mlsanityData to 7 Oct 2026

An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipes

arXiv 2202.06170 ↗First posted 13 Feb 2022physics.flu-dyn cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

The modelling of multiphase flow in a pipe presents a significant challenge for high-resolution computational fluid dynamics (CFD) models due to the high aspect ratio (length over diameter) of the domain. In subsea applications, the pipe length can be several hundreds of kilometres versus a pipe diameter of just a few inches. In this paper, we present a new AI-based non-intrusive reduced-order model within a domain decomposition framework (AI-DDNIROM) which is capable of making predictions for domains significantly larger than the domain used in training. This is achieved by using domain decomposition; dimensionality reduction; training a neural network to make predictions for a single subdomain; and by using an iteration-by-subdomain technique to converge the solution over the whole domain. To find the low-dimensional space, we explore several types of autoencoder networks, known for their ability to compress information accurately and compactly. The performance of the autoencoders is assessed on two advection-dominated problems: flow past a cylinder and slug flow in a pipe. To make predictions in time, we exploit an adversarial network which aims to learn the distribution of the training data, in addition to learning the mapping between particular inputs and outputs. This type of network has shown the potential to produce realistic outputs. The whole framework is applied to multiphase slug flow in a horizontal pipe for which an AI-DDNIROM is trained on high-fidelity CFD simulations of a pipe of length 10 m with an aspect ratio of 13:1, and tested by simulating the flow for a pipe of length 98 m with an aspect ratio of almost 130:1. Statistics of the flows obtained from the CFD simulations are compared to those of the AI-DDNIROM predictions to demonstrate the success of our approach.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 91 references that are in the map. First posted on arXiv 13 Feb 2022.

Builds on

27 of 91 references.

References · 27

  1. 2019Machine Learning for Fluid Mechanicscited by 380
  2. 2020A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEscited by 105
  3. 2018Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flowcited by 97
  4. 2019Digital Twin: Values, Challenges and Enablerscited by 81
  5. 2021POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decompositioncited by 79
  6. 2018Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systemscited by 54
  7. 2020Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernelscited by 53
  8. 2019Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamicscited by 45
  9. 2020Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flowscited by 36
  10. 2021A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networkscited by 30
  11. 2020Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equationscited by 24
  12. 2021Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniquescited by 23
15 more
  1. 2020Deep learning-based reduced order models in cardiac electrophysiologycited by 22
  2. 2021A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modelingcited by 22
  3. 2020An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusioncited by 19
  4. 2019Deep Learning Models for Global Coordinate Transformations that Linearize PDEscited by 17
  5. 2020Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial networkcited by 16
  6. 2021Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilationcited by 15
  7. 2020Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulationcited by 11
  8. 2021Nonlinear proper orthogonal decomposition for convection-dominated flowscited by 11
  9. 2020An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modellingcited by 10
  10. 2021Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilationcited by 7
  11. 2020A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizationscited by 6
  12. 2021Digital twins based on bidirectional LSTM and GAN for modelling the COVID-19 pandemiccited by 5
  13. 2021Adversarially trained LSTMs on reduced order models of urban air pollution simulationscited by 4
  14. 2021Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulationscited by 4
  15. 2021Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2022AI-enhanced iterative solvers for accelerating the solution of large scale parametrized systemscited by 3
  2. 2022Deep Convolutional Architectures for Extrapolative Forecast in Time-dependent Flow Problemscited by 1
  3. 2026Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approachcited by 0