Artificial Neural Network: A Powerful Tool for Predicting Gravity Anomaly from Sparse Data

  • A.R. Tierra
  • S.R.C. de Freitas
Part of the International Association of Geodesy Symposia book series (IAG SYMPOSIA, volume 129)


Generally, the gravity surveys are developed along roads or other communication ways. This leads to an irregular space distribution and lacking data in large areas, like that containing high mountains, wetlands, lakes and forests. The usual methods for geoid computation from gravity data need a regular grid of gravity anomalies. Numerous methods have been developed for gravity anomalies interpolation at regular distribution. This paper reports on implementation of an interpolation method by using techniques for learning and training of Artificial Neural Networks (ANN) in predicting both free-air and Bouguer gravity anomalies from irregular and sparse data. The method was applied for a region in the Ecuador (5°S - 1°N and 75°W – 81°W) that has strong variations in crustal density and morphology. The free-air gravity anomalies prediction results were compared with the method of Kriging interpolation. The ANN method presented better results in predicting gravity anomalies in the considered region.


Free air and Bouguer anomalies Predicting Artificial Neural Network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

8 References

  1. Cressie, N (1993). Statistics for Spatial Data. ISU, New York.Google Scholar
  2. Li, Y., and Bridgwater, J (2000). Prediction of Extrusion Pressure Using Artificial Neural Network. Powder Technology 108: 65–73.CrossRefGoogle Scholar
  3. Haykin, S (1999). Neural Networks: A Comprehensive Foundation. 2. ed. New Jersey: Prentice Hall.Google Scholar
  4. Haykin, S (2001). Redes Neurais: Princípios e Prática. 2. ed. Porto Alegre: Bookman.Google Scholar
  5. Heiskanen, W., and Moritz, H (1967). Physical Geodesy. H. Freeman and Company.Google Scholar
  6. Forsberg, R (1994). Terrain Effects in Geoid Computations. In: Lectures Notes of the International School for the Determination and Use of the Geoid. International Geoid Service, Milan.Google Scholar
  7. Moritz, H (1980). Advanxed Physical Geodesy. H. Wichmann Verlag, Karlsruhe.Google Scholar
  8. Muñoz, A (1996). Aplicación de Técnicas de Redes Neuronales Artificiales al Diagnóstico de Procesos Industriales. Ph.D. Thesis, Dept. de Electrotécnia y Sistemas, Universidad Pontificia Comillas de Madrid.Google Scholar
  9. Loeseh, C., and Sari, S (1996). Redes Neurais Artificias. Fundamentos e Modelos. Blumenau, Brazil.Google Scholar
  10. Smith, W., and Wessel, P (1990). Gridding with Continuous Curvature Splines in Tension. Geophysics 55(3):293–305.CrossRefGoogle Scholar
  11. Tierra, A., and De Freitas, S (2002). Predicting Free-Air Gravity Anomaly Using Artificial Neural Network. International Association of Geodesy Symposia: Vertical Reference Systems. Springe 124: 215–218.Google Scholar
  12. Tierra, A (2003). Metodologia para a Geração da Malha de Anomalias Gravimétricas para Obtenção do Geoide Gravimétrico Local a partir de Dados Esparsos. Ph.D. Thesis Department of Geomatics, Federal University of Parana.Google Scholar
  13. Torge, W (1989). Gravimetry. New York: de Gruyter, New York.Google Scholar
  14. Watson, D (1992). Contouring: A Guide to the Analysis and Display of Spatial Data. Pergamon.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • A.R. Tierra
    • 1
  • S.R.C. de Freitas
    • 2
  1. 1.Geodetic Laboratory, Department of Geography and Environmental EngineeringArmy Polytechnic SchoolSangolquíEcuador
  2. 2.Graduate Course of GeodesyFederal University of Parana, Centra PolitécnicoCuritibaBrazil

Personalised recommendations