Fitting the GPS/Leveling Quasi-Geoid Using Bayesian-Regulation BP Neural Network

Abstract:

The 2.5′×2.5′resolution local quasi-geoid is calculated using the global gravity field model and GPS/leveling data of region which points spacing is about 10km with the Bayesian- regulation BP neural network in this paper. The inner and outer precision of quasi-geoid are both superior 0.05m.The result indicat that the Bayesian regulation BP neural network could improve the precision of fitting and restrain the over-fitting in fitting. The region quasi-geoid excelled than 0.05m can be computed using the global gravity field model and about 10km baseline GPS/leveling data in smoothness region.

• Periodical: Applied Mechanics and Materials (Volumes 90-93)
• Pages: 2903-2906
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.90-93.2903
• Online since: September 2011
• Authors: Lei Song, Xiao Qing Hu
• Keywords: Bayesion-Regulation, BP Neural Network (BPNN), GPS/Leveling, Quasi-Geoid

References

[1] DingboChao: Geomatics and Information Science of Wuhan University.Vol 28(2003 Sup),p.110.In Chinese.

[2] Mingqing Yang, Fan Jin and Dacheng Zhu : Acta Geodaetica et Cartographica Sinica. Vol 28(1999),p.301. 110.In Chinese.

[3] Wusheng Hu, Xisheng Hua: Acta Geodaetica et Cartographica Sinica. Vol 31(2002),p.128. 110.In Chinese.

[4] Lei Song, Teng Huang: Journal of Southwest Jiaotong University. Vol 43(2008),p.724. 110.In Chinese.

[5] T. Kavzoglu, M.H. Saka: Journal of Geodesy. Vol 78(2004),p.520.

[6] Lei Song, Jian Fang:Geomatics and Information Science of Wuhan University. Vol 34(2009),p.552. 110.In Chinese.

[7] R.H. Rapp: Journal of Geodesy. Vol 71(1997),p.282.

[8] Chenglong Liu, Tianyu Yang: Journal of Southwest Jiaotong University. Vol 42(2007),p.148. In Chinese.

[9] Hongxia Li, Shiguo Xu, Chuiren Fan : Journal of Dalian University of Technology. Vol 46(2006 Sup),p.174. In Chinese.

[10] D.J. C. Mackay: Neural Computation. Vol 4(2009),p.415.