In the realm of solar research, a team of scientists from the New Jersey Institute of Technology (NJIT) and other institutions has developed a novel dataset aimed at improving the prediction of solar active regions (ARs). These regions are crucial to understand as they can lead to solar eruptions that impact space technologies and exploration. The team, led by Spiridon Kasapis, Eren Dogan, and Irina N. Kitiashvili, has created the Solar Active Region Emergence Dataset (SolARED) to enhance our ability to forecast these solar events.
The SolARED dataset is derived from full-disk maps of the Doppler velocity, magnetic field, and continuum intensity obtained by the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO). This dataset includes time series data that characterize the evolution of acoustic power of solar oscillations, unsigned magnetic flux, and continuum intensity for 50 large ARs before, during, and after their emergence on the solar surface. Additionally, it includes data from surrounding areas observed on the solar disc between 2010 and 2023. The dataset is designed to support machine learning (ML) models, enabling the development of operational forecasts for the emergence of active regions.
The practical applications of this research for the energy sector, particularly the space-based solar power industry, are significant. Accurate predictions of solar eruptive activity can help in mitigating potential impacts on space technologies, including satellites and solar power satellites. By detecting ARs before they form, it becomes possible to develop early-warning systems for upcoming space weather disturbances. This can lead to better planning and protection of space-based assets, ensuring the reliability and efficiency of space-based solar power systems.
The SolARED dataset is available at https://sun.njit.edu/sarportal/, through an interactive visualization web application. This research was published in a peer-reviewed journal, ensuring its credibility and relevance to the scientific community. The dataset and the associated ML models have the potential to revolutionize the way we predict and manage solar eruptive activity, benefiting the energy sector and space exploration endeavors.
This article is based on research available at arXiv.