Researchers from the University of Hawaii Institute of Astronomy (SiA) are helping to reshape the way scientists study the Sun. THE UH-the led team developed a new artificial intelligence (AI) tool capable of mapping the Sun’s magnetic field in three dimensions with unprecedented precision, supporting research linked to the United States National Science Foundation (NSF) Daniel K. Inouye Solar Telescope built and managed by the NSF National Solar Observatory (NSO) on Haleakalā. The team’s findings were published in the Astrophysics Journal.
“The Sun is the most powerful space weather source that can affect daily life here on Earth, especially now that we rely so much on technology,” said Kai Yang, a researcher. SiA postdoctoral researcher who led the work. “The Sun’s magnetic field causes explosive events such as solar flares and coronal mass ejections. This new technique helps us understand what triggers these events and strengthens space weather forecasts, giving us earlier warnings to protect the systems we use every day.”
The Sun’s magnetic field controls flares that can disrupt satellites, power systems, and communications on Earth. However, the field is difficult to measure, making it difficult to create accurate maps. Instruments can show how the field tilts, but not whether it points toward us or away from us, like looking at a string from the side and not knowing which end is closer. Another problem is height. When scientists observe the Sun, they see several layers at the same time, so it is difficult to determine the actual height of each magnetic structure. Sunspots make this even trickier because their powerful magnetic fields bend the surface downward, creating a dip.
AI-optimized information
SiA researchers teamed up with the National Solar Observatory and the High Altitude Observatory of NSF National Center for Atmospheric Research to build a new machine learning system that combines real data with the fundamental laws of physics. Their algorithm, the Haleakalā Disambiguation Decoder, is based on a simple rule: magnetic fields form loops and neither begin nor end. From there, the AI can determine the true direction of the field and estimate the correct height of each layer.
The method worked well on detailed computer models of the Sun, including quiet zones, bright active regions and sunspots. Its precision is particularly useful for making sense of the high-resolution images from the Daniel K. Inouye Solar Telescope.
“With this new machine learning tool, the Daniel K. Inouye Solar Telescope can help scientists create a more accurate 3D map of the Sun’s magnetic field,” Yang said. “It also reveals related features, like vector electric currents in the solar atmosphere, that were previously very difficult to measure. Together, this gives us a clearer picture of what causes powerful solar flares.”
Clearer information about the sun
With these advances, researchers can see the Sun’s magnetic landscape more accurately and improve predictions of solar activity that impacts life on Earth.