Please use this identifier to cite or link to this item:
Authors: Cander, L. R.* 
Milosavljevic´, M. M.* 
Tomasevic´, S.* 
Title: Ionospheric storm forecasting technique by artificial neural network
Issue Date: 2003
Series/Report no.: 4/46 (2003)
Keywords: prediction and forecasting
neural networks
ionospheric storms modelling
space weather
Subject Classification01. Atmosphere::01.02. Ionosphere::01.02.03. Forecasts 
01. Atmosphere::01.02. Ionosphere::01.02.06. Instruments and techniques 
Abstract: In this work we further refine and improve the neural network based ionospheric characteristic's foF2 predictor, which is actually a neural network autoregressive model with additional input signals (NNARX). Our analysis is focused on choice of X parts of NNARX model in order to capture middle and long term dependencies. Daily distribution of prediction error suggests need for structural changes of the neural network model, as well as adaptation of running average lengths used for determination of X inputs. Generalisation properties of proposed neural predictor are improved by carefully designed pruning procedure with additional regularisation term in criterion function. Some results from the NNARX model are presented to illustrate the feasibility of using such a model as ionospheric storm forecasting technique.
Appears in Collections:Annals of Geophysics

Files in This Item:
File Description SizeFormat
Canoer719_724.pdf124.71 kBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Feb 7, 2023

Download(s) 50

checked on Feb 7, 2023

Google ScholarTM