Massive Multi‐Mission Statistical Study and Analytical Modeling of the Earth's Magnetopause: 1. A Gradient Boosting Based Automatic Detection of Near‐Earth Regions. Issue 1 (19th January 2022)

• Record Type: Journal Article
• Authors: Nguyen, G.; Aunai, N.; Michotte de Welle, B.; Jeandet, A.; Lavraud, B.; Fontaine, D.
• Is Part Of: Journal of geophysical research. Volume 127:Issue 1(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-01-19
• Subjects: magnetosphere -- solar wind -- machine learning -- magnetopause -- bow shock; Magnetospheric physics -- Periodicals; Space environment -- Periodicals; Cosmic physics -- Periodicals; Planets -- Atmospheres -- Periodicals; Heliosphere (Astrophysics) -- Periodicals; Geophysics -- Periodicals; 523.01
• DOI: 10.1029/2021JA029773
• Languages: English
• ISSNs: 2169-9380

Abstract

Abstract: We present an automatic classification method of the three near‐Earth regions, the magnetosphere, the magnetosheath and the solar wind from their in situ data measurement by multiple spacecraft. Based on gradient boosting classifier, this very simple and very fast method outperforms the detection routines based on manually set thresholds. The method is used to identify 15, 062 magnetopause crossings and 17, 227 bow shock crossings in the data of 11 different spacecraft of the THEMIS, ARTEMIS, Cluster, MMS, and Double Star missions and for a total of 83 cumulated years. These multi‐mission catalogs are easily reproducible, can be automatically enlarged with additional data and their elaboration paves the way for future massive statistical analysis of near‐Earth boundaries. Key Points: A gradient boosting algorithm is used to classify the magnetosphere, magnetosheath and solar wind in situ data from multiple missions The method outperforms the detection methods based on manual threshold and is trained faster than existing machine‐learning based methods The method is used to identify 15, 062 magnetopause crossings and 17, 227 bow shock crossings