IBM’s GRAF weather system tipped to set global forecasting on new level

An August 2018 monsoon in India, shown by the best current weather model that operates at 13-km resolution (left) while on the right, the new IBM Global High-Resolution Atmospheric Forecasting System (GRAF) operates at 3-km resolution and updates 6 to 12 times more often

A new high-resolution global weather forecast model will significantly improve weather forecasts in underserved regions like Africa and South America while also resolving convective weather on a global scale.

The new IBM Global High-Resolution Atmospheric Forecasting System (GRAF) will be the first hourly-updating commercial weather system that is able to predict something as small as thunderstorms globally. Compared to existing models, it will provide a nearly 200 per cent improvement in forecasting resolution for much of the globe (from 12 to 3 sq km). It will be available later this year.

GRAF – developed by IBM and its subsidiary The Weather Company – uses advanced IBM POWER9-based supercomputers, crowdsourced data from millions of sensors worldwide, and in-flight data to create more localised, more accurate views of weather globally.

“Today, weather forecasts around the world are not created equal, so we are changing that,” said Cameron Clayton, general manager of Watson Media and Weather for IBM. “Weather influences what people do day-to-day and is arguably the most important external swing factor in business performance. As extreme weather becomes more common, our new weather system will ensure every person and organization around the world has access to more accurate, more finely-tuned weather forecasts.”

Today, outside of the United StatesJapan and a handful of other countries primarily in Western Europe, the rest of the world has to settle for less accurate forecasts for predictions that cover 12- to 15-kilometre swathes of land — too wide to capture many weather phenomena. And, traditionally, leading weather models update less frequently, only every 6 to 12 hours. In contrast, GRAF will provide 3-kilometre resolution that updates hourly, delivering reliable predictions for the day ahead.

The new system will be the first to draw on untapped data such as sensor readings from aircraft, overcoming the lack of specialised weather equipment in many parts of the world. It will also give people the opportunity to contribute to helping improve weather forecasts globally, as it will be able to make use of pressure sensor readings sent from barometers found within smartphones if people opt-in to sharing that information. The Weather Company will assure it conforms to the relevant operating system terms of use. Additionally, hundreds of thousands of weather stations, many run by amateur weather enthusiasts, can also contribute data to the model.

While the resulting volume of data would be too much for most supercomputers, this powerful new model analyses data using IBM POWER9 technology, which is behind the US Department of Energy’s Summit and Sierra, the world’s most powerful supercomputers.

Predictions from the new system will be made available globally later in 2019, helping airlines to better minimise disruption from turbulence; insurers to better prepare for storm recovery operations; utility companies to better position repair crews for outages; farmers to better anticipate and prepare for dramatic shifts in weather and more.