Forecasting of ionospheric critical frequency using neural networks

Altinay O., Tulunay E., Tulunay Y.

GEOPHYSICAL RESEARCH LETTERS, vol.24, no.12, pp.1467-1470, 1997 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 24 Issue: 12
  • Publication Date: 1997
  • Doi Number: 10.1029/97gl01381
  • Journal Name: GEOPHYSICAL RESEARCH LETTERS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1467-1470
  • Middle East Technical University Affiliated: Yes

Abstract

Multilayer perceptron type neural networks (NN) are employed for forecasting ionospheric critical frequency (foF2) one hour in advance. The nonlinear black-box modeling approach in system identification is used. The main contributions: 1. A flexible and easily accessible training database capable of handling extensive physical data is prepared, 2. Novel NN design and experimentation software is developed, 3. A training strategy is adopted in order to significantly enhance the generalization or extrapolation ability of NNs, 4. A method is developed for determining the relative significances (RS) of NN inputs in terms of mapping capability.