Journal cover Journal topic
Annales Geophysicae An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 1.621 IF 1.621
  • IF 5-year value: 1.614 IF 5-year
    1.614
  • CiteScore value: 1.61 CiteScore
    1.61
  • SNIP value: 0.900 SNIP 0.900
  • SJR value: 0.910 SJR 0.910
  • IPP value: 1.58 IPP 1.58
  • h5-index value: 24 h5-index 24
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 80 Scimago H
    index 80
Volume 12, issue 1
Ann. Geophys., 12, 19-24, 1994
https://doi.org/10.1007/s00585-994-0019-2
© European Geosciences Union 1994
Ann. Geophys., 12, 19-24, 1994
https://doi.org/10.1007/s00585-994-0019-2
© European Geosciences Union 1994

  31 Jan 1994

31 Jan 1994

Prediction of geomagnetic storms from solar wind data with the use of a neural network

H. Lundstedt and P. Wintoft H. Lundstedt and P. Wintoft

Abstract. An artificial feed-forward neural network with one hidden layer and error back-propagation learning is used to predict the geomagnetic activity index (Dst) one hour in advance. The Bz-component and ΣBz, the density, and the velocity of the solar wind are used as input to the network. The network is trained on data covering a total of 8700 h, extracted from the 25-year period from 1963 to 1987, taken from the NSSDC data base. The performance of the network is examined with test data, not included in the training set, which covers 386 h and includes four different storms. Whilst the network predicts the initial and main phase well, the recovery phase is not modelled correctly, implying that a single hidden layer error back-propagation network is not enough, if the measured Dst is not available instantaneously. The performance of the network is independent of whether the raw parameters are used, or the electric field and square root of the dynamical pressure.

Publications Copernicus
Download
XML
Citation