NASA Teams Up With Amazon to Study Solar Superstorms

Unsupervised learning and anomaly detection are being applied to learn what makes a solar storm a superstorm.

Solar superstorms are rare, occurring about once every 50 years, but when it happens, they send an electric current that can cause a lot of havoc down on earth.

A super solar storm was to blame for the Hydro-Quebec electric grid collapsing in March of 1989 and for 200 different reports of power grid malfunctions in the U.S. at the same time. 

RELATED: SOLAR STORM MAKES AURORA BOREALIS VISIBLE IN NYC 

Solar superstorms are hard to study 

For years scientists have been studying what causes an average solar storm to morph into a superstorm and thanks to a partnership between Amazon and NASA they are now using advanced technology to look at that and how to create an early response system. 

"Predicting superstorms, and developing early response systems to these extreme events is a difficult endeavor. For one, given just how rare superstorms are, there are very few historical examples that can be used to train algorithms. This makes common machine learning approaches like supervised learning woefully inadequate for predicting superstorms," said Arun Krishnan, Amazon's science editor in a blog post

"Additionally, with dozens of past and current satellites gathering space weather information from different key vantage points around Earth, the amount of data is prodigious -- and the attempt to find correlations laborious when searched conventionally."

Unsupervised learning, anomaly detection helps NASA study superstorms

To overcome the challenges NASA, AWS Professional Services and Amazon Machine Learning Solutions Lab are using unsupervised learnings and anomaly detection to understand the extreme conditions that are present with these superstorms. 

Through Amazon ML Solutions Lab, NASA scientists can connect with machine learning experts within the eCommerce giant.  Krishnan said in the blog post that with the power and speed of AWS, 1,000 data sets can be sifted through at one time which is helpful given NASA relies on classifying superstorms based on anomalies, specifically simultaneous observations of solar wind drivers and responses in the earth's magnetic field. 

“We have to look at superstorms holistically, just like meteorologists do with extreme weather events,” said Janet Kozyra, a heliophysicist who leads this project from NASA in the blog post.

“Research in heliophysics involves working with many instruments, often in different space or ground-based observatories. There’s a lot of data, and factors like time lags add to the complexity. With Amazon, we can take every single piece of data that we have on superstorms, and use anomalies we have detected to improve the models that predict and classify superstorms effectively."

Advertisement

Stay on top of the latest engineering news

Just enter your email and we’ll take care of the rest: