Automatic detection of the Earth Bow Shock and Magnetopause from in-situ data with machine learning

Abstract. We provide an automatic classification method of the three near-Earth regions, the magnetosphere, the magnetosheath and the solar wind in the streaming in-situ data measurement that outperforms the previous methods of automatic region classification. The method was used to identify 14186 magnetopause crossings and 16192 bow shock crossings in the data of 10 different spacecrafts of the THEMIS, ARTEMIS, Cluster and Double Star missions and for a total of 79 cumulated years. These multi-missions catalogs are non ambiguous and can be automatically enlarged with the increasing quantity of data and their elaboration paves the way for additional massive statistical analysis of the two near-Earth boundaries. The development of these algorithms is a promising step towards their usage for the onboard selection of data of interest.