Inversion of coincident loop TEM data for layered polarizable ground using neural networks

Hesham M. El-Kaliouby, Mary M. Poulton, Essam A. ElDiwany

Research output: Contribution to conferencePaperpeer-review

11 Scopus citations

Abstract

Inversion of the transient voltage response of a coincident loop electromagnetic system above polarizable ground is performed using a neural network approach. The voltage response, which includes a negative part, is inverted for the Cole-Cole parameters of the ground. The inversion is found to be successful with low root mean square (RMS) error using voltage response data for one loop radius. Reduction of the RMS error results when using data from two loop radii and when dividing the parameter ranges into two groups. The results could be effectively used as starting models in classical inversion programs to obtain more accurate results since the present results are free of trapping in far local minima.

Original languageEnglish (US)
StatePublished - 1999
Event1999 Society of Exploration Geophysicists Annual Meeting, SEG 1999 - Houston, United States
Duration: Oct 31 1999Nov 5 1999

Other

Other1999 Society of Exploration Geophysicists Annual Meeting, SEG 1999
Country/TerritoryUnited States
CityHouston
Period10/31/9911/5/99

ASJC Scopus subject areas

  • Geophysics

Fingerprint

Dive into the research topics of 'Inversion of coincident loop TEM data for layered polarizable ground using neural networks'. Together they form a unique fingerprint.

Cite this