Storm-time atmospheric density modeling using neural networks and its application in orbit propagation

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Upper atmospheric densities during geomagnetic storms are usually poorly estimated due to a lack of clear understanding of coupling mechanisms between the thermosphere and magnetosphere. Consequently, the orbit determination and propagation for low-Earth-orbit objects during geomagnetic storms have large uncertainties. Artificial neural networks are often used to identify nonlinear systems in the absence of rigorous theory. In the present study, an attempt has been made to model the storm-time atmospheric density using neural networks. Considering the debate over the representative of geomagnetic storm effect, i.e. the geomagnetic indices ap and Dst, three neural network models (NNM) are developed with ap, Dst and a combination of ap and Dst respectively. The density data used for training the NNMs are derived from the measurements of the satellites CHAMP and GRACE. The NNMs are evaluated by looking at: (a) the mean residuals and the standard deviations with respect to the density data that are not used in training process, and (b) the accuracy of reconstructing the orbits of selected objects during storms employing each model. This empirical modeling technique and the comparisons with the models NRLMSIS-00 and Jacchia-Bowman 2008 reveal (1) the capability of neural networks to model the relationship between solar and geomagnetic activities, and density variations; and (2) the merits and demerits of ap and Dst when it comes to characterizing density variations during storms.

Original languageEnglish
Pages (from-to)558-567
Number of pages10
JournalAdvances in Space Research
Volume53
Issue number3
DOIs
Publication statusPublished - Feb 1 2014

Fingerprint

Atmospheric density
atmospheric density
Orbits
Neural networks
orbits
magnetic storms
propagation
geomagnetic storm
modeling
education
orbit determination
thermosphere
Magnetosphere
low Earth orbits
CHAMP
solar activity
nonlinear systems
GRACE
magnetospheres
standard deviation

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Astronomy and Astrophysics
  • Geophysics
  • Atmospheric Science
  • Space and Planetary Science
  • Earth and Planetary Sciences(all)

Cite this

Storm-time atmospheric density modeling using neural networks and its application in orbit propagation. / Chen, Hongru; Liu, Huixin; Hanada, Toshiya.

In: Advances in Space Research, Vol. 53, No. 3, 01.02.2014, p. 558-567.

Research output: Contribution to journalArticle

@article{e26a3e0632b143f4b095c761d865de81,
title = "Storm-time atmospheric density modeling using neural networks and its application in orbit propagation",
abstract = "Upper atmospheric densities during geomagnetic storms are usually poorly estimated due to a lack of clear understanding of coupling mechanisms between the thermosphere and magnetosphere. Consequently, the orbit determination and propagation for low-Earth-orbit objects during geomagnetic storms have large uncertainties. Artificial neural networks are often used to identify nonlinear systems in the absence of rigorous theory. In the present study, an attempt has been made to model the storm-time atmospheric density using neural networks. Considering the debate over the representative of geomagnetic storm effect, i.e. the geomagnetic indices ap and Dst, three neural network models (NNM) are developed with ap, Dst and a combination of ap and Dst respectively. The density data used for training the NNMs are derived from the measurements of the satellites CHAMP and GRACE. The NNMs are evaluated by looking at: (a) the mean residuals and the standard deviations with respect to the density data that are not used in training process, and (b) the accuracy of reconstructing the orbits of selected objects during storms employing each model. This empirical modeling technique and the comparisons with the models NRLMSIS-00 and Jacchia-Bowman 2008 reveal (1) the capability of neural networks to model the relationship between solar and geomagnetic activities, and density variations; and (2) the merits and demerits of ap and Dst when it comes to characterizing density variations during storms.",
author = "Hongru Chen and Huixin Liu and Toshiya Hanada",
year = "2014",
month = "2",
day = "1",
doi = "10.1016/j.asr.2013.11.052",
language = "English",
volume = "53",
pages = "558--567",
journal = "Advances in Space Research",
issn = "0273-1177",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Storm-time atmospheric density modeling using neural networks and its application in orbit propagation

AU - Chen, Hongru

AU - Liu, Huixin

AU - Hanada, Toshiya

PY - 2014/2/1

Y1 - 2014/2/1

N2 - Upper atmospheric densities during geomagnetic storms are usually poorly estimated due to a lack of clear understanding of coupling mechanisms between the thermosphere and magnetosphere. Consequently, the orbit determination and propagation for low-Earth-orbit objects during geomagnetic storms have large uncertainties. Artificial neural networks are often used to identify nonlinear systems in the absence of rigorous theory. In the present study, an attempt has been made to model the storm-time atmospheric density using neural networks. Considering the debate over the representative of geomagnetic storm effect, i.e. the geomagnetic indices ap and Dst, three neural network models (NNM) are developed with ap, Dst and a combination of ap and Dst respectively. The density data used for training the NNMs are derived from the measurements of the satellites CHAMP and GRACE. The NNMs are evaluated by looking at: (a) the mean residuals and the standard deviations with respect to the density data that are not used in training process, and (b) the accuracy of reconstructing the orbits of selected objects during storms employing each model. This empirical modeling technique and the comparisons with the models NRLMSIS-00 and Jacchia-Bowman 2008 reveal (1) the capability of neural networks to model the relationship between solar and geomagnetic activities, and density variations; and (2) the merits and demerits of ap and Dst when it comes to characterizing density variations during storms.

AB - Upper atmospheric densities during geomagnetic storms are usually poorly estimated due to a lack of clear understanding of coupling mechanisms between the thermosphere and magnetosphere. Consequently, the orbit determination and propagation for low-Earth-orbit objects during geomagnetic storms have large uncertainties. Artificial neural networks are often used to identify nonlinear systems in the absence of rigorous theory. In the present study, an attempt has been made to model the storm-time atmospheric density using neural networks. Considering the debate over the representative of geomagnetic storm effect, i.e. the geomagnetic indices ap and Dst, three neural network models (NNM) are developed with ap, Dst and a combination of ap and Dst respectively. The density data used for training the NNMs are derived from the measurements of the satellites CHAMP and GRACE. The NNMs are evaluated by looking at: (a) the mean residuals and the standard deviations with respect to the density data that are not used in training process, and (b) the accuracy of reconstructing the orbits of selected objects during storms employing each model. This empirical modeling technique and the comparisons with the models NRLMSIS-00 and Jacchia-Bowman 2008 reveal (1) the capability of neural networks to model the relationship between solar and geomagnetic activities, and density variations; and (2) the merits and demerits of ap and Dst when it comes to characterizing density variations during storms.

UR - http://www.scopus.com/inward/record.url?scp=84892795738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892795738&partnerID=8YFLogxK

U2 - 10.1016/j.asr.2013.11.052

DO - 10.1016/j.asr.2013.11.052

M3 - Article

AN - SCOPUS:84892795738

VL - 53

SP - 558

EP - 567

JO - Advances in Space Research

JF - Advances in Space Research

SN - 0273-1177

IS - 3

ER -