A novel three-direction datum transformation of geodetic coordinates for Egypt using artificial neural network approach

  • H. T. Elshambaky
  • Mosbeh R. Kaloop
  • Jong Wan Hu
Original Paper
  • 47 Downloads

Abstract

The geodetic datum transformation in-between local and global systems seen in the world are inspiring for the engineering applications. In this context, the Egyptian geodetic network has a limited observation for the terrestrial and satellite of the geodetic networks. Transforming the coordinates of the Egyptian datum, here we demonstrate the datum transformation in three directions from global to local coordinates that utilized the artificial neural network (ANN) technique as a new tool of datum transformation in Egypt. A conventional, which are the Helmert and Molodensky, and numerical, which are the regression, minimum curvature surface, and ANN, datum transformation techniques are investigated and compared over the available data in Egypt. The results showed an accurate transforming datum using ANN technique for both common and check points, and the novel model improved the transformation coordinates by 37 to 72% in space directions. A comparison between the conventional and numerical techniques shows that the accuracy of the developed ANN model is 20.16 cm in terms of standard deviation based on the residuals of the projected coordinates.

Keywords

Datum transformation Coordinates Neural networks 

Notes

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (2017R1A2B2010120).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. Abd-Elmotaal H (1994) Comparison of polynomial and similarity transformation based datum-shifts for Egypt. Bull Geod 68(3):168–172CrossRefGoogle Scholar
  2. Abou-Beih OM, Al-Garni AM (1996) Precise geodetic positioning based on the concept of variable datum transformation parameters. Australian Surveyor 41(3):214–220CrossRefGoogle Scholar
  3. Akyilmaz MO et al (2009) Soft computing methods for geoidal height transformation. Earth Planets Space 61(7):825–833CrossRefGoogle Scholar
  4. Ardalan AA, Grafarend EW, Ihde J (2002) Molodensky potential telluroid based on a minimum-distance map. Case study: the quasi-geoid of east Germany in the World Geodetic Datum 2000. J Geod 76(3):127–138CrossRefGoogle Scholar
  5. Civicioglu P (2012) Transforming geocentric cartesian coordinates to geodetic coordinates by using differential search algorithm. Comput Geosci 46:229–247CrossRefGoogle Scholar
  6. Dawod GM (2009) Geoid modelling in Egypt. google. Available at: https://sites.google.com/site/gomaadawod/geoidofegypt
  7. Dawod GM, Abdel-Aziz TM (2003) Establishement of a precise geodetic control network for updating the river nile maps. In: Proceedings of Al-Azhar Engineering 7th International Conference, Cairo. pp 1–11Google Scholar
  8. Dawod GM, Dalal SA (2000) Optimum geodetic datum transformation techniques for GPS surveys in Egypt. In: Conference: Al-Azhar Engineering Sixth International Conference, Cairo. pp 709–718Google Scholar
  9. Dawod GM, Mohamed HF, Ismail SS (2010) Evaluation and adaptation of the EGM2008 geopotential model along the Northern Nile Valley, Egypt: case study. J Surv Eng 136(1):36–40CrossRefGoogle Scholar
  10. Deakin R (2006) A note on the Bursa-Wolf and Molodensky-Badekas transformations, School of Mathematical & Geospatial Sciences, RMIT University, AustraliaGoogle Scholar
  11. Elmaghraby M, Fayad A, El-habiby M (2005) Investigating the effect of neglecting parts of the EGD geodetic height on the transformation from Helmert 1906 to WGS84. In: FIG Working Week 2005 and GSDI-8, Cairo. p TS13Google Scholar
  12. El-Shambaky HT (2004) Development and improvement the transformation parameters for egyptian. PhD thesis, public works engineering department, Mansoursa university, EgyptGoogle Scholar
  13. El-Tokhey ME et al (2015) Investigating the geometrical problems related to the redifinition of the Egyptian geodetic datum. Int J Eng ResTechnol (IJERT) 4(8):113–121Google Scholar
  14. Erol B, Erol S (2012) GNSS in practical determination of Regional Heights. In: Jin S (ed) Global navigation satellite systems: signal, theory and applications. InTech, Shanghai, China. pp 127–160Google Scholar
  15. Erol B, Erol S (2013) Learning-based computing techniques in geoid modeling for precise height transformation. Comput Geosci 52:95–107CrossRefGoogle Scholar
  16. Fang X (2014) A total least squares solution for geodetic datum transformations. Acta Geodaet Geophys 49(2):189–207CrossRefGoogle Scholar
  17. Fazilova D (2017) The review and development of a modern GNSS network and datum in Uzbekistan. Geodesy and Geodynamics 8(3):187–192Google Scholar
  18. Hagan MT, Demuth HB, Beale MH (1995) Neural network design, vol 2. PWS, Boston Massachusetts, p 734Google Scholar
  19. Haykin S (1994) Neural networks-A comprehensive foundation, 1st edn. Prentice Hall PTR, Upper Saddle RiverGoogle Scholar
  20. Haykin S (2001) Neural network: a comprehensive foundation, 2nd edn, Hamilton OntarioGoogle Scholar
  21. Herrault PA et al (2013) A comparative study of geometric transformation models for the historical “Map of France” registration. Geographia Technica 1:34–46Google Scholar
