IBM’s GRAF System for Accurate Weather Forecasting
By IndraStra Global News Team
On December 12, 2019, a survey report* released by IBM and it’s subsidiary The Weather Company shows that as many as 94% of top Indian business leaders believe climate change and adverse weather conditions have had a negative impact on business operations while around 72% believe they disrupt local economy. Moreover, 89% of the people in India expressed concern that climate change could hurt the economy. The report also revealed that a significant number of Indians said they were not confident about the local weather forecasts.
Last month, on November 14, IBM’s The Weather Company, launched a powerful new forecasting tool called IBM Global High-Resolution Atmospheric Forecasting (GRAF) System which is a high-precision, rapidly updating global weather model that updates hourly and at a 3km resolution to provide a clearer picture of weather activity around the globe. It can predict something as small as a thunderstorm virtually anywhere on the planet.
The new GRAF model employs a numerical modeling system that simulates the global atmosphere through a variable-resolution grid, resembling a honeycomb, that can be configured with higher resolution over areas of particular interest. Over the land areas, the GRAF grid elements will have average resolutions of 3 km, which is about 3–4 times greater than the European ECMWF and American GFS models.
This newest weather prediction system is made possible by The Weather Company’s open-source collaboration with the National Center for Atmospheric Research (NCAR). GRAF incorporates the latest-generation global weather model — the Model for Predictions Across Scales, or MPAS — which was developed by NCAR in conjunction with the Los Alamos National Laboratory.
Speaking on this, IBM Watson Media and Weather General Manager, Cameron Clayton said, “We are excited to launch GRAF model which is globally going to help much brut accuracy around the world especially, a place like India.”
“In the tests we ran, our model is around 30% more accurate (than Indian system) and we have so far designed to issue 12 million pieces of forecast information through IBM GRAF, which will improve the forecast quality massively in India,” Cameron said. “While we have collaborated with various governments across the country, we believe that the only way to get there is through a public-private partnership.”
IBM GRAF runs on an IBM POWER9-based supercomputer optimized for Graphics Processing Units (GPUs), optimized for handling the increased resolution and update frequency. This powerful new system is composed of 84 nodes of the IBM Power Systems AC922 server and 3.5 petabytes, or 3.5 quadrillion bytes, of IBM Spectrum Scale Storage. This is the same IBM POWER9 and IBM Storage technology used by the U.S Department of Energy’s supercomputers Summit and Sierra, the most powerful and smartest supercomputers in the world.
* This survey was conducted by Morning Consult on behalf of IBM from October 29 to November 4, among a national sample of 4,816 adults in India and the US.
To learn more about IBM GRAF and it’s applications, please watch this YouTube video — DEMOCRAYIZING THE WORLD’s WEATHER DATA