An attempt to apply artificial neural networks in integrated interpretation of electromagnetic data - the Grabownica hydrocarbon deposit case study

Abstract

The paper presents an attempt to apply the pattern recognition method using artificial neural networks in integrated interpretation of the magnetotelluric data AMT (Audio-frequency Magnetotellurics) and CSAMT (Controlled Source Audio-frequency Magnetotellurics), acquired from the Grabownica oil and gas deposit (longitudinal and transversal dipole in relation to measurement profile lines). Vertical belts of magnetotelluric cross-sections, each 50 m wide, obtained from interpolation grids, were the objects of classification. The structure of formally non-structural objects was partly imposed through division into: near-surface high-resistivity zone, to 200 m a.s.l., low-resistivity screens and week maxima - diffusion chimneys, from 200 to -100 m a.s.l., and the lowest, high-resistivity deposit zone. The usefulness of the method was proven by correct identification of real deposit zones based on data often coming from ambiguous and incompatible magnetotelluric cross-sections. In addition, two unknown deposit zones were discovered in NE part of cross-section G4 and SW part of cross-section G2.