On the predictability of f0F2 using neural networks

Poole, A. W. V.; McKinnell, Lee-Anne

doi:10.1029/1999rs900105

Cited by 73 publications

(42 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and observed ionospheric parameters (foF2, h'F2, hmF2, etc. ) (Williscroft and Poole, 1996;McKinnell and Poole, 2004;Oyeyemi et al, 2005), short-term forecasting of ionospheric conditions (Altinay et al, 1997;Cander et al, 1998;Kumluca et al, 1999;Wintoft and Cander, 2000;Poole and McKinnell, 2000;Oyeyemi et al, 2006), and long-term trend analyses (Poole and Poole, 2002;Yue et al, 2006). Because of the input-output mapping features of NNs, they could be used to generate reference ionospheric models for possible incorporation into the IRI (McKinnell and Friedrich, 2007).…”

Section: Introductionmentioning

confidence: 99%

Regional reference total electron content model over Japan based on neural network mapping techniques

Maruyama

2007

Ann. Geophys.

View full text Add to dashboard Cite

Abstract.A regional reference model of total electron content (TEC) was constructed using data from the GPS Earth Observation Network (GEONET), which consists of more than 1000 Global Positioning System (GPS) satellite receivers distributed over Japan. The data covered almost one solar activity period from April 1997 to June 2007. First, TECs were determined for 32 grid points, expanding from 27 to 45 • N in latitude and from 127 to 145 • E in longitude at 15-min intervals. Secondly, the time-latitude variation averaged over three days was determined by using the surface harmonic functional expansion. The coefficients of the expansion were then modeled by using a neural network technique with input parameters of the season (day of the year) and solar activity (F10.7 index and sunspot number). Thus, two-dimensional TEC maps (time vs. latitude) can be obtained for any given set of solar activity and day of the year.

show abstract

Section: Introductionmentioning

confidence: 99%

Regional reference total electron content model over Japan based on neural network mapping techniques

Maruyama

2007

Ann. Geophys.

View full text Add to dashboard Cite

show abstract

“…The testing data set was used during training to determine the optimal NN so that the NN was not over-trained. The training of the NN is terminated when the test error values versus the number of training epochs pass through a predetermined amount (Kumluca et al, 1999;Poole and McKinnell, 2000). At this point the NN is said to have achieved generalization, such that it produces a good performance when presented with a new set of input patterns that were not included in the training of the NN (i.e.…”

Section: Training the Nnmentioning

confidence: 99%

Near-real time foF2 predictions using neural networks

Oyeyemi

McKinnell

Poole

2006

Journal of Atmospheric and Solar-Terrestrial Physics

View full text Add to dashboard Cite

“…Over the years a large number of global, regional and station-specific models have been developed to predict the values of F2-layer critical frequency (Jones and Obotts, 1970;Ching and Chiu, 1973;Chiu, 1975;Fox and McNAmara, 1988;Rush et al, 1989;Bilitza, 1990Bilitza, , 2001Poole and McKinnell, 2000). Recently the work of Fuller-Rowell et al (2000), a storm-time correction model, has been a major development for the updating of F2 peak density incorporated into the IRI model.…”

Section: Introductionmentioning

confidence: 97%