A team of researchers has used artificial intelligence to sort through nearly a billion photos of the aurora borealis—the Northern Lights—that could help researchers understand and predict the amazing natural phenomenon below.
The team developed a novel algorithm to classify more than 706 million images of the aurora borealis in THEMIS all-sky images taken between 2008 and 2022. The algorithm organized the images into six categories based on their properties, demonstrating the software's utility for classifying large-scale atmospheric datasets.
“This massive dataset is an important resource that will 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, a researcher at the University of New Hampshire and the lead author of the study, at a university release. “But until now, its sheer size has limited how effectively we can use that data.”
The team's research—published last month in Journal of Geophysical Research: Machine Learning and Computation—describes an algorithm trained to automatically label hundreds of millions of aurora images, potentially helping scientists detect the ethereal phenomenon with speed at scale.
There has been many of auroras this yearin part 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 explosions 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 Earth's atmosphere, they cause an ethereal glow in the sky: auroras. Particles can also mess with the electronics and power grids on Earth and in space, but we're only talking about the beautiful natural phenomena of today, not the merciless chaos that space weather can rain down on humanity.
“The labeled database may reveal further 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 it contains can be used more effectively by researchers and provide a large enough sample for future studies,” Johnson said.
The intensity of solar storms is hard to predict because scientists can't measure the solar outburst they came from with precision until the particles are within an hour of arriving at Earth.
The team sorted hundreds of millions of images into six categories: arc, diffuse, discrete, cloudy, moon, and clear/no aurora. Scientists can achieve this by comparing auroras with atmospheric data from the time the aurora occurred and linking the phenomena to the solar event that ultimately caused the light show.
A better understanding of the chemical mix of solar particles and that in Earth's atmosphere will help scientists determine which types of auroras will emerge from each scenario, and the ability to query hundreds of millions images in a hurry (compared to the speed of that work when done by humans. ) can be a boon to aurora research.
