Nonlinear Processes in Geophysics www.nonlin-processes-geophys.net 1023-5809 1607-7946 9 5/6 2002 10.5194/npg-9-425-2002 http://www.nonlin-processes-geophys.net/9/425/2002/ http://www.nonlin-processes-geophys.net/9/425/2002/npg-9-425-2002.html http://www.nonlin-processes-geophys.net/9/425/2002/npg-9-425-2002.pdf 425 433 0000-00-00 Neural network prediction of geomagnetic activity: a method using local Hölder exponents Z. Vörös D. Jankovičová Geomagnetic Observatory Hurbanovo, Geophysical Institute SAS, Slovak Republic Local scaling and singularity properties of solar wind and geomagnetic time series were analysed using Hölder exponents . It was shown that in analysed cases due to the multifractality of fluctuations, α changes from point to point. We argued there exists a peculiar interplay between regularity/irregularity and amplitude characteristics of fluctuations which could be exploited for the improvement of predictions of geomagnetic activity. To this end, a layered back-propagation artificial neural network model with feedback connection was used for the study of the solar wind magnetosphere coupling and prediction of the geomagnetic D_st index. The solar wind input was taken from the principal component analysis of the interplanetary magnetic field, proton density and bulk velocity. Superior network performance was achieved in cases when the information on local Hölder exponents was added to the input layer.