Reduced-order modeling of unsteady fluid flow using neural network ensembles

Abstract

The use of deep learning has become increasingly popular in reduced-order models (ROMs) to obtain low-dimensional representations of full-order models. Convolutional autoencoders (CAEs) are often used to this end as they are adept at handling data that are spatially distributed, including solutions to partial differential equations. When applied to unsteady physics problems, ROMs also require a model for time-series prediction of the low-dimensional latent variables. Long short-term memory (LSTM) networks, a type of recurrent neural network useful for modeling sequential data, are frequently employed in data-driven ROMs for autoregressive time-series prediction. When making predictions at unseen design points over long time horizons, error propagation is a frequently encountered issue, where errors made early on can compound over time and lead to large inaccuracies. In this work, we propose using bagging, a commonly used ensemble learning technique, to develop a fully data-driven ROM framework referred to as the CAE-eLSTM ROM that uses CAEs for spatial reconstruction of the full-order model and LSTM ensembles for time-series prediction. When applied to two unsteady fluid dynamics problems, our results show that the presented framework effectively reduces error propagation and leads to more accurate time-series prediction of latent variables at unseen points.

Updated with revisions

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Enhancing Computational Fluid Dynamics with Machine Learning
• Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning
• Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
• Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• On the stability of projection-based model order reduction for convection-dominated laminar and turbulent flows
• A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
• Residual-based physics-informed transfer learning: A hybrid method for accelerating long-term CFD simulations via deep learning
• XLB: A differentiable massively parallel lattice Boltzmann library in Python