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

GPS Solutions - Tập 25 Số 1 - Trang 1-17 - 2021
Zheng, Dunyong1,2,3, Yao, Yibin1, Nie, Wenfeng4, Chu, Nan3, Lin, Dongfang3, Ao, Minsi5
1School of Geodesy and Geomatics, Wuhan University, Wuhan, China
2State Key Laboratory of Geodesy and Earth’s Dynamics, Institute of Geodesy and Geophysics, Chinese Academy of Sciences, Wuhan, China
3National–Local Joint Engineering Laboratory of Geo-Spatial Information Technology, Hunan University of Science and Technology, Xiangtan, China
4Institute of Space Sciences, Shandong University, Weihai, China
5Hunan Province Mapping and Science and Technology Investigation Institute, Changsha, China

Tóm tắt

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.

Tài liệu tham khảo

citation_journal_title=Space Weather; citation_title=Regional 3-D ionospheric electron density specification on the basis of data assimilation of ground-based GNSS and radio occultation data; citation_author=E Aa, S Liu, W Huang, L Shi, J Gong, Y Chen, H Shen, J Li; citation_volume=14; citation_issue=6; citation_publication_date=2016; citation_pages=433-448; citation_doi=10.1002/2016SW001363; citation_id=CR1 citation_journal_title=Ann Geophys Ger; citation_title=First assimilations of COSMIC radio occultation data into the electron density assimilative model (EDAM); citation_author=MJ Angling; citation_volume=26; citation_publication_date=2008; citation_pages=353-359; citation_doi=10.5194/angeo-26-353-2008; citation_id=CR2 citation_title=Yeh KC (1986) Application of computerized tomography techniques to ionospheric research; citation_inbook_title=Radio beacon contribution to the study of ionization and dynamics of the ionosphere and corrections to geodesy; citation_publication_date=1986; citation_pages=9-14; citation_id=CR3; citation_author=JR Austen; citation_author=SJ Franke; citation_author=CH Liu; citation_publisher=Finland citation_journal_title=Radio Sci; citation_title=Ionospheric imaging using computerized tomography; citation_author=JR Austen, SJ Franke, CH Liu; citation_volume=23; citation_issue=3; citation_publication_date=1988; citation_pages=299-307; citation_doi=10.1029/RS023i003p00299; citation_id=CR4 citation_journal_title=Space Weather; citation_title=International reference ionosphere 2016: from ionospheric climate to real-time weather predictions; citation_author=D Bilitza, D Altadill, V Truhlik, V Shubin, I Galkin, B Reinisch, X Huang; citation_volume=15; citation_issue=2; citation_publication_date=2017; citation_pages=418-429; citation_doi=10.1002/2016SW001593; citation_id=CR5 citation_journal_title=J Geophys Res Space Phys; citation_title=Ionospheric data assimilation three-dimensional (IDA3D): a global, multisensor, electron density specification algorithm; citation_author=GS Bust, TW Garner, TL Gaussiran; citation_volume=109; citation_publication_date=2004; citation_pages=A11312; citation_doi=10.1029/2003JA010234; citation_id=CR6 citation_journal_title=Scientific World J; citation_title=An adaboost-backpropagation neural network for automated image sentiment classification; citation_author=J Cao, J Chen, H Li; citation_volume=2014; citation_publication_date=2014; citation_pages=364649; citation_id=CR7 Chen B, Wu L, Dai W, Luo X, Xu Y (2019) A new parameterized approach for ionospheric tomography. GPS Solutions 23(4) https://doi.org/10.1007/s10291-019-0893-4 citation_journal_title=Adv Space Res; citation_title=Regional application of multi-layer artificial neural networks in 3-D ionosphere tomography; citation_author=MR Ghaffari Razin, B Voosoghi; citation_volume=58; citation_issue=3; citation_publication_date=2016; citation_pages=339-348; citation_doi=10.1016/j.asr.2016.04.029; citation_id=CR9 citation_journal_title=GPS Solut; citation_title=Ionosphere tomography using wavelet neural network and particle swarm optimization training algorithm in Iranian case study; citation_author=MR Ghaffari Razin, B Voosoghi; citation_volume=21; citation_issue=3; citation_publication_date=2017; citation_pages=1301-1314; citation_doi=10.1007/s10291-017-0614-9; citation_id=CR10 citation_journal_title=Radio Sci; citation_title=Numerical validations of neuralnetworkbased ionospheric tomography for disturbed ionospheric conditions and sparse data; citation_author=S Hirooka, K Hattori, T Takeda; citation_volume=46; citation_issue=5; citation_publication_date=2011; citation_pages=RS0F05; citation_doi=10.1029/2011RS004760; citation_id=CR11 citation_journal_title=Electr Eng Jpn; citation_title=Development of ionospheric tomography using neural network and its application to the 2007 southern Sumatra earthquake; citation_author=S Hirooka, K Hattori, M Nishihashi, S Kon, T Takeda; citation_volume=181; citation_issue=4; citation_publication_date=2012; citation_pages=9-18; citation_doi=10.1002/eej.22298; citation_id=CR12 citation_journal_title=Earth Planets Space; citation_title=Constrained simultaneous algebraic reconstruction technique (C-SART)—a new and simple algorithm applied to ionospheric tomography; citation_author=T Hobiger, T Kondo, Y Koyama; citation_volume=60; citation_issue=7; citation_publication_date=2008; citation_pages=727-735; citation_doi=10.1186/BF03352821; citation_id=CR13 