EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Flux Reconstruction With Machine Learning Techniques for the ESA JUICE Mission Radiation Monitor, RADEM

Rafael Parente, Marco Pinto, Inês Ochoa, António Gomes, Patrícia Gonçalves

Space Weather · 2026-11 · 24 (11)

DOI: 10.1029/2026sw005219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Space Weather, online erschienen am 07.11.2026. Verfasst von Rafael Parente und 4 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: European Space Agency.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Solar energetic particles (SEPs) are a significant space weather hazard to spacecraft. For Radiation Hardness Assurance (RHA) in future space missions, it is important to characterize the differential flux spectra of SEP events. In this paper, we present a machine learning model developed for reconstructing the differential flux spectrum from count rates measured by the Radiation Hard Electron Monitor (RADEM) onboard the Jupiter Icy Moons Explorer (JUICE), launched by the European Space Agency (ESA). The model is motivated by limitations of the bow‐tie technique when applied to RADEM count rates in the first coincidence configuration, particularly for SEP events with non‐negligible high‐energy proton flux. To validate the model, we applied it to proton count rate data measured by RADEM during a series of SEP events on 10–18 May 2024. Using our model, we estimated the proton differential flux, and used the response functions of RADEM to reconstruct the count rates measured by the instrument. For the considered detection bins, the reconstructed count rates generally agree with the measurements to within 10% during time intervals in which the measured count rates exceed twice the background mean. Additionally, we compared the proton differential flux reconstructed from count rate data measured by RADEM, with our model and the bow‐tie technique, as well as the differential flux measured by STEREO‐A in a time period when the proton flux was isotropic. The proton differential flux reconstructed with our model is in good agreement with STEREO‐A measurements, with relative errors below 35%.

Förderung

  • European Space Agency

Zitieren

APA

Parente, R., Pinto, M., Ochoa, I., Gomes, A., & Gonçalves, P. (2026). Flux Reconstruction With Machine Learning Techniques for the ESA JUICE Mission Radiation Monitor, RADEM. Space Weather, 24(11). https://doi.org/10.1029/2026sw005219

Vancouver

Parente R, Pinto M, Ochoa I, Gomes A, Gonçalves P. Flux Reconstruction With Machine Learning Techniques for the ESA JUICE Mission Radiation Monitor, RADEM. Space Weather. 2026;24(11). doi:10.1029/2026sw005219

BibTeX
@article{Parente2026,
  author = {Parente, Rafael and Pinto, Marco and Ochoa, Inês and Gomes, António and Gonçalves, Patrícia},
  title = {Flux Reconstruction With Machine Learning Techniques for the ESA JUICE Mission Radiation Monitor, RADEM},
  journal = {Space Weather},
  year = {2026},
  volume = {24},
  number = {11},
  doi = {10.1029/2026sw005219}
}
Kostenlos starten →