Ionosphere tomography using wavelet neural network and particle swarm optimization training algorithm in Iranian case study

Computerized tomography provides valuable information for imaging the ionospheric electron density distribution. We use a wavelet neural network with a particle swarm optimization training algorithm to solve pixel-based ionospheric tomography. This new method is called ionospheric tomography based on the neural network (ITNN). In this method, vertical and horizontal objective functions are minimized. Due to a poor vertical resolution of ionospheric tomography, empirical orthogonal functions are used as vertical objective function. For numerical experimentation, observations collected at 38 GPS stations on 2 days in 2007 (April 3 and July 13) from the Iranian permanent GPS network (IPGN) are used. Ionosonde observations (φ = 35.7382°, λ = 51.3851°) are used for validating the reliability of the proposed method. The modeling region is between 24°E to 40°E and 44°N to 64°N. The results of the ITNN method have been compared to those of the international reference ionosphere model 2012 (IRI-2012) and the spherical cap harmonics (SCHs) method as a local model. The minimum relative error for ITNN is 1.41% and the maximum relative error is 24.03%. Also, the root-mean-square error of 0.1932 × 1011 (el/m3) has been computed for ITNN, which is less than the RMSE of the IRI-2012 and SCHs method. The comparison of ITNN results with IRI-2012 and SCHs method shows that the proposed approach is superior to those of the traditional methods.

[1]  Mir Reza Ghaffari Razin,et al.  Development and analysis of 3D ionosphere modeling using base functions and GPS data over Iran , 2016, Acta Geodaetica et Geophysica.

[2]  Sandro M. Radicella,et al.  Calibration errors on experimental slant total electron content (TEC) determined with GPS , 2007 .

[3]  Lee-Anne McKinnell,et al.  A recurrent neural network approach to quantitatively studying solar wind effects on TEC derived from GPS; preliminary results , 2009 .

[4]  S. Schaer.  Mapping and predicting the Earth's ionosphere using the Global Positioning System. , 1999 .

[5]  Jiwen Dong,et al.  Time-series prediction using a local linear wavelet neural network , 2006, Neurocomputing.

[6]  Yibin Yao,et al.  A New Ionosphere Tomography Algorithm With Two-Grid Virtual Observations Constraints and Three-Dimensional Velocity Profile , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[7]  John W. MacDougall,et al.  GPS tomography in the polar cap: comparison with ionosondes and in situ spacecraft data , 2011 .

[8]  Mir Reza Ghaffari Razin,et al.  Regional ionosphere modeling using spherical cap harmonics and empirical orthogonal functions over Iran , 2017, Acta Geodaetica et Geophysica.

[9]  Yong Wang,et al.  A new two-step algorithm for ionospheric tomography solution , 2011, GPS Solutions.

[10]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[11]  D. Bilitza,et al.  International Reference Ionosphere 2007: Improvements and new parameters , 2008 .

[12]  G. V. Haines.  Computer programs for spherical cap harmonic analysis of potential and general fields , 1988 .

[13]  Ljiljana R. Cander,et al.  Artificial neural network applications in ionospheric studies , 1998 .

[14]  Mir Reza Ghaffari Razin,et al.  Regional application of multi-layer artificial neural networks in 3-D ionosphere tomography , 2016 .

[15]  Jeffrey Robert Austen,et al.  Ionospheric imaging using computerized tomography , 1988 .

[16]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[17]  Artem M. Padokhin,et al.  Ionospheric radio tomography based on the GPS/GLONASS navigation systems , 2011 .

[18]  Peter. Dyson,et al.  Using tomography of GPS TEC to routinely determine ionospheric average electron density profiles , 2007 .

[19]  Patricia H. Doherty,et al.  COMPARISON OF REAL-TIME IONOSPHERIC ALGORITHMS FOR A GPS WIDE-AREA AUGMENTATION SYSTEM (WAAS) , 1994 .

[20]  John W. Sheppard,et al.  DOSI: Training artificial neural networks using overlapping swarm intelligence with local credit assignment , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.

[21]  Mir Reza Ghaffari Razin,et al.  Wavelet neural networks using particle swarm optimization training in modeling regional ionospheric total electron content , 2016 .

[22]  John A. Klobuchar,et al.  A First-Order, Worldwide, Ionospheric, Time-Delay Algorithm , 1975 .

[23]  Yang Gao,et al.  Ionospheric TEC predictions over a local area GPS reference network , 2004 .

[24]  Lee-Anne McKinnell,et al.  Neural network-based ionospheric modelling over the South African region , 2004 .

[25]  Jean-Fu Kiang,et al.  Modeling of ionospheric perturbation by 2004 Sumatra tsunami , 2009 .

[26]  Zhizhao Liu,et al.  Ionosphere modelling using carrier smoothed ionosphere observations from a regional gps network , 2002 .

[27]  Takashi Maruyama,et al.  Three‐dimensional ionospheric tomography using observation data of GPS ground receivers and ionosonde by neural network , 2005 .

[28]  Antonio Anzueto,et al.  A new two-step algorithm for the treatment of COPD , 2017, European Respiratory Journal.

[29]  Richard B. Langley,et al.  An Assessment of Predicted and Measured Ionospheric Total Electron Content Using a Regional GPS Network , 1996 .

[30]  Ulf Riebesell,et al.  Synthesis of iron fertilization experiments: From the iron age in the age of enlightenment , 2005 .

[31]  Atila Yilmaz,et al.  Regional TEC mapping using neural networks , 2009 .

[32]  M. Kamp,et al.  Medium-scale 4-D ionospheric tomography using a dense GPS network , 2013 .