Multiphase flow applications of nonintrusive reduced-order models with Gaussian process emulation

• Published in: Data-Centric Engineering (Online) Vol. 3
• Main Authors: Botsas, Themistoklis, Pan, Indranil, Mason, Lachlan R., Matar, Omar K.
• Format: Journal Article
• Language: English
• Published: Cambridge Cambridge University Press 01.01.2022
• Subjects: Algorithms; Autoencoders; Computational fluid dynamics; deep Gaussian process; Gaussian process; Generalized linear models; Initial conditions; Interpolation; Machine learning; Multiphase flow; Neural networks; Parameter estimation; Partial differential equations; Principal components analysis; Reduced order models; Simulation
• ISSN: 2632-6736; 2632-6736
• DOI: 10.1017/dce.2022.19

Abstract Reduced-order models (ROMs) are computationally inexpensive simplifications of high-fidelity complex ones. Such models can be found in computational fluid dynamics where they can be used to predict the characteristics of multiphase flows. In previous work, we presented a ROM analysis framework that coupled compression techniques, such as autoencoders, with Gaussian process regression in the latent space. This pairing has significant advantages over the standard encoding–decoding routine, such as the ability to interpolate or extrapolate in the initial conditions’ space, which can provide predictions even when simulation data are not available. In this work, we focus on this major advantage and show its effectiveness by performing the pipeline on three multiphase flow applications. We also extend the methodology by using deep Gaussian processes as the interpolation algorithm and compare the performance of our two variations, as well as another variation from the literature that uses long short-term memory networks, for the interpolation.