Abstract:
Singular spectrum isolates significant principal components in a time series from the embedded noise. This tool-kit is used to reconstruct trend-free individual time series, formed by restricting the mean monthly hourly values of geomagnetic field to one hour at a time at a low latitude station Alibag (dipole latitude 9.5°N). Each reconstructed component is extrapolated over the next 12 values using an autoregressive model based on Burg’s maximum entropy algorithm. Details of a numerical approach to increase the reliability of extrapolation are highlighted. The extrapolated reconstructed components are then combined to generate predicted monthly values for each hour. The mean diurnal variation for any month obtained from the extrapolated individual hourly time series compares favorably with the observations. This approach to Sq(H) modelling incorporating both long and short term variations will be beneficial in the derivation of Dst index.
