In a joint collaboration, IBM and the Weather Channel, an IBM subsidiary, has unveiled a universal weather forecasting system, named Global High-Resolution Atmospheric Forecasting System (GRAF), to "provide the most accurate local weather forecasts ever seen worldwide".
According to IBM, GRAF is powered with IBM POWER9-based supercomputers, crowdsourced data from millions of sensors worldwide and in-flight data. The system, compared to existing models, will aim to provide"a nearly 200% improvement in forecasting resolution for much of the globe," IBM added.
An example of a GRAF forecast.
"Today, outside of the US, Japan 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 12–15km swaths of land," IBM said. "GRAF will provide 3km resolution that updates hourly, delivering reliable predictions for the day ahead."
In order to create the forecasts, GRAF will leverage crowdsourced, "untapped data", such as in-flight sensor readings and atmospheric pressure data from smartphones users with the Weather Channel app – if users opt-in to share the data.
"Today, weather forecasts around the world are not created equal, so we are changing that," Cameron Clayton, general manager of Watson Media and Weather for IBM said.
"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," he added.
GRAF can be leveraged by various industries. Some examples provided by the tech giant include the ability to assist airlines avoid disruptions and turbulence and helping farmers prepare for dramatic shifts in weather.
Forecasts from the new system will be made available later this year.