The paper presents an investigation into the use of artificial neural networks to predict the values of the IF2 and IG ionospheric indices. Since 1982, the World Data Centre C1 for Solar-Terrestrial Physics has produced predictions for these indices using an adaptation of the McNish-Lincoln technique for predicting sunspot numbers. It is demonstrated that significantly more accurate predictions are obtained using artificial neural networks, which form the basis of predictions which will in future be issued by the World Data Centre.
References
-
-
1)
-
H.C. Koons ,
D.J. Gorney
.
A sunspot maximum prediction using a neural network.
EOS
,
18 ,
677 -
678
-
2)
-
P. Grassberger ,
I. Procaccia
.
Characterization of strange attractors.
Phys. Rev. Lett.
,
5 ,
346 -
349
-
3)
-
D. Rumelhart ,
G. Hinton ,
R. Williams
.
Learning representations by backpropagating errors.
Nature
,
533 -
536
-
4)
-
M. Lockwood
.
Simple M-factor algorithm for improved estimation of the basicmaximum usable frequency of radio waves reflected from the ionospheric F-region.
IEE Proc. F
,
4 ,
296 -
302
-
5)
-
R. Fletcher ,
M.J.D. Powell
.
A rapidly convergent descent method for minimization.
Comput. J.
,
163 -
168
-
6)
-
J.V. Hernandez ,
T. Tajima ,
W. Horton
.
Neural net forecasting for geomagnetic activity.
Geophys. Res. Lett.
,
23 ,
2707 -
2710
-
7)
-
H. Lundstedt ,
P. Wintoft
.
Prediction of geomagnetic storms from solar wind data with the use ofa neural network.
Ann. Geophys.
,
19 -
24
-
8)
-
K. Macpherson
.
Neural network computation techniques applied to solar activity prediction.
Adv. Space Res.
,
9 ,
447 -
450
-
9)
-
F. Fessant ,
S. Bengio ,
D. Collobert
.
On the prediction of solar activity using different neural network models.
Ann. Geophys.
,
20 -
26
-
10)
-
A.G. McNish ,
J.V. Lincoln
.
Prediction of sunspot numbers.
Trans. Am. Geophys. Union
,
5 ,
673 -
685
-
11)
-
Hecht-Nielsen, R.: `Kolmogorov's mapping neural network existence theorem', Proceedings of the IEEE first international conference on Neuralnetworks, 1987, 2, San Diego, p. 445–462.
-
12)
-
H.D.I. Abarbanel ,
R. Brown ,
J.J. Sidorich ,
L.S. Tsimring
.
The analysis of observed chaotic data in physical systems.
Rev. Mod. Phys.
,
4 ,
1331 -
1392
-
13)
-
C. de Groot ,
D. Würtz
.
Plain backpropagation and advanced optimization algorithms: a comparativestudy.
Neurocomput.
,
153 -
161
-
14)
-
R.Y. Liu ,
P.A. Smith ,
J.W. King
.
A new solar index which leads to improved foF2 predictions using theCCIR atlas.
Telecommun. J.
,
8 ,
408 -
414
-
15)
-
R.A. Calvo ,
H.A. Ceccatto ,
R.D. Piacentini
.
Neural network prediction of solar activity.
Astrophys. J.
,
916 -
921
-
16)
-
C.M. Minnis
.
A new index of solar activity based on ionospheric measurements.
J. Atmos. Terr. Phys.
,
310 -
321
-
17)
-
C.M. Minnis ,
G.H. Bazzard
.
A monthly ionospheric index of solar activity based on F2-layer ionizationat eleven stations.
J. Atmos. Terr. Phys.
,
297 -
305
-
18)
-
H. Lundstedt
.
Neural networks and predictions of solar-terrestrial effects.
Planet. Space Sci.
,
4 ,
457 -
464
-
19)
-
Brown, J.C., McInnes, C.R., Macpherson, K.P., Conway, A.J.: `Neural network approach to solar activity prediction: ESOC Contract 9810/92/D/IMFinal report', CRP 3883, Technical report, 1994.
-
20)
-
Wild, M.N. Private communication. World Data Centre Cl forSolar-TerrestrialPhysics, 1994.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-map_19960575
Related content
content/journals/10.1049/ip-map_19960575
pub_keyword,iet_inspecKeyword,pub_concept
6
6