Traditional physics-based ensemble forecasts such as those produced by the ENS, at 0.2° or 0.1° resolution, take hours on a supercomputer with tens of thousands of processors.

Advanced forecasting of extreme weather events

More accurate forecasts of extreme weather risks can help officials secure more lives, prevent damage and save money. When we tested GenCast’s ability to predict extreme heat and cold and high wind speeds, GenCast consistently outperformed ENS.

Now consider tropical cyclones, also known as hurricanes and typhoons. Getting better and more advanced warnings about where they will hit land is invaluable. GenCast delivers superior predictions of the tracks of these deadly storms.

Better forecasting can 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. In a proof-of-principle experiment that analyzed predictions of the total wind power generated by clusters of wind farms around the world, GenCast was more accurate than ENS.

Next generation forecasts and climate understanding at Google

GenCast is part of Google’s growing suite of next-generation AI-based weather models, including Google DeepMind’s AI-based deterministic medium-range forecastsand Google Research NeuralGCM, SEEDand flood models. These models are beginning to enhance user experiences on Google Search and Maps and improve forecasting precipitation, forest fires, flood and extreme heat.

We greatly value our partnerships with weather agencies and will continue to work with them to develop AI-based methods that improve their forecasts. Meanwhile, traditional models remain essential to this work. First, they provide the training data and initial weather conditions required by models such as GenCast. This collaboration between artificial intelligence and traditional meteorology highlights the power of a combined approach to improve forecasting and better serve society.

To foster broader collaboration and help accelerate research and development in the weather and climate community, we have made GenCast an open model and released its code and scalesas we did for our deterministic medium-range global weather forecast model.

We will soon release real-time and historical forecasts from GenCast and previous models, which will enable anyone to integrate these weather inputs into their own models and research workflows.

We are keen to engage with the wider weather community, including academic researchers, meteorologists, data scientists, renewable energy companies and organizations focused on food security and disaster preparedness. Such partnerships offer deep insight and constructive feedback, as well as invaluable opportunities for commercial and non-commercial influence, all of which are critical to our mission to apply our models for the benefit of humanity.