Computer Science – Performance
Scientific paper
Jul 2002
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2002angeo..20.1031c&link_type=abstract
Annales Geophysicae, vol. 20, Issue 7, pp.1031-1038
Computer Science
Performance
2
Scientific paper
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 reoptimization of neural network models on a regular basis to cope with changes in the statistical properties of geophysical data sets. Periodic retraining and reoptimization of the models resulted in a reduction of the model predictive error by ~ 0.1 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.
Cannon Paul S.
Chan H. Y. A.
No associations
LandOfFree
Nonlinear forecasts of foF2: variation of model predictive accuracy over time does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Nonlinear forecasts of foF2: variation of model predictive accuracy over time, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Nonlinear forecasts of foF2: variation of model predictive accuracy over time will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-960175