A neural network approach for regional vertical total electron content modelling

2007 ◽  
Vol 51 (2) ◽  
pp. 279-292 ◽  
Author(s):  
R. F. Leandro ◽  
M. C. Santos
Keyword(s):  
Neural Network ◽  
Total Electron Content ◽  
Electron Content ◽  
Vertical Total Electron Content ◽  
Network Approach ◽  
Neural Network Approach ◽  
Total Electron

PREDICTION OF TOTAL ELECTRON CONTENT OF THE IONOSPHERE USING NEURAL NETWORK

2016 ◽  
Vol 78 (5-8) ◽  
Author(s):  
Mariyam Jamilah Homam
Keyword(s):  
Neural Network ◽  
Total Electron Content ◽  
Relative Error ◽  
Absolute Error ◽  
Ionospheric Scintillation ◽  
Electron Content ◽  
Vertical Total Electron Content ◽  
Total Electron ◽  
Acceptable Range ◽  
Set Up

This paper presents the prediction of hourly Vertical Total Electron Content (VTEC) using a neural network by utilizing the data from a GPS Ionospheric Scintillation and TEC Monitor (GISTM) receiver for six years (from 2005 to 2010) during low to medium solar activity (Sunspot number (SSN) between 0.0 and 42.6). Several network configurations were investigated to observe the effect of the number of neurons, and hidden layers. Overall testing process for several network set-up yielded Root Mean Square Error (RMSE) value of 3 to 7 TECU, absolute error of 2 to 6 TECU and relative error of 8% to 28%.  Testing using April 2010 to November 2010 data (SSN from 8.0 to 25.2) produced RMSE value of 2.95 to 3.88 TECU,absolute error of 2.39 to 3.09 TECU and relative error of 8.11% to 16.18%, which are within the acceptable range. 

scholarly journals Appraisal of ANN and ANFIS for Predicting Vertical Total Electron Content (VTEC) in the Ionosphere for GPS Observations

2017 ◽  
Vol 17 (2) ◽  
pp. 12-16
Author(s):  
I. Yakubu ◽  
Y. Y. Ziggah ◽  
D. Asafo-Agyei
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Total Electron Content ◽  
Fuzzy Inference ◽  
Electron Content ◽  
Vertical Total Electron Content ◽  
Inference System ◽  
Total Electron ◽  
Neuro Fuzzy ◽  
Gps Observations

Positional accuracy in the usage of GPS receiver is one of the major challenges in GPS observations. The propagation of the GPS signals are interfered by free electrons which are the massive particles in the ionosphere region and results in delays in the transmission of signals to the Earth. Therefore, the total electron content is a key parameter in mitigating ionospheric effects on GPS receivers. Many researchers have therefore proposed various models and methods for predicting the total electron content along the signal path. This paper focuses on the use of two different models for predicting the Vertical Total Electron Content (VTEC). Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) algorithms have been developed for the prediction of VTEC in the ionosphere.  The developed ANN and ANFIS model gave Root Mean Square Error (RMSE) of 1.953 and 1.190 respectively.  From the results it can be stated that the ANFIS is more suitable tool for the prediction of VTEC. Keywords: Artificial Neural Network, Adaptive Neuro Fuzzy Inference System, Vertical Total Electron

Analysis of ionospheric vertical total electron content before the 1 April 2014 Mw 8.2 Chile earthquake

2017 ◽  
Vol 21 (6) ◽  
pp. 1599-1612 ◽  
Author(s):  
Weiping Jiang ◽  
Yifang Ma ◽  
Xiaohui Zhou ◽  
Zhao Li ◽  
Xiangdong An ◽  
...  
Keyword(s):  
Total Electron Content ◽  
Electron Content ◽  
Vertical Total Electron Content ◽  
Total Electron ◽  
Chile Earthquake

scholarly journals Neural network based model for global Total Electron Content forecasting

2020 ◽  
Vol 10 ◽  
pp. 11 ◽  
Author(s):  
Claudio Cesaroni ◽  
Luca Spogli ◽  
Angela Aragon-Angel ◽  
Michele Fiocca ◽  
Varuliator Dear ◽  
...  
Keyword(s):  
Neural Network ◽  
Total Electron Content ◽  
Geomagnetic Storms ◽  
Single Point ◽  
Global Scale ◽  
External Input ◽  
Electron Content ◽  
International Gnss Service ◽  
Total Electron ◽  
Grid Points

We introduce a novel empirical model to forecast, 24 h in advance, the Total Electron Content (TEC) at global scale. The technique leverages on the Global Ionospheric Map (GIM), provided by the International GNSS Service (IGS), and applies a nonlinear autoregressive neural network with external input (NARX) to selected GIM grid points for the 24 h single-point TEC forecasting, taking into account the actual and forecasted geomagnetic conditions. To extend the forecasting at a global scale, the technique makes use of the NeQuick2 Model fed by an effective sunspot number R12 (R12eff), estimated by minimizing the root mean square error (RMSE) between NARX output and NeQuick2 applied at the same GIM grid points. The novel approach is able to reproduce the features of the ionosphere especially during disturbed periods. The performance of the forecasting approach is extensively tested under different geospatial conditions, against both TEC maps products by UPC (Universitat Politècnica de Catalunya) and independent TEC data from Jason-3 spacecraft. The testing results are very satisfactory in terms of RMSE, as it has been found to range between 3 and 5 TECu. RMSE depend on the latitude sectors, time of the day, geomagnetic conditions, and provide a statistical estimation of the accuracy of the 24-h forecasting technique even over the oceans. The validation of the forecasting during five geomagnetic storms reveals that the model performance is not deteriorated during disturbed periods. This 24-h empirical approach is currently implemented on the Ionosphere Prediction Service (IPS), a prototype platform to support different classes of GNSS users.