citation_journal_title=GPS Solut; citation_title=M_DCB: Matlab code for estimating GNSS satellite and receiver differential code biases; citation_author=R Jin, S Jin, G Feng; citation_volume=16; citation_issue=4; citation_publication_date=2012; citation_pages=541-548; citation_doi=10.1007/s10291-012-0279-3; citation_id=CR14 citation_journal_title=J Geophys Res Space Phys; citation_title=On the utility of the ionosonde doppler-derived EXB drift during the daytime; citation_author=LM Joshi, S Sripathi; citation_volume=121; citation_issue=3; citation_publication_date=2016; citation_pages=2795-2811; citation_doi=10.1002/2015JA021971; citation_id=CR15 citation_journal_title=J Geophys Res; citation_title=Three-dimensional ionospheric tomography using observation data of GPS ground receivers and ionosonde by neural network; citation_author=X Ma, T Maruyama, G Ma, T Takeda; citation_volume=110; citation_issue=A5; citation_publication_date=2005; citation_pages=A05308; citation_doi=10.1029/2004JA010797; citation_id=CR16 citation_journal_title=Ann Geophys; citation_title=Tomographic imaging of the ionospheric mid-latitude trough; citation_author=S Pryse, L Kersley, D Rice, C Russell, I Walker; citation_volume=11; citation_issue=2–3; citation_publication_date=1993; citation_pages=144-149; citation_id=CR17 citation_journal_title=Radio Sci; citation_title=Application of computerized tomography to the investigation of ionospheric structures; citation_author=T Raymund, J Austen, S Franke, C Liu, J Klobuchar, J Stalker; citation_volume=25; citation_issue=5; citation_publication_date=1990; citation_pages=771-789; citation_doi=10.1029/RS025i005p00771; citation_id=CR18 citation_journal_title=GPS Solut; citation_title=Global ionospheric electron density estimation based on multi-source TEC data assimilation; citation_author=C She, W Wan, X Yue, B Xiong, Y Yu, F Ding, B Zhao; citation_volume=21; citation_issue=3; citation_publication_date=2017; citation_pages=1125-1137; citation_doi=10.1007/s10291-016-0580-7; citation_id=CR19 citation_journal_title=J Atmos Sol-Terr Phy; citation_title=Predicting fof2 in the china region using the neural networks improved by the genetic algorithm; citation_author=R Wang, C Zhou, Z Deng, B Ni, Z Zhao; citation_volume=92; citation_publication_date=2013; citation_pages=7-17; citation_doi=10.1016/j.jastp.2012.09.010; citation_id=CR20 citation_journal_title=GPS Solut; citation_title=Three-dimensional ionospheric tomography by an improved algebraic reconstruction technique; citation_author=D Wen, Y Yuan, J Ou, X Huo, K Zhang; citation_volume=11; citation_issue=4; citation_publication_date=2007; citation_pages=251-258; citation_doi=10.1007/s10291-007-0055-y; citation_id=CR21 citation_journal_title=GPS Solut; citation_title=Tomographic reconstruction of ionospheric electron density based on constrained algebraic reconstruction technique; citation_author=D Wen, S Liu, P Tang; citation_volume=14; citation_issue=4; citation_publication_date=2010; citation_pages=375-380; citation_doi=10.1007/s10291-010-0161-0; citation_id=CR22 citation_journal_title=IEEE T Geosci Remote; citation_title=An improved iterative algorithm for 3-D ionospheric tomography reconstruction; citation_author=Y Yao, J Tang, P Chen, S Zhang, J Chen; citation_volume=52; citation_issue=8; citation_publication_date=2014; citation_pages=4696-4706; citation_doi=10.1109/TGRS.2013.2283736; citation_id=CR23 citation_journal_title=Chinese J Geophys-Ch; citation_title=An adaptive simultaneous iteration reconstruction technique for three-dimensional ionospheric tomography; citation_author=Y Yao, T Jun, Z Liang, YH Chang, Z Shun; citation_volume=57; citation_issue=2; citation_publication_date=2014; citation_pages=345-353; citation_id=CR24 citation_journal_title=Neural Comput Appl; citation_title=A constrained optimization method based on bp neural network; citation_author=L Zhang, F Wang, T Sun, B Xu; citation_volume=29; citation_publication_date=2016; citation_pages=413-421; citation_doi=10.1007/s00521-016-2455-9; citation_id=CR25 citation_journal_title=Adv Space Res; citation_title=A prediction model of short-term ionospheric fof2 based on adaboost; citation_author=X Zhao, B Ning, L Liu, G Song; citation_volume=53; citation_issue=3; citation_publication_date=2014; citation_pages=387-394; citation_doi=10.1016/j.asr.2013.12.001; citation_id=CR26 citation_journal_title=Surv Rev; citation_title=Predicting ionospheric critical frequency of the F2 layer over Lycksele using the neural network improved by error compensation technology; citation_author=D Zheng, W Hu, P Li; citation_volume=48; citation_issue=347; citation_publication_date=2016; citation_pages=130-139; citation_doi=10.1179/1752270615Y.0000000015; citation_id=CR27 citation_journal_title=Radio Sci; citation_title=An improved iterative algorithm for ionospheric tomography reconstruction by using the automatic search technology of relaxation factor; citation_author=D Zheng, Y Yao, W Nie, W Yang, W Hu, M Ao, H Zheng; citation_publication_date=2018; citation_doi=10.1029/2018RS006588; citation_id=CR28