Physics-agnostic and Physics-infused machine learning for thin films flows: modeling, and predictions from small data

Abstract

Numerical simulations of multiphase flows are crucial in numerous engineering applications, but are often limited by the computationally demanding solution of the Navier-Stokes (NS) equations. Here, we present a data-driven workflow where a handful of detailed NS simulation data are leveraged into a reduced-order model for a prototypical vertically falling liquid film. We develop a physics-agnostic model for the film thickness, achieving a far better agreement with the NS solutions than the asymptotic Kuramoto-Sivashinsky (KS) equation. We also develop two variants of physics-infused models providing a form of calibration of a low-fidelity model (i.e. the KS) against a few high-fidelity NS data. Finally, predictive models for missing data are developed, for either the amplitude, or the full-field velocity and even the flow parameter from partial information. This is achieved with the so-called "Gappy Diffusion Maps", which we compare favorably to its linear counterpart, Gappy POD.

References in corpus (15)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
• Machine learning building-block-flow wall model for large-eddy simulation
• Reinforcement Learning of Control Strategies for Reducing Skin Friction Drag in a Fully Developed Channel Flow
• Constructing coarse-scale bifurcation diagrams from spatio-temporal observations of microscopic simulations: A parsimonious machine learning approach
• Deep Learning Closure Models for Large-Eddy Simulation of Flows around Bluff Bodies
• From snapshots to manifolds - A tale of shear flows
• Linking Gaussian Process regression with data-driven manifold embeddings for nonlinear data fusion
• Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network
• Double Diffusion Maps and their Latent Harmonics for Scientific Computations in Latent Space
• From partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonics
• Black and Gray Box Learning of Amplitude Equations: Application to Phase Field Systems
• Efficient prediction of turbulent flow quantities using a Bayesian hierarchical multifidelity model
• A Discrete Droplet Method for Modelling Thin Film Flows
• Particles to Partial Differential Equations Parsimoniously

Cited by in corpus (3)

• Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy
• Integrating supervised and unsupervised learning approaches to unveil critical process inputs
• Learning the Latent dynamics of Fluid flows from High-Fidelity Numerical Simulations using Parsimonious Diffusion Maps