Forecasting total electron content maps by neural network technique

Abstract

[1] Near-Earth space processes are highly nonlinear. Since the 1990s, a small group at the Middle East Technical University in Ankara has been working on a data-driven generic model of such processes, that is, forecasting and nowcasting of a near-Earth space parameter of interest. The model developed is called the Middle East Technical University Neural Network (METU-NN) model. The METU-NN is a data-driven neural network model of one hidden layer and several neurons. In order to understand more about the complex response of the magnetosphere and ionosphere to extreme solar events, we chose this time the series of space weather events in November 2003. Total electron content (TEC) values of the ionosphere are forecast during these space weather events. In order to facilitate an easier interpretation of the forecast TEC values, maps of TEC are produced by using the Bezier surface-fitting technique.

A fuzzy neural network model to forecast the percent cloud coverage and cloud top temperature maps

“…Tulunay et al, , 2001Y. Tulunay et al, , 2004aRadicella and Tulunay, 2004;Stamper et al, 2004;Tulunay et al, 2006).…”

“…The Bezier surfaces have been used for mapping of some Near Earth Space parameters by the authors previously (Tulunay et al, 2006). Equation (2) is employed in computing the %CC or CTT forecast values at any location on the map by using Bezier surfaces.…”

Investigating the performance of neural network backpropagation algorithms for TEC estimations using South African GPS data

“…Research has shown that different problems require different training algorithms and types of neural networks. For example, in space weather applications involving predictions that use solar wind data as inputs, recurrent networks have been found to be more desirable (Lundstedt et al, 2002;Weigel et al, 2002Weigel et al, , 2003Vandegriff et al, 2005;Lundestedt, 2006;Habarulema et al, 2009;Heilig et al, 2010). Other ionospheric parameters, such as the critical frequency of the Eregion (foE) and critical frequency of the F2 layer (foF2), have been predicted using feed forward networks (e.g.…”

Nonlinear dynamic systems modeling using Gaussian processes: Predicting ionospheric total electron content over South Africa

“…[3] Other severely affected systems range from navigational systems (including high-frequency direction finding and satellite navigation) to Global Positioning System (GPS) surveying and space weather forecasts Hoffman-Wellenhof et al, 1992;Tulunay et al, 2004Tulunay et al, , 2006Opperman et al, 2007]. The vertical total electron content (TEC), defined as the number of free electrons in the ionosphere contained in a vertical column of unit cross sectional area (1 m 2 ), provides an indication of the ionospheric electron density and is often used to (partially) characterize the ionospheric variability.…”

“…[11] Nevertheless, neural networks have found considerable use in the modeling of TEC for over a decade, and in fact, besides the commonly encountered global International Reference Ionosphere (IRI) empirical model [Bilitza, 2001] which suffers from a historic scarcity of data in the Southern Hemisphere [McKinnel, 2002], the most interesting contributions to TEC modeling from a practical point of view have arguably been the development of several regional neural network models (see for example the work by HernandezPajares et al [1997] which made use of GPS observations, Xenos et al [2003] which employed Faraday-rotation derived TEC, Tulunay et al [2006] where NNs were used to predict TEC maps, as well as the work by Leandro and Santos [2007], Habarulema et al [2009], andYilmaz et al [2009]). …”