Articles | Volume 39, issue 5
Ann. Geophys., 39, 861–881, 2021
Ann. Geophys., 39, 861–881, 2021
Regular paper
08 Oct 2021
Regular paper | 08 Oct 2021

Unsupervised classification of simulated magnetospheric regions

Maria Elena Innocenti et al.

Related authors

FLIP-MHD-based model sensitivity analysis
C. Skandrani, M. E. Innocenti, L. Bettarini, F. Crespon, J. Lamouroux, and G. Lapenta
Nonlin. Processes Geophys., 21, 539–553,,, 2014

Related subject area

Subject: Magnetosphere & space plasma physics | Keywords: Magnetospheric configuration and dynamics
The fate of O+ ions observed in the plasma mantle: particle tracing modelling and cluster observations
Audrey Schillings, Herbert Gunell, Hans Nilsson, Alexandre De Spiegeleer, Yusuke Ebihara, Lars G. Westerberg, Masatoshi Yamauchi, and Rikard Slapak
Ann. Geophys., 38, 645–656,,, 2020
Short summary
The increase in the curvature radius of geomagnetic field lines preceding a classical dipolarization
Osuke Saka
Ann. Geophys., 38, 467–479,,, 2020
Short summary
A multi-fluid model of the magnetopause
Roberto Manuzzo, Francesco Califano, Gerard Belmont, and Laurence Rezeau
Ann. Geophys., 38, 275–286,,, 2020
Short summary
Magnetodisc modelling in Jupiter's magnetosphere using Juno magnetic field data and the paraboloid magnetic field model
Ivan A. Pensionerov, Elena S. Belenkaya, Stanley W. H. Cowley, Igor I. Alexeev, Vladimir V. Kalegaev, and David A. Parunakian
Ann. Geophys., 37, 101–109,,, 2019
Short summary

Cited articles

Amaya, J., Dupuis, R., Innocenti, M. E., and Lapenta, G.: Visualizing and Interpreting Unsupervised Solar Wind Classifications, Front. Astron. Space Sci., 7, 66,, 2020. a, b, c, d, e, f
Anderson, B. J., Korth, H., Welling, D. T., Merkin, V. G., Wiltberger, M. J., Raeder, J., Barnes, R. J., Waters, C. L., Pulkkinen, A. A., and Rastaetter, L.: Comparison of predictive estimates of high-latitude electrodynamics with observations of global-scale Birkeland currents, Space Weather, 15, 352–373,, 2017. a
Angelopoulos, V.: The THEMIS mission, in: The THEMIS mission, 5–34, Springer, New York, NY, 2009. a
Argall, M. R., Small, C. R., Piatt, S., Breen, L., Petrik, M., Kokkonen, K., Barnum, J., Larsen, K., Wilder, F. D., Oka, M., Paterson, W. R., Torbert, R. B., Ergun, R. E., Phan, T., Giles, B. L., and Burch, J. L.: MMS SITL Ground Loop: Automating the Burst Data Selection Process, Front. Astron. Space Sci., 7, 54,, 2020. a, b, c
Armstrong, J. A. and Fletcher, L.: Fast solar image classification using deep learning and its importance for automation in solar physics, Solar Phys., 294, 80,, 2019. a
Short summary
Spacecraft missions do not always record observations at the highest possible resolution, and the so-called burst mode is switched on only occasionally. It is of paramount importance that processes of interest are sampled in burst mode. At the moment, many missions rely on a scientist in the loop, who decides when to trigger burst mode by looking at the preview data. Our work constitutes a first step towards making this decision automatic to improve mission operations and decrease human bias.