Nonlinear forecasts of foF2: variation of model predictive accuracy over time

A H Y Chan, P S Cannon

Research output: Contribution to journalArticlepeer-review

9 Citations (SciVal)


A nonlinear technique employing radial basis function neural networks (RBF-NNs) has been applied to the short-term forecasting of the ionospheric F2-layer critical frequency, foF2. The accuracy of the model forecasts at a northern mid-latitude location over long periods is assessed, and is found to degrade with time. The results highlight the need for the retraining and re-optimization of neural network models on a regular basis to cope with changes in the statistical properties of geophysical data sets. Periodic retraining and re-optimization of the models resulted in a reduction of the model predictive error by similar to0.1 MHz per six months. A detailed examination of error metrics is also presented to illustrate the difficulties encountered in evaluating the performance of various prediction/forecasting techniques.
Original languageEnglish
Pages (from-to)1031-1038
Number of pages8
JournalAnnales Geophysicae
Issue number7
Publication statusPublished - 2002


Dive into the research topics of 'Nonlinear forecasts of foF2: variation of model predictive accuracy over time'. Together they form a unique fingerprint.

Cite this