AI algorithm brings us closer to forecasting the Northern Lights

A group of researchers used artificial intelligence to sort through nearly a billion images of the aurora borealis – the aurora borealis – which could help researchers understand and predict the remarkable natural phenomenon down the line.

The team developed a novel algorithm to sort through more than 706 million images of the aurora borealis in the THEMIS sky imager that were taken between 2008 and 2022. The algorithm classified the images into six categories based on their characteristics, which shows the utility of the software to categorize large-scale atmospheric datasets.

“The massive dataset is a valuable resource that can help researchers understand how the solar wind interacts with Earth’s magnetosphere, the protective bubble that protects us from charged particles streaming in from the sun,” said Jeremiah Johnson, researcher at the University of New Hampshire. and the main author of the study, in a university liberation. “But until now, its large size limited how effectively we could use this data.”

The search for the team –published last month in the Journal of Geophysical Research: Machine Learning and Computation— describes an algorithm trained to automatically label hundreds of millions of images of the aurora, potentially helping scientists discover the ethereal phenomenon at scale speed.

They have been there a lot of dawn this yearpartly because the Sun is at the peak of its solar cycle. The peak of the Sun’s 11-year solar cycle is defined by increased activity on the star’s surface, including eruptions of solar material (coronal mass ejections, or CMEs), and solar flares.

These events send charged particles into space, and when those particles react with particles in the Earth’s atmosphere, they cause an ethereal glow in the sky: the aurora. Particles can too disrupt the electronics and energy networks on Earth and in space, but we’re only talking about the good natural phenomena now, not the merciless chaos that space weather can rain down on humanity.

“The labeled database could reveal more insight into auroral dynamics, but at a very basic level, we aim to organize the THEMIS all-sky image database so that the vast amount of historical data that it can be used more effectively by researchers and provide a large enough sample for future studies,” said Johnson.

The intensity of solar storms is difficult to predict because scientists can’t accurately measure incoming solar flares until the particles are within an hour of reaching Earth.

The team sorted hundreds of millions of images into six categories: arc, diffuse, discrete, cloudy, moon and clear/no aurora. Scientists can gain by comparing the aurora with atmospheric data from the time the aurora occurred and link the phenomena to the solar event that ultimately caused the light show.

A better understanding of the chemical mix of solar particles and those in the Earth’s atmosphere will help scientists determine which types of auroras arise from each scenario, and the ability to quickly interrogate hundreds of millions of images ( compared to the rate of that work when done by humans). ) could be a boon for aurora research.