Application of Convolutional Neural Networks for Resistivity Logs Processing and Non-Iterative Express-Inversion in Complex Reservoir Environments

Abstract

The work is devoted to the development of techniques and software for the quantitative interpretation of resistivity oil well logs. The article considers the results of applying the neural network approach to the processing of resistivity logging data measured at intervals composed of thin layers with contrasting electrical properties. The proposed algorithms combine the advantages of data interpretation based on a two-dimensional axisymmetric medium model and high performance, which allows them to be used at the primary processing stage, increasing the reliability of express interpretation.