Home > Cars > For this solar racing team, a full tank means…

For this solar racing team, a full tank means predicting the clouds

Few things in life are as constant as the sun. It peeks out from the east each morning, spreading warmth and light across the globe, before settling past the western horizon to wake up the rest of the world. That being said, predicting solar radiation is trickier than you might think.

For groups like the University of Michigan Solar Car Team, this presents a unique dilemma. Aurum, the team’s current race vehicle, is powered entirely by that burning ball of hydrogen in the sky, so accurate solar forecasts are crucial to keep the sleek and streamlined catamaran moving. They’re also essential when devising race strategies, such as when to put the hammer down and when to coast and conserve.

As the crew prepares for the Bridgestone World Solar Challenge — a week-long, 1,800-mile trek across the Australian outback — its members will lean on advanced solar forecasting technology courtesy of IBM Research. The system utilizes data from sensor networks, local weather stations, satellites, and multiple weather prediction models to anticipate exactly when and where the sun’s rays will be strongest, allowing the UM team to distribute energy to the car’s electric motors appropriately.

“The University of Michigan has been competing in solar car races for 25 years,” said Pavan Naik, Program Manager for the UM Solar Car Team. “In the past, we have not been able to capture and analyze the variety and amount of cloud data needed to confidently impact our race strategy. This year, IBM’s solar forecasting technology will allow us to know where the clouds are, where they are going, and where we should go faster in order to chase the sun.”

Related: Google sees ride sharing, solar power in the future of its self driving car

IBM’s tech was born from a program supported by the U.S. Department of Energy’s SunShot Initiative, which aims to both improve the accuracy of solar forecasts and more efficiently integrate the sun’s energy into the power grid. By using cognitive computing and machine learning, IBM claims it can predict weather patterns with up to 30 percent greater precision than by traditional means.

Practically, that means the UM team will know exactly how much solar energy will be available at a certain place at a certain time. For even greater assurance, a scout car will pace approximately one hour ahead of the bright yellow one-seater and use a sky camera to record real-time weather conditions. The Bridgestone World Solar Challenge kicks off down under on October 18.