Initial release of the CME recommendation algorithm code and dataset

The CME data used in this work were from the SOHO LASCO CME catalog, covering all CME events observed by the SOHO satellite from February 1996 to May 2024 (viewable at cdaw.gsfc.nasa.gov/CME_list/UNIVERSAL/text_ver). This CME catalog is generated and maintained at the CDAW Data Center by National Aeronautics and Space Administration (NASA) and The Catholic University of America in cooperation with the Naval Research Laboratory.

SOHO is an international collaborative project jointly conducted by the European Space Agency (ESA) and NASA. Samples were labeled based on whether CMEs reach Earth: events that actually reach Earth were defined as positive samples, and those that do not were defined as negative samples. Among them, Earth-arriving events were identified by the Richardson and Cane list (a Near-Earth Interplanetary Coronal Mass Ejections database), the CME Scoreboard, and final manual verification by our team.