A group of researchers used artificial intelligence to collate nearly one billion images of the aurora borealis, or northern lights. This can help researchers understand and predict incredible natural phenomena.
The team developed a new algorithm to sort more than 706 million aurora borealis images in THEMIS all-sky images taken between 2008 and 2022. The algorithm sorted the images into 6 categories according to specific characteristics which shows the benefits of Software for classifying large atmospheric datasets
“The large dataset is a valuable resource that can help researchers understand how the solar wind interacts with Earth's magnetic field. It's an air bubble that protects us from charged particles flowing from the sun,” said Jeremiah Johnson, a researcher at the University of New Hampshire and lead author of the university study. release– “But until now Its sheer size limits how efficiently we can use that information.”
Team 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. This may help scientists quickly explore this ethereal phenomenon.
already exists lots or Aurora this yearThis is partly 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 the eruption of solar material. (Coronal mass ejection or CME) and solar flares
These events send charged particles out into space. And when those particles interact with particles in the Earth's atmosphere It will create an ethereal aurora in the sky. Particles are fine. Interfering with electronic devices and electrical grid On Earth and in space But we're just talking about a beautiful natural phenomenon right now. It's not the merciless chaos that space weather can rain down on humanity.
“The labeled database could reveal further insights into the dynamics of the aurora borealis. But at a basic level We aim to organize THEMIS' entire sky image database so that the vast amount of historical data it contains can be used more effectively by researchers and to provide a sufficiently large sample size for future studies. Johnson said.
The intensity of the solar storm is hard to guess This is because scientists cannot accurately measure the solar explosions that occur. Until the particle is within an hour of reaching Earth.
The team sorted hundreds of millions of images into six categories: arc, diffuse, discontinuous, cloudy, lunar, and clear/no aurora. Scientists might benefit from comparing the aurora borealis with atmospheric data from the time the auroras occurred. and linking the phenomenon to the solar event that ultimately caused the light show.
Understanding the chemical mix of solar particles and particles in Earth's atmosphere will help scientists determine what types of auroras occur in different situations. and the ability to interrogate hundreds of millions of images at a rapid pace. (compared to the rate of that work done by humans) could be useful for aurora research.