An AI algorithm brings us closer to predicting the Northern Lights

A team of researchers used artificial intelligence to sort through nearly a billion images of the aurora borealis (Northern Lights), which could help researchers understand and predict the remarkable natural phenomenon.

The team developed a new algorithm to sort through more than 706 million images of the aurora borealis in THEMIS all-sky images taken between 2008 and 2022. The algorithm divided the images into six categories based on their characteristics, which showed their usefulness. software for the classification of large-scale atmospheric data sets.

“The massive data set is a valuable resource that can help researchers understand how the solar wind interacts with Earth’s magnetosphere, the protective bubble that shields us from charged particles streaming in from the sun,” said University of New Hampshire researcher Jeremiah Johnson. and lead author of the study, at a university release. “But so far, its sheer size has limited how effectively we can use this data.”

Team research –has been published last month 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 rapidly explore the aether phenomenon at scale.

There was a lot of auroras this yearpartly because the Sun is at the peak of its solar cycle. The peak of the Sun’s 11-year solar cycle is marked 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 these particles react with particles in Earth’s atmosphere, they cause an ethereal glow in the sky: auroras. There may also be particles break electronics and electrical networks On Earth and in space, but we’re just talking about pretty natural phenomena now, not the merciless chaos that space weather can wreak upon humanity.

“A tagged database could provide more information about auroral dynamics, but at a very basic level, we aimed to organize the THEMIS all-sky imaging database so that the large amount of historical data it contains can be used more efficiently by researchers and is large enough for future research. example,” Johnson said.

Intensity of solar storms it is difficult to predict because scientists can’t accurately measure solar flares until the particles arrive within an hour of reaching Earth.

The team sorted hundreds of millions of images into six categories: arc, diffuse, discrete, cloudy, lunar, and clear/no aurora. Scientists can profit from comparing the auroras with atmospheric data at the time they occurred and linking the events to the solar event that eventually caused the light show.

A better understanding of the chemical mix of solar particles and Earth’s atmosphere will help scientists determine what types of auroras result from each scenario and the ability to rapidly interrogate hundreds of millions of images (compared to the speed at which this can be done when seen by humans). ) could be a boon for aurora research.