Gated Recurrent Units for Lithofacies Classification Based on Seismic Inversion

Abstract

As a qualitative indicator, subsurface lithofacies is an important parameter that can characterize hydrocarbon reservoirs for the degree of compartmentalization. In order to account for the geological dependency between data samples along the vertical direction, the feed-backward Recurrent Neural Networks is applied to classify the sequential lithofacies in the subsurface. Particularly, Gated Recurrent Units (GRU) is used, which can be dedicated to learning how to update or reset hidden states (in this case, lithofacies), such that the information flow through the system is regulated. Operating on the output layer, the softmax function is able to map the probability values over various possible lithofacies, and the associated uncertainty could be analyzed subsequently. In addition, the statistical Hidden Markov Models (HMM) is applied to benchmark the performance of GRU, in which the embedded transition matrix could enforce the conditional probability between different lithofacies. The designed GRU and HMM are applied to a synthetic model of the Book Cliffs and a real dataset from the Vienna Basin. Instead of using well logs, elastic rock properties from a non-linear inversion scheme are proposed as inputs for the classification purpose, which could help to overcome the location limitations of cored wells, and 2D sections of reservoir lithofacies are then obtained.