History Matching under Uncertainty of Geological Scenarios with Implicit Geological Realism Control with Generative Deep Learning and Graph Convolutions
This work addresses uncertainty in reservoir modeling for geology and energy sectors, but it is incremental as it builds on existing generative deep learning methods with a graph-based adaptation.
The paper tackled the problem of history matching under uncertainty in geological scenarios by using a graph-based variational autoencoder to implicitly control geological realism through latent variables and geodesic metrics, achieving viability on a synthetic dataset with 3D channelised representations.
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.