Machine Learning in Viscoelastic Fluids via Energy-Based Kernel Embedding

TL;DR

This paper introduces energy-based kernel functions for viscoelastic fluid flows that embed flowfield data into a Hilbert space, enabling accurate energy-based metrics and reconstructions, improving analysis of complex fluid dynamics.

Contribution

The study develops a novel kernel embedding method for viscoelastic fluids that directly encodes mechanical energy, facilitating better flowfield analysis and reconstruction without hyperparameter tuning.

Findings

Kernel functions effectively embed flowfields into RKHS with energy as norm.

KPCA with these kernels outperforms traditional PCA in reconstructing flow energy.

The approach enables extraction of dominant coherent structures across flow regimes.

Abstract

The ability to measure differences in collected data is of fundamental importance for quantitative science and machine learning, motivating the establishment of metrics grounded in physical principles. In this study, we focus on the development of such metrics for viscoelastic fluid flows governed by a large class of linear and nonlinear stress models. To do this, we introduce a kernel function corresponding to a given viscoelastic stress model that implicitly embeds flowfield snapshots into a Reproducing Kernel Hilbert Space (RKHS) whose squared norm equals the total mechanical energy. Working implicitly with lifted representations in the RKHS via the kernel function provides natural and unambiguous metrics for distances and angles between flowfields without the need for hyperparameter tuning. Additionally, we present a solution to the preimage problem for our kernels, enabling accurate reconstruction of flowfields from their RKHS representations. Through numerical experiments on an unsteady viscoelastic lid-driven cavity flow, we demonstrate the utility of our kernels for extracting energetically-dominant coherent structures in viscoelastic flows across a range of Reynolds and Weissenberg numbers. Specifically, the features extracted by Kernel Principal Component Analysis (KPCA) of flowfield snapshots using our kernel functions yield reconstructions with superior accuracy in terms of mechanical energy compared to conventional methods such as ordinary Principal Component Analysis (PCA) with na\"ively-defined state vectors or KPCA with ad-hoc choices of kernel functions. Our findings underscore the importance of principled choices of metrics in both scientific and machine learning investigations of complex fluid systems.