scholarly journals Adaptive Modeling of the Global Ionosphere Vertical Total Electron Content

2020 ◽  
Vol 12 (11) ◽  
pp. 1822
Author(s):  
Eren Erdogan ◽  
Michael Schmidt ◽  
Andreas Goss ◽  
Barbara Görres ◽  
Florian Seitz
Keyword(s):  
Total Electron Content ◽  
Temporal Variations ◽  
Model Parameters ◽  
Electron Content ◽  
Vertical Total Electron Content ◽  
Model Uncertainties ◽  
Data Set ◽  
Total Electron ◽  
B Spline ◽  
Run Time

The Kalman filter (KF) is widely applied in (ultra) rapid and (near) real-time ionosphere modeling to meet the demand on ionosphere products required in many applications extending from navigation and positioning to monitoring space weather events and naturals disasters. The requirement of a prior definition of the stochastic models attached to the measurements and the dynamic models of the KF is a drawback associated with its standard implementation since model uncertainties can exhibit temporal variations or the time span of a given test data set would not be large enough. Adaptive methods can mitigate these problems by tuning the stochastic model parameters during the filter run-time. Accordingly, one of the primary objectives of our study is to apply an adaptive KF based on variance component estimation to compute the global Vertical Total Electron Content (VTEC) of the ionosphere by assimilating different ionospheric GNSS measurements. Secondly, the derived VTEC representation is based on a series expansion in terms of compactly supported B-spline functions. We highlight the morphological similarity of the spatial distributions and the magnitudes between VTEC values and the corresponding estimated B-spline coefficients. This similarity allows for deducing physical interpretations from the coefficients. In this context, an empirical adaptive model to account for the dynamic model uncertainties, representing the temporal variations of VTEC errors, is developed in this work according to the structure of B-spline coefficients. For the validation, the differential slant total electron content (dSTEC) analysis and a comparison with Jason-2/3 altimetry data are performed. Assessments show that the quality of the VTEC products derived by the presented algorithm is in good agreement, or even more accurate, with the products provided by IGS ionosphere analysis centers within the selected periods in 2015 and 2017. Furthermore, we show that the presented approach can be applied to different ionosphere conditions ranging from very high to low solar activity without concerning time-variable model uncertainties, including measurement error and process noise of the KF because the associated covariance matrices are computed in a self-adaptive manner during run-time.

scholarly journals Real-Time Global Ionospheric Map and Its Application in Single-Frequency Positioning

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1138 ◽  
Author(s):  
Liang Zhang ◽  
Yibin Yao ◽  
Wenjie Peng ◽  
Lulu Shan ◽  
Yulin He ◽  
...  
Keyword(s):  
Real Time ◽  
Total Electron Content ◽  
Precise Point Positioning ◽  
Single Frequency ◽  
Electron Content ◽  
Vertical Total Electron Content ◽  
Total Electron ◽  
Time Service ◽  
Point Positioning ◽  
Raw Observations

The prevalence of real-time, low-cost, single-frequency, decimeter-level positioning has increased with the development of global navigation satellite systems (GNSSs). Ionospheric delay accounts for most errors in real-time single-frequency GNSS positioning. To eliminate ionospheric interference in real-time single-frequency precise point positioning (RT-SF-PPP), global ionospheric vertical total electron content (VTEC) product is designed in the next stage of the International GNSS Service (IGS) real-time service (RTS). In this study, real-time generation of a global ionospheric map (GIM) based on IGS RTS is proposed and assessed. There are three crucial steps in the process of generating a real-time global ionospheric map (RTGIM): estimating station differential code bias (DCB) using the precise point positioning (PPP) method, deriving slant total electron content (STEC) from PPP with raw observations, and modeling global vertical total electron content (VTEC). Experiments were carried out to validate the algorithm’s effectiveness. First, one month’s data from 16 globally distributed IGS stations were used to validate the performance of DCB estimation with the PPP method. Second, 30 IGS stations were used to verify the accuracy of static PPP with raw observations. Third, the modeling of residuals was assessed in high and quiet ionospheric activity periods. Afterwards, the quality of RTGIM products was assessed from two aspects: (1) comparison with the Center for Orbit Determination in Europe (CODE) global ionospheric map (GIM) products and (2) determination of the performance of RT-SF-PPP with the RTGIM. Experimental results show that DCB estimation using the PPP method can realize an average accuracy of 0.2 ns; static PPP with raw observations can achieve an accuracy of 0.7, 1.2, and 2.1 cm in the north, east, and up components, respectively. The average standard deviations (STDs) of the model residuals are 2.07 and 2.17 TEC units (TECU) for moderate and high ionospheric activity periods. Moreover, the average root-mean-square (RMS) error of RTGIM products is 2.4 TECU for the one-month moderate ionospheric period. Nevertheless, for the high ionospheric period, the RMS is greater than the RMS in the moderate period. A sub-meter-level horizontal accuracy and meter-level vertical accuracy can be achieved when the RTGIM is employed in RT-SF-PPP.

Sign in / Sign up

Export Citation Format

Share Document