| A new method is presented to recover the lost data in geophysical time series. It is clear that gaps in data are a substantial problem in obtaining correct outcomes about phenomenon in time series processing. Moreover, using the data with irregular coarse steps results in the loss of prime information during analysis. We suggest an approach to solving these problems, that is based on the idea of modeling the data with the help of small-dimension manifolds, and it is implemented with the help of a neural network. We use this approach on real data and show its proper use for analyzing time series of cosmogenic isotopes. In addition, multifractal analysis was applied to the recovered 14C concentration in the Earth's atmosphere.
for LaTeX users @article{ANGorban2002-3,
author = {A. N. Gorban and A. Rossiev and N. Makarenk and Y. Kuandykov and V. Dergachev},
title = {Recovering data gaps through neural network methods},
journal = {J. Geomagn. Aeron.},
volume = {3},
pages = {191-197},
year = {2002}
}
\bibitem{ANGorban2002-3} A.N. Gorban, A. Rossiev, N. Makarenk, Y. Kuandykov, V. Dergachev,
Recovering data gaps through neural network methods,
J. Geomagn. Aeron. {\bf 3} (2002) 191-197.ANGorban2002-3
A.N. Gorban, A. Rossiev, N. Makarenk, Y. Kuandykov, V. Dergachev
Recovering data gaps through neural network methods
J. Geomagn. Aeron.,3,2002,191-197 |
mk@mat.ethz.ch
1 out of 810 entries requested
[H-factor to-date: > 0]
