Towards geological inference with process-based and deep generative modeling, part 2: inversion of fluvial deposits and latent-space disentanglement

TL;DR

This paper investigates the use of process-based generative adversarial networks (GANs) for modeling fluvial deposits, focusing on inversion techniques and latent space disentanglement to improve geological predictions.

Contribution

It introduces inversion methods for GANs trained on geological data and explores latent space disentanglement strategies to enhance model accuracy and interpretability.

Findings

GAN inversion struggles with increased well data and divergent test samples.

Latent space entanglement limits inversion success, but partial disentanglement helps.

Fine-tuning GANs improves match quality, supporting their integration into workflows.

Abstract

High costs and uncertainties make subsurface decision-making challenging, as acquiring new data is rarely scalable. Embedding geological knowledge directly into predictive models offers a valuable alternative. A joint approach enables just that: process-based models that mimic geological processes can help train generative models that make predictions more efficiently. This study explores whether a generative adversarial network (GAN) - a type of deep-learning algorithm for generative modeling - trained to produce fluvial deposits can be inverted to match well and seismic data. Four inversion approaches applied to three test samples with 4, 8, and 20 wells struggled to match these well data, especially as the well number increased or as the test sample diverged from the training data. The key bottleneck lies in the GAN's latent representation: it is entangled, so samples with similar sedimentological features are not necessarily close in the latent space. Label conditioning or latent overparameterization can partially disentangle the latent space during training, although not yet sufficiently for a successful inversion. Fine-tuning the GAN to restructure the latent space locally reduces mismatches to acceptable levels for all test cases, with and without seismic data. But this approach depends on an initial, partially successful inversion step, which influences the quality and diversity of the final samples. Overall, GANs can already handle the tasks required for their integration into geomodeling workflows. We still need to further assess their robustness, and how to best leverage them in support of geological interpretation.