ML‐EPM: A Machine Learning Model of Auroral Electron Precipitation Spectra Using Long‐Term DMSP Observations
Open Access
- 17 August 2026
- journal article
- research article
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 24 (8)
Abstract
Auroral precipitation plays a key role in coupling the Magnetosphere–Ionosphere–Thermosphere system by modifying ionospheric conductance, currents, atmospheric heating, and upper‐atmospheric dynamics. Leveraging 17 years of electron spectrum data from the Defense Meteorological Satellite Program (DMSP), we developed a Machine Learning‐based Electron Precipitation Model (ML‐EPM) that nowcasts differential energy fluxes of precipitating electrons in 19 energy channels ranging from 30 eV to 30 keV, using 6‐hr histories of solar wind (SW), interplanetary magnetic field (IMF) and geomagnetic indices as inputs. The model performance was evaluated using a 2‐year DMSP data set (2013–2014) and a geomagnetic storm event on 27–28 February 2014, both of which were not included in training. ML‐EPM achieved moderate‐to‐strong correlation coefficients (0.5–0.72) for 16 out of 19 channels while maintaining root‐mean‐square and mean‐absolute errors within the same order of magnitude. Although the model underestimated total energy flux compared to OVATION and DMSP observations, it reproduces key auroral features, including (a) auroral oval broadening, equatorward shifting of auroral boundaries, and enhanced precipitation during disturbed periods, (b) low‐energy precipitation (<1 keV) such as soft electrons in the cusp, polar rain in the polar cap, and secondary electrons generated by primary auroral electrons, and (c) various auroral spectral shapes, including diffuse, monoenergetic, and broadband auroras. Rather than relying on total energy flux and mean energy to estimate an idealized Maxwellian shape, ML‐EPM directly nowcasts electron fluxes across 19 distinct energy channels, allowing global circulation models to more accurately resolve altitude‐dependent ionization rates and predict ionosphere‐thermosphere dynamics.Keywords
This publication has 81 references indexed in Scilit:
- Statistical Patterns of Ionospheric Convection Derived From Mid‐latitude, High‐Latitude, and Polar SuperDARN HF Radar ObservationsJournal of Geophysical Research: Space Physics, 2018
- Ushering in a New Frontier in Geospace Through Data ScienceJournal of Geophysical Research: Space Physics, 2017
- New DMSP database of precipitating auroral electrons and ionsJournal of Geophysical Research: Space Physics, 2017
- High‐latitude ionospheric conductivity variability in three dimensionsGeophysical Research Letters, 2016
- Modes of high‐latitude auroral conductance variability derived from DMSP energetic electron precipitation observations: Empirical orthogonal function analysisJournal of Geophysical Research: Space Physics, 2015
- Auroral Precipitation Models and Space Weather2015
- Maps of precipitating electron spectra characterized by Maxwellian and kappa distributionsJournal of Geophysical Research: Space Physics, 2014
- Observations in the E region ionosphere of kappa distribution functions associated with precipitating auroral electrons and discrete auroraeJournal of Geophysical Research: Space Physics, 2014
- Altitude‐adjusted corrected geomagnetic coordinates: Definition and functional approximationsJournal of Geophysical Research: Space Physics, 2014
- OVATION Prime‐2013: Extension of auroral precipitation model to higher disturbance levelsSpace Weather, 2014