Mathematical Geosciences

, Volume 41, Issue 4, pp 379–395 | Cite as

Optimal Interpolation of Gravity Maps Using a Modified Neural Network

  • O. Sarzeaud
  • M.-F. LeQuentrec-Lalancette
  • D. Rouxel


This paper proposes an interpolation method based on a modified Kohonen artificial neural network, and is used to interpolate marine gravity data on a regular grid. This method combines accuracy comparable to that of kriging with a much shorter computing time than kriging. It is particularly efficient when both the size of the grid and the quantity of available data are large. Under some hypotheses similar to those of kriging with a trend, the unbiasedness and optimality of the method can be demonstrated. Comparison with kriging with a trend using marine gravity data shows similar results. Although neural interpolation is slightly less efficient, it is more robust outside of the marine data area.


Kohonen neural network Self-organizing map Universal kriging Optimal interpolation Gravity model 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Chilès JP, Delfiner P (1999) Geostatistics, modeling spatial uncertainty. Wiley series in probability and statistics. Wiley, New York Google Scholar
  2. David M, Crozet D, Robb JM (1986) Automated mapping of the ocean floor using the theory of intrinsic random functions of order k. Mar Geophys Res 8:49–74 CrossRefGoogle Scholar
  3. Kanevski M, Arutyunyan R, Bolshov L, Demyanov V, Maignan M (1996) Artificial neural networks and spatial estimations of Chernobyl fallout. Geoinformatics 7(1–2):5–11 Google Scholar
  4. Kohonen T (1995) Self-organizing maps. Springer, New York Google Scholar
  5. Lemoine FG, Kenyon SC, Factor JK, Trimmer RG, Pavlis NK, Chinn DS, Cox CM, Klosko SM, Lutchke SB, Torrence MH, Wang YM, Williamson RG, Pavlis EC, Rapp RH, Olson TR (1998) The development of the joint NASA GSFC and the National Imagery and Mapping Agency (NIMA) Geopotential Model EGM96: NASA/TP-1998-206861, Goddard Space Flight Center, NASA Greenbelt, Maryland 20771, USA Google Scholar
  6. Matheron G (1973) The intrinsic random functions and their applications. Adv Appl Probab 5:439–468 CrossRefGoogle Scholar
  7. Poggio T, Girosi F (1990) Networks for approximation and learning. Proc IEEE 78(9):1481–1497 CrossRefGoogle Scholar
  8. Ritter H, Schulten K (1986) On the stationary state of Kohonen’s self-organizing sensory mapping. Biol Cybern 54:99–106 CrossRefGoogle Scholar
  9. Ritter H, Schulten K (1988) Convergence properties of Kohonen’s topology conserving maps: Fluctuations, stability, and dimension selection. Biol Cybern 60:59–71 CrossRefGoogle Scholar
  10. Sarzeaud O, Stéphan Y (2000) Fast interpolation using Kohonen self-organizing neural networks. In: van Leeuwen J, Watanabe O, Hagiya M, Mosses PD, Ito T (eds) Theoretical computer science. Exploring new frontiers of theoretical informatics, International conference IFIP TCS 2000, Sendai, Japan. Lecture notes in computer science, vol 1872. Springer, Heidelberg, pp 126–139 Google Scholar

Copyright information

© International Association for Mathematical Geosciences 2009

Authors and Affiliations

  • O. Sarzeaud
    • 1
  • M.-F. LeQuentrec-Lalancette
    • 2
  • D. Rouxel
    • 2
  1. 1.ECTIANantes cedex 1France
  2. 2.EPSHOMBrest cedexFrance

Personalised recommendations