[PDF][PDF] Integrating physics-based modeling with machine learning: A survey

J Willard, X Jia, S Xu, M Steinbach… - arXiv preprint arXiv …, 2020 - beiyulincs.github.io
There is a growing consensus that solutions to complex science and engineering problems
require novel methodologies that are able to integrate traditional physics-based modeling …

[HTML][HTML] Forecasting global climate drivers using Gaussian processes and convolutional autoencoders

J Donnelly, A Daneshkhah, S Abolfathi - Engineering Applications of …, 2024 - Elsevier
Abstract Machine learning (ML) methods have become an important tool for modelling and
forecasting complex high-dimensional spatiotemporal datasets such as those found in …

[HTML][HTML] Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders

R Maulik, B Lusch, P Balaprakash - Physics of Fluids, 2021 - pubs.aip.org
A common strategy for the dimensionality reduction of nonlinear partial differential equations
(PDEs) relies on the use of the proper orthogonal decomposition (POD) to identify a reduced …

Stiff neural ordinary differential equations

S Kim, W Ji, S Deng, Y Ma… - Chaos: An Interdisciplinary …, 2021 - pubs.aip.org
ABSTRACT Neural Ordinary Differential Equations (ODEs) are a promising approach to
learn dynamical models from time-series data in science and engineering applications. This …

Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow

T Nakamura, K Fukami, K Hasegawa, Y Nabae… - Physics of …, 2021 - pubs.aip.org
We investigate the applicability of the machine learning based reduced order model (ML-
ROM) to three-dimensional complex flows. As an example, we consider a turbulent channel …

Assessment of supervised machine learning methods for fluid flows

K Fukami, K Fukagata, K Taira - Theoretical and Computational Fluid …, 2020 - Springer
We apply supervised machine learning techniques to a number of regression problems in
fluid dynamics. Four machine learning architectures are examined in terms of their …

Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data

K Fukami, T Nakamura, K Fukagata - Physics of Fluids, 2020 - pubs.aip.org
We propose a customized convolutional neural network based autoencoder called a
hierarchical autoencoder, which allows us to extract nonlinear autoencoder modes of flow …

Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics

J Xu, K Duraisamy - Computer Methods in Applied Mechanics and …, 2020 - Elsevier
A data-driven framework is proposed towards the end of predictive modeling of complex
spatio-temporal dynamics, leveraging nested non-linear manifolds. Three levels of neural …

Data-driven discovery of intrinsic dynamics

D Floryan, MD Graham - Nature Machine Intelligence, 2022 - nature.com
Dynamical models underpin our ability to understand and predict the behaviour of natural
systems. Whether dynamical models are developed from first-principles derivations or from …

Multi-scale simulation of complex systems: a perspective of integrating knowledge and data

H Wang, H Yan, C Rong, Y Yuan, F Jiang… - ACM Computing …, 2024 - dl.acm.org
Complex system simulation has been playing an irreplaceable role in understanding,
predicting, and controlling diverse complex systems. In the past few decades, the multi-scale …