Time-dependent prediction degradation assessment of neural-networks-based TEC forecasting models

Xenos, T. D.; Kouris, S. S.; Casimiro, A

http://hdl.handle.net/10400.1/11821

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
npg-10-585-2003.pdf		96.38 KB	Adobe PDF	Download

Send Feedback

Authors

Xenos, T. D.

Kouris, S. S.

Casimiro, A

Abstract(s)

An estimation of the difference in TEC prediction accuracy achieved when the prediction varies from 1 h to 7 days in advance is described using classical neural networks. Hourly-daily Faraday-rotation derived TEC measurements from Florence are used. It is shown that the prediction accuracy for the examined dataset, though degrading when time span increases, is always high. In fact, when a relative prediction error margin of +/-10% is considered, the population percentage included therein is almost always well above the 55%. It is found that the results are highly dependent on season and the dataset wealth, whereas they highly depend on the f(0)F2 - TEC variability difference and on hysteresis-like effect between these two ionospheric characteristics.