Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approach

TL;DR

This paper introduces grid-size-invariant neural network surrogate models for simulating rock-fluid interactions, offering a computationally efficient alternative to high-fidelity models with improved performance and reduced memory usage.

Contribution

It presents a novel grid-size-invariant neural network framework for rock-fluid interaction modeling and compares UNet and UNet++ architectures, demonstrating UNet++'s superior accuracy.

Findings

Grid-size-invariant models outperform reduced-order models in accuracy.

UNet++ surpasses UNet in predictive performance.

The approach reduces memory consumption during training.

Abstract

Modelling rock-fluid interaction requires solving a set of partial differential equations (PDEs) to predict the flow behaviour and the reactions of the fluid with the rock on the interfaces. Conventional high-fidelity numerical models require a high resolution to obtain reliable results, resulting in huge computational expense. This restricts the applicability of these models for multi-query problems, such as uncertainty quantification and optimisation, which require running numerous scenarios. As a cheaper alternative to high-fidelity models, this work develops eight surrogate models for predicting the fluid flow in porous media. Four of these are reduced-order models (ROM) based on one neural network for compression and another for prediction. The other four are single neural networks with the property of grid-size invariance; a term which we use to refer to image-to-image models that are capable of inferring on computational domains that are larger than those used during training. In addition to the novel grid-size-invariant framework for surrogate models, we compare the predictive performance of UNet and UNet++ architectures, and demonstrate that UNet++ outperforms UNet for surrogate models. Furthermore, we show that the grid-size-invariant approach is a reliable way to reduce memory consumption during training, resulting in good correlation between predicted and ground-truth values and outperforming the ROMs analysed. The application analysed is particularly challenging because fluid-induced rock dissolution results in a non-static solid field and, consequently, it cannot be used to help in adjustments of the future prediction.