Comparison of Adaptive Algorithms for Significant Feature Selection in Neural Network Based Solution of the Inverse Problem of Electrical Prospecting

  • Authors:

  • Sergey Dolenko;Alexander Guzhva;Eugeny Obornev;Igor Persiantsev;Mikhail Shimelevich

  • Affiliations:

  • D.V. Skobeltsyn Institute of Nuclear Physics, M.V. Lomonosov Moscow State University, Moscow, Russia 119991;D.V. Skobeltsyn Institute of Nuclear Physics, M.V. Lomonosov Moscow State University, Moscow, Russia 119991;S.Ordjonikidze Russian State Geological Prospecting University, RSGPU, Moscow, Russia 117997;D.V. Skobeltsyn Institute of Nuclear Physics, M.V. Lomonosov Moscow State University, Moscow, Russia 119991;S.Ordjonikidze Russian State Geological Prospecting University, RSGPU, Moscow, Russia 117997

  • Venue:
  • ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

One of the important directions of research in geophysical electrical prospecting is solution of inverse problems (IP), in particular, the IP of magnetotellurics --- the problem of determining the distribution of electrical conductivity in the thickness of earth by the values of electromagnetic field induced by ionosphere sources, observed on earth surface. Solution of this IP is hampered by very high dimensionality of the input data (~103---104). Selection of the most significant features for each determined parameter makes it possible to simplify the IP and to increase the precision of its solution. This paper presents a comparison of two modifications of the developed algorithm for multi-step selection of significant features and the results of their application.