The computer model, say the researchers, could help meteorologists make quicker and more accurate predictions in their forecasts. The framework, which ran on the Bridges supercomputer at the Pittsburgh Supercomputing Center , is based on machine learning linear classifiers and detects rotational movements in clouds from satellite images that might have otherwise gone unnoticed.
"The very best forecasting incorporates as much data as possible," says Steve Wistar, senior forensic meteorologist at AccuWeather. "There's so much to take in, as the atmosphere is infinitely complex. By using the models and the data we have [in front of us], we're taking a snapshot of the most complete look of the atmosphere."
In their work, the researchers worked with Wistar and other AccuWeather meteorologists to analyze more than 50,000 historical U.S. weather satellite images. In them, experts identified and labeled the shape and motion of "comma-shaped" clouds (see image) - cloud patterns that are strongly associated with cyclone formations, which can lead to severe weather events including hail, thunderstorms, high winds, and blizzards.
The researchers then used computer vision and machine learning techniques to teach algorithms to automatically recognize and detect comma-shaped clouds in satellite images. The system can then assist experts by pointing out in real time where, in an ocean of data, could they focus their attention in order to detect the onset of severe weather.
"Because the comma-shaped cloud is a visual indicator of severe weather events," says Rachel Zheng, a doctoral student in the College of Information Sciences and Technology (IST) at Penn State and the main researcher on the project, "our scheme can help meteorologists forecast such events."
The researchers found that their method can effectively detect comma-shaped clouds with 99% accuracy, at an average of 40 seconds per prediction. It was also able to predict 64% of severe weather events, outperforming other existing severe-weather detection methods.
"Our method can capture most human-labeled, comma-shaped clouds," says Zheng. "Moreover,