mlsanityData to 7 Oct 2026

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

arXiv 2602.22188 ↗First posted 25 Feb 2026cs.LG cs.AI physics.flu-dyncited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 69 references that are in the map. First posted on arXiv 25 Feb 2026.

Builds on

28 of 69 references.

References · 28

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  5. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  6. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
  7. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
  8. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 470
  9. 2015Adversarial Autoencoderscited by 359
  10. 2021U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flowcited by 292
  11. 2021Curriculum Learning: A Surveycited by 257
  12. 2020A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEscited by 105
16 more
  1. 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulationcited by 65
  2. 2018Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systemscited by 54
  3. 2020Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equationscited by 24
  4. 2021Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniquescited by 23
  5. 2020An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusioncited by 19
  6. 2024Temporally Consistent Koopman Autoencoders for Forecasting Dynamical Systemscited by 15
  7. 2021Surrogate Modeling of Fluid Dynamics with a Multigrid Inspired Neural Network Architecturecited by 9
  8. 2022Surrogate Modeling of Melt Pool Thermal Field using Deep Learningcited by 8
  9. 2021Non-intrusive Surrogate Modeling for Parametrized Time-dependent PDEs using Convolutional Autoencoderscited by 6
  10. 2024IE-NeRF: Inpainting Enhanced Neural Radiance Fields in the Wildcited by 6
  11. 2021Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Surveycited by 4
  12. 2022An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipescited by 3
  13. 2023Solving Large-scale Spatial Problems with Convolutional Neural Networkscited by 3
  14. 2023Patch-CNN: Training data-efficient deep learning for high-fidelity diffusion tensor estimation from minimal diffusion protocolscited by 3
  15. 2022Image-based Artificial Intelligence empowered surrogate model and shape morpher for real-time blank shape optimisation in the hot stamping processcited by 1
  16. 2025A Deep-Learning Iterative Stacked Approach for Prediction of Reactive Dissolution in Porous Mediacited by 1

Built on by

Not cited yet.