Write a comment
Researchers at the New Jersey Institute of Technology (NJIT) have received a $593,864 grant from the National Science Foundation (NSF) to develop an AI-powered system that enhances the forecasting of solar eruptions, such as solar flares and coronal mass ejections (CMEs). This three-year initiative, led by Yan Xu from NJIT's Institute for Space Weather Sciences (ISWS) and Jason Wang from the uni by Clarence Oxford
Los Angeles CA (SPX) Sep 22, 2024
Researchers at the New Jersey Institute of Technology (NJIT) have received a $593,864 grant from the National Science Foundation (NSF) to develop an AI-powered system that enhances the forecasting of solar eruptions, such as solar flares and coronal mass ejections (CMEs). This three-year initiative, led by Yan Xu from NJIT's Institute for Space Weather Sciences (ISWS) and Jason Wang from the university's Ying Wu College of Computing, aims to improve the speed and accuracy of space weather predictions.
The project will focus on developing an AI forecasting tool, SolarDM, which is designed to analyze the Sun's magnetic fields to anticipate explosive solar events. SolarDM could improve the ability to detect these events days in advance, offering critical insights as solar activity intensifies during the current 11-year solar cycle, which began 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."
Magnetic fields in the Sun's corona have long been studied by solar physicists, as disruptions in these fields are linked to events that can impact Earth's technology, including satellites. However, understanding magnetic field conditions in the chromosphere, a layer of the Sun's atmosphere located above the photosphere, has been challenging due to limited visibility and data.
To overcome this, the NJIT team will use artificial intelligence to generate synthetic vector magnetograms - detailed visualizations of magnetic field dynamics in both the chromosphere and photosphere. These magnetograms will offer new data to help forecast solar eruptions more accurately.
The AI system will be trained using data from NSF's Synoptic Optical Long-term Investigations of the Sun (SOLIS) and NASA's solar missions. SOLIS, one of the world's leading solar telescopes, is based at NJIT's Big Bear Solar Observatory.
"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."
The AI system will not only predict solar eruptions but will also provide explanations for its predictions, which could enhance scientific understanding of the underlying magnetic processes.
The project, titled "AI-Driven Generation of Vector Magnetograms in the Chromosphere and Photosphere with Application to Explainable Solar Eruption Predictions," will run from September 15, 2024, through August 31, 2027. It is part of NSF's Collaborations in Artificial Intelligence and Geosciences (CAIG) program, which aims to integrate AI with geoscience research to improve natural hazard forecasting and understanding of Earth's systems.
Related Links
NJIT Institute for Space Weather Sciences
Solar Science News at SpaceDaily