AI summaryⓘ
The authors created eight simpler computer models to predict how fluid moves through porous rocks, which usually requires complex and slow calculations. Four models use two neural networks—one to shrink the data and one to make predictions—while the other four are single neural networks that can work on bigger areas than they were trained on, called grid-size invariance. They found that the UNet++ architecture works better than UNet for their models. Also, the grid-size-invariant models use less memory and predict fluid flow more accurately than the simpler reduced-order models. Their work focuses on a tough problem where the rock changes over time due to fluid dissolving it, which makes future predictions harder.
rock-fluid interactionpartial differential equationsreduced-order modelsneural networksgrid-size invarianceUNetUNet++surrogate modelsporous mediafluid-induced rock dissolution
Authors
Nathalie C. Pinheiro, Donghu Guo, Hannah P. Menke, Aniket C. Joshi, Claire E. Heaney, Ahmed H. ElSheikh, Christopher C. Pain
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.