Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Space Weather Physics: Dynamic Neural Network Studies of Solar Wind-Magnetosphere Coupling

Wu, Jian-Guo LU (1997)
Abstract
This thesis presents studies of solar wind-magnetosphere coupling using dynamic neural networks in combination with statistically correlative analysis. The primary contribution of the thesis is dynamic neural network models that can be implemented for near real-time predictions of geomagnetic storms from the solar wind alone. With acceptable accuracy, the prediction time has been extended up to 5 hours. This is of great socioeconomic significance in space weather forecasting. The secondary contribution of the thesis is the modeling of the magnetospheric dynamics, which optimizes combinations of solar wind parameters and coupling functions. The third contribution of the thesis includes the development of a C-cod of Elman recurrent network... (More)
This thesis presents studies of solar wind-magnetosphere coupling using dynamic neural networks in combination with statistically correlative analysis. The primary contribution of the thesis is dynamic neural network models that can be implemented for near real-time predictions of geomagnetic storms from the solar wind alone. With acceptable accuracy, the prediction time has been extended up to 5 hours. This is of great socioeconomic significance in space weather forecasting. The secondary contribution of the thesis is the modeling of the magnetospheric dynamics, which optimizes combinations of solar wind parameters and coupling functions. The third contribution of the thesis includes the development of a C-cod of Elman recurrent network models, the development of an algorithm for pruning Elman networks and the algorithms for post network error analyses. The fourth contribution of the thesis is the exploitation of the hybrid of a time-delay network and a recurrent network by examining the role of a time-delay line in recurrent networks.



This thesis consists of five chapters. Chapter 1 provides an introduction to solar-terrestrial physics. Chapter 2 is a general description of neural networks. Chapter 3 describes solar wind-magnetosphere coupling and related studies. Chapter 4 is devoted to studies of a time-dependent system, such as the solar wind-driven magnetosphere, using neural networks. Chapter 5 is a summary of the papers included in this thesis.



Paper I pioneered exploitation of recurrent neural networks in prediction of geomagnetic activity and presents very accurate one hour ahead prediction of magnetic storms using only solar wind data.



Paper II is a study of solar wind-magnetosphere coupling using a partially recurrent neural network to find the optimal coupling functions. The optimal coupling functions found are used to predict magnetic storms up to 5 hours with acceptable accuracy. This study was the first to present real-time one hour ahead prediction of magnetic storms using the satellite WIND real-time data.



Paper III made predictions of magnetic storms up to 8 hours. It presents the appropriate combinations of solar wind parameters for predicting magnetic storms, which reveals the relative importance of solar wind parameters. It is found that a magnetic storm is formed in the magnetosphere on a timescale of about 1 hour. In this study, we exploit a time-delay recurrent network which is a hybrid of a time-delay network and an Elman recurrent network, and prove it very helpful in improving predictions.



Paper IV studies solar wind-magnetosphere interaction in detail, which finds the best coupling functions for accurate prediction of geomagnetic activity based on neural network modeling, in comparison with the results from cross-correlation analyses. The algorithms for computation of confidence limits on the prediction accuracy are developed in this study. (Less)
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • Dr Vassiliadis, Dimitris, GSFC/NASA, USA
organization
publishing date
type
Thesis
publication status
published
subject
keywords
Geophysics, kosmisk kemi, rymdvetenskap, Astronomi, cosmic chemistry, solar wind, space weather, magnetosphere, solar wind-magnetosphere coupling, geomagnetic activity, geomagnetic storms, predictions, modeling, neural networks, space research, Astronomy, physical oceanography, meteorology, Geofysik, fysisk oceanografi, meteorologi, Fysicumarkivet A:1997:Wu
pages
120 pages
publisher
Lund Observatory, Lund University
defense location
Physics Institute, sal B, Sölvegatan 14
defense date
1997-05-22 14:00:00
external identifiers
  • other:ISRN: LUNFD6/(NFAS-1016)/1-120/(1997)
language
English
LU publication?
yes
id
cfdef2b3-1c38-40e0-9b95-d30ef55ac23d (old id 29206)
date added to LUP
2016-04-04 12:06:35
date last changed
2018-11-21 21:09:03
@phdthesis{cfdef2b3-1c38-40e0-9b95-d30ef55ac23d,
  abstract     = {{This thesis presents studies of solar wind-magnetosphere coupling using dynamic neural networks in combination with statistically correlative analysis. The primary contribution of the thesis is dynamic neural network models that can be implemented for near real-time predictions of geomagnetic storms from the solar wind alone. With acceptable accuracy, the prediction time has been extended up to 5 hours. This is of great socioeconomic significance in space weather forecasting. The secondary contribution of the thesis is the modeling of the magnetospheric dynamics, which optimizes combinations of solar wind parameters and coupling functions. The third contribution of the thesis includes the development of a C-cod of Elman recurrent network models, the development of an algorithm for pruning Elman networks and the algorithms for post network error analyses. The fourth contribution of the thesis is the exploitation of the hybrid of a time-delay network and a recurrent network by examining the role of a time-delay line in recurrent networks.<br/><br>
<br/><br>
This thesis consists of five chapters. Chapter 1 provides an introduction to solar-terrestrial physics. Chapter 2 is a general description of neural networks. Chapter 3 describes solar wind-magnetosphere coupling and related studies. Chapter 4 is devoted to studies of a time-dependent system, such as the solar wind-driven magnetosphere, using neural networks. Chapter 5 is a summary of the papers included in this thesis.<br/><br>
<br/><br>
Paper I pioneered exploitation of recurrent neural networks in prediction of geomagnetic activity and presents very accurate one hour ahead prediction of magnetic storms using only solar wind data.<br/><br>
<br/><br>
Paper II is a study of solar wind-magnetosphere coupling using a partially recurrent neural network to find the optimal coupling functions. The optimal coupling functions found are used to predict magnetic storms up to 5 hours with acceptable accuracy. This study was the first to present real-time one hour ahead prediction of magnetic storms using the satellite WIND real-time data.<br/><br>
<br/><br>
Paper III made predictions of magnetic storms up to 8 hours. It presents the appropriate combinations of solar wind parameters for predicting magnetic storms, which reveals the relative importance of solar wind parameters. It is found that a magnetic storm is formed in the magnetosphere on a timescale of about 1 hour. In this study, we exploit a time-delay recurrent network which is a hybrid of a time-delay network and an Elman recurrent network, and prove it very helpful in improving predictions.<br/><br>
<br/><br>
Paper IV studies solar wind-magnetosphere interaction in detail, which finds the best coupling functions for accurate prediction of geomagnetic activity based on neural network modeling, in comparison with the results from cross-correlation analyses. The algorithms for computation of confidence limits on the prediction accuracy are developed in this study.}},
  author       = {{Wu, Jian-Guo}},
  keywords     = {{Geophysics; kosmisk kemi; rymdvetenskap; Astronomi; cosmic chemistry; solar wind; space weather; magnetosphere; solar wind-magnetosphere coupling; geomagnetic activity; geomagnetic storms; predictions; modeling; neural networks; space research; Astronomy; physical oceanography; meteorology; Geofysik; fysisk oceanografi; meteorologi; Fysicumarkivet A:1997:Wu}},
  language     = {{eng}},
  publisher    = {{Lund Observatory, Lund University}},
  school       = {{Lund University}},
  title        = {{Space Weather Physics: Dynamic Neural Network Studies of Solar Wind-Magnetosphere Coupling}},
  year         = {{1997}},
}