Science Through Machine Learning: Quantification of Post‐Storm Thermospheric Cooling
Open Access
- 26 September 2022
- journal article
- research article
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 20 (9)
Abstract
Machine learning (ML) models are universal function approximators and—if used correctly—can summarize the information content of observational data sets in a functional form for scientific and engineering applications. A benefit to ML over parametric models is that there are no a priori assumptions about particular basis functions which can potentially limit the phenomena that can be modeled. In this work, we develop ML models on three data sets: the Space Environment Technologies High Accuracy Satellite Drag Model (HASDM) density database, a spatiotemporally matched data set of outputs from the Jacchia‐Bowman 2008 Empirical Thermospheric Density Model (JB2008), and an accelerometer‐derived density data set from CHAllenging Minisatellite Payload (CHAMP). These ML models are compared to the Naval Research Laboratory Mass Spectrometer and Incoherent Scatter radar (NRLMSIS 2.0) model to study the presence of post‐storm cooling in the middle‐thermosphere. We find that both NRLMSIS 2.0 and JB2008‐ML do not account for post‐storm cooling and consequently perform poorly in periods following strong geomagnetic storms (e.g., the 2003 Halloween storms). Conversely, HASDM‐ML and CHAMP‐ML do show evidence of post‐storm cooling indicating that this phenomenon is present in the original data sets. Results show that density reductions up to 40% can occur 1–3 days post‐storm depending on the location and strength of the storm.Keywords
All Related Versions
Funding Information
- National Science Foundation (2140204, 2149747)
- National Aeronautics and Space Administration (80NSSC20K1362, 80HQTR20T0081)
This publication has 34 references indexed in Scilit:
- Overcooling in the upper thermosphere during the recovery phase of the 2003 October stormsJournal of Geophysical Research, 2012
- The development of new solar indices for use in thermospheric density modelingJournal of Atmospheric and Solar-Terrestrial Physics, 2008
- Improved ionospheric electrodynamic models and application to calculating Joule heating ratesJournal of Geophysical Research, 2005
- High accuracy satellite drag model (HASDM)Advances In Space Research, 2005
- The natural thermostat of nitric oxide emission at 5.3 μm in the thermosphere observed during the solar storms of April 2002Geophysical Research Letters, 2003
- Total Densities Derived from Accelerometer DataJournal of Spacecraft and Rockets, 2003
- CHAMP mission statusAdvances In Space Research, 2002
- Storm-time magnetospheric currents inferred from mid-latitude geomagnetic field variations.Journal of geomagnetism and geoelectricity, 1990
- MSIS‐86 Thermospheric ModelJournal of Geophysical Research, 1987
- Nitric oxide cooling in the terrestrial thermosphereGeophysical Research Letters, 1980