METHOD FOR DETERMINING THE ELECTRICAL RESISTIVITY OF TERRIGENOUS OIL RESERVOIRS FROM THE DATA OF ELECTRIC LOGGING OF SUBVERTICAL WELLS USING ARTIFICIAL NEURAL NETWORKS Russian patent published in 2022 - IPC G01V3/18 G01V3/38 

FIELD: downhole electrometry.

SUBSTANCE: invention relates to the field of downhole electrometry and can be used to search for missed oil-bearing formations according to electrical logging data of subvertical and slightly deviated wells. The determination of the specific electrical resistance of the environment of the rock mass is carried out in stages. At the first stage, an initial approximation of the borehole environment model is built using a neural network algorithm for the approximate solution of the inverse problem of electric logging sounding. At the second stage, the obtained near-wellbore model is refined by numerical inversion of the electric logging dataset using neural network modeling algorithms.

EFFECT: increasing the reliability of the results of interpretation of electric logging data measured in intervals of terrigenous deposits containing reservoirs, including thin ones, and improving the quality of the oil content forecast on this basis.

1 cl, 7 dwg