History Matching under Uncertainty of Geological Scenarios with Implicit Geological Realism Control with Generative Deep Learning and Graph Convolutions

TL;DR

This paper introduces a graph-based variational autoencoder for reservoir modeling that captures geological scenario uncertainty and implicitly controls geological realism through latent variables and geodesic metrics.

Contribution

It presents a novel graph-based deep learning approach for geological realism control in reservoir modeling, differing from traditional lattice-based methods.

Findings

Viability demonstrated on synthetic 3D geological data

Latent space analysis reveals meaningful structure

Effective uncertainty handling in geological scenarios

Abstract

The graph-based variational autoencoder represents an architecture that can handle the uncertainty of different geological scenarios, such as depositional or structural, through the concept of a lowerdimensional latent space. The main difference from recent studies is utilisation of a graph-based approach in reservoir modelling instead of the more traditional lattice-based deep learning methods. We provide a solution to implicitly control the geological realism through the latent variables of a generative model and Geodesic metrics. Our experiments of AHM with synthetic dataset that consists of 3D realisations of channelised geological representations with two distinct scenarios with one and two channels shows the viability of the approach. We offer in-depth analysis of the latent space using tools such as PCA, t-SNE, and TDA to illustrate its structure.