Convolutional autoencoders for the reconstruction of three-dimensional interfacial multiphase flows

TL;DR

This paper systematically investigates how different interface representations affect the performance of convolutional autoencoders in reconstructing 3D interfacial multiphase flows, highlighting the importance of choosing a balanced diffuse interface.

Contribution

It provides a comprehensive analysis of interface representation impacts on autoencoder accuracy, establishing best practices for reduced-order modeling of multiphase flows.

Findings

Moderately diffuse interfaces yield optimal reconstruction accuracy.

Sharp interfaces cause loss of small-scale features.

Diffuse interfaces degrade overall accuracy.

Abstract

We present a systematic investigation of convolutional autoencoders for the reduced-order representation of three-dimensional interfacial multiphase flows. Focusing on the reconstruction of phase indicators, we examine how the choice of interface representation, including sharp, diffuse, and level-set formulations, impacts reconstruction accuracy across a range of interface complexities. Training and validation are performed using both synthetic datasets with controlled geometric complexity and high-fidelity simulations of multiphase homogeneous isotropic turbulence. We show that the interface representation plays a critical role in autoencoder performance. Excessively sharp interfaces lead to the loss of small-scale features, while overly diffuse interfaces degrade overall accuracy. Across all datasets and metrics considered, a moderately diffuse interface provides the best balance between preserving fine-scale structures and achieving accurate reconstructions. These findings elucidate key limitations and best practices for dimensionality reduction of multiphase flows using autoencoders. By clarifying how interface representations interact with the inductive biases of convolutional neural networks, this work lays the foundation for decoupling the training of autoencoders for accurate state compression from the training of surrogate models for temporal forecasting or input-output prediction in latent space.