  22. Hornik KM, Stinchombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366CrossRefGoogle Scholar
  23. Jones GC (2002) New solutions for the geodetic coordinate transformation. J Geod 76(8):437–446CrossRefGoogle Scholar
  24. Khazraei SM et al (2017) Combination of GPS and leveling observations and geoid models using least-squares variance component estimation. J Surv Eng 143(2):04016023,1–0401602311CrossRefGoogle Scholar
  25. Kinneen RW, Featherstone WE (2004) An empirical comparison of coordinate transformations from the Australian Geodetic Datum (AGD66 and AGD84) to the Geocentric Datum of Australia (GDA94). J Spat Sci 49(2):1–29CrossRefGoogle Scholar
  26. Konakoglu B, Cakır L, Gökalp E (2016) 2D coordinate transformation using artificial neural networks. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-2/W1(October), pp 183–186Google Scholar
  27. Kwon JH, Bae TS, Choi YS, Lee DC, Lee YW (2005) Geodetic datum transformation to the global geocentric datum for seas and islands around Korea. Geosci J 9(4):353–361CrossRefGoogle Scholar
  28. Liao DC, Wang QJ, Zhou YH, Liao XH, Huang CL (2012) Long-term prediction of the earth orientation parameters by the artificial neural network technique. J Geodyn 62(May):87–92CrossRefGoogle Scholar
  29. Lwangasi AS (1993) Datum transformation parameters for the Kenya geodetic system. Surv Rev 32(247):39–46CrossRefGoogle Scholar
  30. Mataija M, Pogarčic M, Pogarčic I (2014) Helmert transformation of reference coordinating systems for geodesic purposes in local frames. Procedia Eng 69:168–176CrossRefGoogle Scholar
  31. MathWorks Inc (2015) Signal processing toolbox™ User’s guide R2015b. MathWorks Inc, p.OverviewGoogle Scholar
  32. Mikhail EM (1976) Observations and least squares. Dun Donnelly, New YorkGoogle Scholar
  33. Mina E (2006) A unified system of transformation parameters for combining different geodetic networks in Egypt. In: ASPRS 2006 Annual Conference Reno, NevadaGoogle Scholar
  34. Rabah M, Shaker A, Farhan M (2015) Towards a semi-kinematic datum for Egypt. Positioning 6:49–60CrossRefGoogle Scholar
  35. Rabah M, Elmewafey M, Farahan MH (2016) Datum maintenance of the main Egyptian geodetic control networks by utilizing precise point positioning “PPP” technique. NRIAG J Astron Geophys 5(1):96–105CrossRefGoogle Scholar
  36. Richard K (2009) Geometric aspects of mapping. International Institute for Geo-Information Science and Earth Observation (ITC), Enschede. Available at: https://kartoweb.itc.nl/geometrics/
  37. Saad AA, Elsayed MS (2007) Simple model for improving the accuracy of the egyptian geodetic triangulation network. In: FIG Working Week 2007 Hong Kong. pp 1–24Google Scholar
  38. Shaker AA et al (2007) Remove-restore technique for improving the datum transformation process. In: FIG Working Week 2007 Hong Kong. pp 13–17Google Scholar
  39. Shen YZ, Chen Y, Zheng DH (2006) A quaternion-based geodetic datum transformation algorithm. J Geod 80(5):233–239CrossRefGoogle Scholar
  40. Srivastava N et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958Google Scholar
  41. Tierra A, Romero R (2014) Planes coordinates transformation between PSAD56 to SIRGAS using a multilayer artificial neural network. Geodesy Cartography 63(2):199–209CrossRefGoogle Scholar
  42. Tierra A, Dalazoana R, De Freitas S (2008) Using an artificial neural network to improve the transformation of coordinates between classical geodetic reference frames. Comput Geosci 34(3):181–189CrossRefGoogle Scholar
  43. Vandenberg DJ (1999) Combining GPS and terrestrial observations to determine deflection of the vertical. Master thesis, Faculty of Engineering, Purdue University, USAGoogle Scholar
  44. Yang Y (1999) Robust estimation of geodetic datum transformation. J Geod 73(5):268–274CrossRefGoogle Scholar
  45. Zaki AM (2015) Assessment of GOCE models in Egypt. Master thesis, Cairo UniversityGoogle Scholar
  46. Závoti J, Kalmár J (2016) A comparison of different solutions of the Bursa–Wolf model and of the 3D, 7-parameter datum transformation. Acta Geodaetica et Geophysica 51(2):245–256CrossRefGoogle Scholar
  47. Ziggah YY et al (2013) Determination of GPS coordinate transformation parameters of geodetic data between reference datums—a case study of Ghana geodetic reference network. Int J Eng Sci Res Technol 2(4):956–971Google Scholar
  48. Ziggah YY, Youjian H, Yu X, Basommi LP (2016) Capability of artificial neural network for forward conversion of geodetic coordinates ( ϕ, λ, h ) to Cartesian coordinates (X, Y, Z). Math Geosci 48(6):687–721CrossRefGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2018

Authors and Affiliations

  • H. T. Elshambaky
    • 1
  • Mosbeh R. Kaloop
    • 2
    • 3
    • 4
  • Jong Wan Hu
    • 2
    • 3
  1. 1.Department of Civil EngineeringMisr Higher Institute for Engineering and TechnologyMansouraEgypt
  2. 2.Department of Civil and Environmental EngineeringIncheon National UniversityIncheonSouth Korea
  3. 3.Incheon Disaster Prevention Research CenterIncheon National UniversityIncheonSouth Korea
  4. 4.Department of Public Works and Civil EngineeringMansoura UniversityMansouraEgypt

Personalised recommendations