ByAshwini Sakharkar

21 Sep, 2024

New Jersey Institute of Technology (NJIT) researchers are leveraging artificial intelligence to gain unprecedented insights into the conditions in the Sun’s lower atmosphere, which drive some of the solar system‘s most powerful explosions, capable of disrupting critical infrastructure on Earth.

NJIT researchers have secured a $593,864 National Science Foundation grant to pioneer a new AI system for rapidly and accurately predicting the occurrence of explosive space weather events on the Sun, ranging from solar flares to coronal mass ejections (CMEs).

Over the course of three years, the project, spearheaded by Yan Xu at NJIT’s Institute for Space Weather Sciences (ISWS) and Jason Wang at the university’s Ying Wu College of Computing, aims to develop AI-powered space weather forecasting capabilities. These capabilities could provide solar researchers with a groundbreaking means to gain insights into the complex magnetic processes in regions of the Sun’s atmosphere that trigger such eruptions. These regions have been rarely observed until now.

Researchers have unveiled a groundbreaking AI-powered forecasting system, SolarDM, which has the potential to provide early-warning detection of eruptive events on Earth days in advance. This innovation offers crucial insights to the space weather science community, especially as activity on our nearest star intensifies during the current 11-year solar cycle that commenced in 2019.

“Major solar eruptions are powered by magnetic processes taking place in the solar corona, where we’ve lacked critical data due to poor observation conditions and insufficient instruments,” said Xu, the project’s principal investigator and research professor at NJIT’s Center for Solar-Terrestrial Research. “Observations of the atmospheric layer underneath are crucial to study 3D magnetic fields. SolarDM’s data insights potentially give us a way to map the magnetic landscape of this region, allowing us to better predict these powerful eruptions.”

Solar physicists have dedicated years to unraveling the mysteries of the Sun’s upper atmosphere, known as the corona. The dynamic interplay of magnetic fields in this region fuels explosive events that have the potential to disrupt vital technologies on Earth, from satellite operations to communication systems.

Yet, the challenges of observing the Sun’s second atmospheric layer, the chromosphere, have persisted. This elusive region, positioned above the photosphere, holds crucial clues about solar eruptions but remains rarely visible.

In a groundbreaking approach, the NJIT team is harnessing the power of advanced artificial intelligence to create synthetic vector magnetograms. These computer-generated representations of magnetic field dynamics in both the photosphere and chromosphere promise to unlock critical insights into the precursors of solar eruptions.

The SolarDM AI system will undergo rigorous training using simulations of the Sun’s magnetic field and observational data from the NSF’s Synoptic Optical Long-term Investigations of the Sun (SOLIS) – a pioneering solar telescope stationed at NJIT’s Big Bear Solar Observatory. Furthermore, data from NASA’s missions will enrich the training process, propelling solar research into a new era of understanding and prediction.

“Due to the differences between the instruments on board the ground-based and space-borne observatories, it is extremely challenging to obtain high-quality alignments of the data needed for training and testing the AI system,” explained Wang. “The forecast horizon of state-of-the-art solar eruption forecasting systems is 24 hours. If successful, with SolarDM’s generated vector magnetograms, it is expected that the new AI system can extend the forecast horizon from 24 hours to three days.”

Xu and Wang’s groundbreaking AI modeling system is set to revolutionize our understanding of solar eruptions. Not only will it predict when and where these immense events are likely to occur across vast distances of the solar atmosphere, but it will also provide clear explanations for its forecasts.

“Insights into why the AI model is making its forecasts could significantly enhance our understanding of the underlying physics that are behind these powerful events,” noted Xu.

The NJIT project, “AI-Driven Generation of Vector Magnetograms in the Chromosphere and Photosphere with Application to Explainable Solar Eruption Predictions,” is scheduled to run from September 15, 2024, to August 31, 2027. This initiative is part of the NSF’s Collaborations in Artificial Intelligence and Geosciences (CAIG) program, aiming to integrate AI approaches with geoscience research to improve natural hazard forecasting and inform decision-making in the face of climate change.