Centre dedocumentation
scientifique

Modeling of ionosphere time series using wavelet neural networks (case study: N-W of Iran) / Mir Reza Ghaffari Razin in Advances in space research, vol 58 n° 1 (July 2016)  

Public [article]  inAdvances in space research > vol 58 n° 1 (July 2016) . - pp 74 - 83 Titre : Modeling of ionosphere time series using wavelet neural networks (case study: N-W of Iran) Type de document : Article/Communication Auteurs : Mir Reza Ghaffari Razin, Auteur ; Behzad Voosoghi, Auteur Année de publication : 2016 Article en page(s) : pp 74 - 83 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes descripteurs IGN] International Reference Ionosphere [Termes descripteurs IGN] Iran [Termes descripteurs IGN] modèle numérique [Termes descripteurs IGN] ondelette [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] teneur totale en électrons Résumé : (auteur) Wavelet neural networks (WNNs) are important tools for analyzing time series especially when it is non-linear and non-stationary. It takes advantage of high resolution of wavelets and feed forward nature of neural networks (NNs). Therefore, in this paper, WNNs is used for modeling of ionosphere time series in Iran. To apply the method, observations collected at 22 GPS stations in 12 successive days of 2012 (DOY# 219–230) from Azerbaijan local GPS network are used. For training of WNN, back-propagation (BP) algorithm is used. The results of WNN compared with results of international reference ionosphere 2012 (IRI-2012) and international GNSS service (IGS) products. To assess the error of WNN, statistical indicators, relative and absolute errors are used. Minimum relative error for WNN compared with GPS TEC is 6.37% and maximum relative error is 12.94%. Also the maximum and minimum absolute error computed 6.32 and 0.13 TECU, respectively. Comparison of diurnal predicted TEC values from the WNN model and the IRI-2012 with GPS TEC revealed that the WNN provides more accurate predictions than the IRI-2012 model and IGS products in the test area. Numéro de notice : A2016-562 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://dx.doi.org/10.1016/j.asr.2016.04.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81742 [article]