Advertisement

Interpretation of Airborne Electromagnetic Data with Neural Networks

  • Edmund Winkler
  • Wolfgang Seiberl
  • Andreas Ahl
Part of the Modern Approaches in Geophysics book series (MAGE, volume 21)

Abstract

Artificial Neural Networks (ANNs) are used for the interpretation of multi-frequency airborne electromagnetic (AEM) data independently of the sensor height, with one-dimensional (1-D) horizontally layered homogeneous earth structures. A divide-and-conquer strategy is applied. One ANN is trained to interpret data, which are best described by homogeneous half-space (HHS) models. A second ANN inverts data from horizontally layered half-space models with two layers (2LHS). Tests have shown that when the 2LHS ANN is applied to data, which are best, described with a HHS-like structure, interpretation errors can become large. Therefore, a third ANN is trained, which classifies the best interpretation of measurements as a HHS model or a 2LHS model. This modular ANN approach shows a good performance on synthetic data. Finally, the interpretation of data from an AEM survey over a tertiary basin structure, shows good accordance with known geological data.

Keywords

Error Threshold Sensor Height Frequency Pair Hide Layer Output Layer Coil Separation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Anderson, W., 1979, Numerical integration of related Hankel transforms of order 0 and I by adaptive digital filtering: Geophysics, 44, 1287–1305.Google Scholar
  2. Anguita, D., Parodi, G., and Zunino, R., 1993, Speed Improvement of the back-propagation on current generation workstations: Proceedings of the World Congress on Neural Networking, Portland, Oregon, 1993, vol. 1, Lawrence Erlbaum/INNS Press, 165–168.Google Scholar
  3. Elliott, D., 1993, A better activation function for artificial neural networks: ISR Technical Report TR93–8, Institute for System Research, University of Maryland.Google Scholar
  4. Fahlman, S. E., 1988, An empirical study of learning speed in back-propagation networks: CMU-CS-88–162, September 1988.Google Scholar
  5. Wait, J. R., 1982, Geo-electromagnetism: Academic Press Inc., 121–124.Google Scholar
  6. Yu, Y., and Simmons, R., 1990, Descending epsilon in backpropagation: a technique for better generalization: Proc. Internat. Joint Conf. on Neural Networks, 167–172.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2003

Authors and Affiliations

  • Edmund Winkler
    • 1
  • Wolfgang Seiberl
    • 2
  • Andreas Ahl
    • 2
  1. 1.Geological Survey of AustriaWienAustria
  2. 2.Institute of Meteorology and GeophysicsWienAustria

Personalised recommendations