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

arXiv: https://arxiv.org/abs/2508.04084 · HTML: https://mlsanity.com/paper/2508.04084/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Machine Learning for Fluid Mechanics](https://mlsanity.com/paper/1905.11075/) (2019)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [Enhancing Computational Fluid Dynamics with Machine Learning](https://mlsanity.com/paper/2110.02085/) (2021)
- [Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow](https://mlsanity.com/paper/1802.10123/) (2018)
- [β-Variational autoencoders and transformers for reduced-order modelling of fluid flows](https://mlsanity.com/paper/2304.03571/) (2023)
- [Reduced order modeling of subsurface multiphase flow models using deep residual recurrent neural networks](https://mlsanity.com/paper/1810.10422/) (2018)
- [Symmetry-Aware Autoencoders: s-PCA and s-nlPCA](https://mlsanity.com/paper/2111.02893/) (2021)

## Built on by (most cited first, 2 of 2)

- [Generative prediction of laser-induced rocket ignition with dynamic latent space representations](https://mlsanity.com/paper/2603.07525/) (2026)
- [Learning Interface Breakup: A Geometry-Conditioned Latent Surrogate for Spray Formation](https://mlsanity.com/paper/2606.16587/) (2026)

## Abstract (arXiv)

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.