A new three-dimensional computerized ionospheric tomography model based on a neural network

Computerized ionospheric tomography (CIT) is an ill-posed inverse problem owing to insufficient data acquisition. Therefore, the ionospheric electron density (IED) distributions cannot be reconstructed accurately. Although many attempts have been made to deal with this issue, there is still a long way to go before it can be completely overcome. Specifically, the inverted IEDs of voxels without observational information show a strong dependence on initial values, which affects the overall accuracy of CIT. Taking this into account, a new three-dimensional CIT model is developed, based on a backpropagation neural network. The neural network model is trained using the characteristics and inverted IEDs of voxels with observational information, and then, the IEDs of voxels without observational information are predicted again. Careful validation of the proposed model is performed by conducting numerical experiments with GPS simulation and real data under both quiet and disturbed ionospheric conditions. Compared with the traditional non-neural network method in the simulation experiment, the proposed method offers improvements of 62.0 and 56.89% in root mean square error and the mean absolute error for those voxels without observational information, respectively, while it offers improvements of 30.98 and 26.67% for all voxels of the whole region. In the real data experiment, the IEDs of the control groups obtained by the proposed method are compared with the target IEDs for all periods. The result presents correlation coefficient greater than 0.96 between this predicted IEDs and the target IEDs for all periods, and this further certifies the feasibility of the proposed method. Additionally, the latitude–longitude maps and profiles of the ionospheric electron density also show that the ill-posedness problem has a significantly weaker effect for those voxels without observational information.

[1]  Gangbing Song,et al.  A prediction model of short-term ionospheric foF2 based on AdaBoost , 2014 .

[2]  Behzad Voosoghi,et al.  Ionosphere tomography using wavelet neural network and particle swarm optimization training algorithm in Iranian case study , 2017, GPS Solutions.

[3]  Yao Yi.  An adaptive simultaneous iteration reconstruction technique for three-dimensional ionospheric tomography , 2014 .

[4]  I. K. Walker,et al.  Tomographic imaging of the ionospheric mid-latitude trough , 1993 .

[5]  S. Sripathi,et al.  On the utility of the ionosonde Doppler‐derived EXB drift during the daytime , 2016 .

[6]  Katsumi Hattori,et al.  Numerical validations of neural‐network‐based ionospheric tomography for disturbed ionospheric conditions and sparse data , 2011 .

[7]  Thomas L. Gaussiran,et al.  Ionospheric Data Assimilation Three‐Dimensional (IDA3D): A global, multisensor, electron density specification algorithm , 2004 .

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

[9]  Yibin Yao,et al.  An Improved Iterative Algorithm for 3-D Ionospheric Tomography Reconstruction , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Bodo W. Reinisch,et al.  International Reference Ionosphere 2016: From ionospheric climate to real‐time weather predictions , 2017 .

[11]  Shuanggen Jin,et al.  M_DCB: Matlab code for estimating GNSS satellite and receiver differential code biases , 2012, GPS Solutions.

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

[13]  Junjie Chen,et al.  An Adaboost-Backpropagation Neural Network for Automated Image Sentiment Classification , 2014, TheScientificWorldJournal.

[14]  Debao Wen,et al.  Tomographic reconstruction of ionospheric electron density based on constrained algebraic reconstruction technique , 2010 .

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

[17]  S. Franke,et al.  Application of computerized tomography techniques to ionospheric research , 1986 .

[18]  Xiaomin Luo,et al.  A new parameterized approach for ionospheric tomography , 2019, GPS Solutions.

[19]  Yibin Yao,et al.  An Improved Iterative Algorithm for Ionospheric Tomography Reconstruction by Using the Automatic Search Technology of Relaxation Factor , 2018, Radio Science.

[20]  J. Klobuchar,et al.  Application of computerized tomography to the investigation of ionospheric structures , 1990 .

[21]  M. Angling.  First assimilations of COSMIC radio occultation data into the Electron Density Assimilative Model (EDAM) , 2008 .

[22]  Xingliang Huo,et al.  Three-dimensional ionospheric tomography by an improved algebraic reconstruction technique , 2007 .

[23]  F. Ding,et al.  Global ionospheric electron density estimation based on multisource TEC data assimilation , 2017, GPS Solutions.

[24]  Li Zhang,et al.  A constrained optimization method based on BP neural network , 2016, Neural Computing and Applications.

[25]  Peiqing Li,et al.  Predicting ionospheric critical frequency of the F2 layer over Lycksele using the neural network improved by error compensation technology , 2016 .

[26]  Chen Zhou,et al.  Predicting foF2 in the China region using the neural networks improved by the genetic algorithm , 2013 .

[27]  Yanhong Chen,et al.  Regional 3‐D ionospheric electron density specification on the basis of data assimilation of ground‐based GNSS and radio occultation data , 2016 .

[28]  Thomas Hobiger,et al.  Constrained simultaneous algebraic reconstruction technique (C-SART) —a new and simple algorithm applied to ionospheric tomography , 2008 .