Although the source active regions of some coronal mass ejections (CMEs) were identified in CME catalogues, vast majority of CMEs do not have an identified source active region. We propose a method that uses a filtration process and machine learning to identify the sunspot groups associated with a large fraction of CMEs and compare the physical parameters of these identified sunspot groups with properties of their corresponding CMEs to find mechanisms behind the initiation of CMEs. These CMEs were taken from the Coordinated Data Analysis Workshops (CDAW) database hosted at NASA's website. The Helio-seismic and Magnetic Imager (HMI) Active Region Patches (HARPs) were taken from the Stanford University's JSOC database. The source active regions of the CMEs were identified by the help of a custom filtration procedure and then by training a Long Short-Term Memory Network (LSTM) to identify the patterns in the physical magnetic parameters derived from vector and line of sight magnetograms. The neural network simultaneously considers the time series data of these magnetic parameters at once and learns the patterns at the onset of CMEs. This neural network was then used to identify the source HARPs for the CMEs recorded from 2011 till 2020. The neural network was able to reliably identify source HARPs for 4895 CMEs out of 14604 listed in the CDAW database during the afore-mentioned period.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.