Deep neural networks for nonlinear model order reduction of unsteady flows

H Eivazi, H Veisi, MH Naderi, V Esfahanian - Physics of Fluids, 2020 - pubs.aip.org
Unsteady fluid systems are nonlinear high-dimensional dynamical systems that may exhibit
multiple complex phenomena in both time and space. Reduced Order Modeling (ROM) of …

[HTML][HTML] An AI-based non-intrusive reduced-order model for extended domains applied to multiphase flow in pipes

CE Heaney, Z Wolffs, JA Tómasson, L Kahouadji… - Physics of …, 2022 - pubs.aip.org
The modeling of multiphase flow in a pipe presents a significant challenge for high-
resolution computational fluid dynamics (CFD) models due to the high aspect ratio (length …

[HTML][HTML] Model fusion with physics-guided machine learning: Projection-based reduced-order modeling

S Pawar, O San, A Nair, A Rasheed, T Kvamsdal - Physics of Fluids, 2021 - pubs.aip.org
The unprecedented amount of data generated from experiments, field observations, and
large-scale numerical simulations at a wide range of spatiotemporal scales has enabled the …

Physics-guided deep learning framework for predictive modeling of bridge vortex-induced vibrations from field monitoring

S Li, S Laima, H Li - Physics of Fluids, 2021 - pubs.aip.org
Vortex-induced vibrations (VIVs) with large amplitudes have been observed on long-span
bridges worldwide. Classic semi-empirical VIV models that depend on wind tunnel tests are …

Fast estimation of internal flowfields in scramjet intakes via reduced-order modeling and machine learning

S Brahmachary, A Bhagyarajan, H Ogawa - Physics of Fluids, 2021 - pubs.aip.org
The interface between fluid mechanics and machine learning has ushered in a new avenue
of scientific inquiry for complex fluid flow problems. This paper presents the development of …

Accurate storm surge forecasting using the encoder–decoder long short term memory recurrent neural network

LH Bai, H Xu - Physics of Fluids, 2022 - pubs.aip.org
The encoder–decoder LSTM (long short term memory) recurrent neural network is proposed
to predict storm surge in Florida. Two types of hurricanes with six events are collected for …

[HTML][HTML] Machine learning and physics-driven modelling and simulation of multiphase systems

N Basha, R Arcucci, P Angeli, C Anastasiou… - International Journal of …, 2024 - Elsevier
We highlight the work of a multi-university collaborative programme, PREMIERE (PREdictive
Modelling with QuantIfication of UncERtainty for MultiphasE Systems), which is at the …

Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation

R Maulik, T Botsas, N Ramachandra, LR Mason… - Physica D: Nonlinear …, 2021 - Elsevier
Non-intrusive reduced-order models (ROMs) have recently generated considerable interest
for constructing computationally efficient counterparts of nonlinear dynamical systems …

Reduced order modeling using advection-aware autoencoders

S Dutta, P Rivera-Casillas, B Styles… - Mathematical and …, 2022 - mdpi.com
Physical systems governed by advection-dominated partial differential equations (PDEs) are
found in applications ranging from engineering design to weather forecasting. They are …

Deploying deep learning in OpenFOAM with TensorFlow

R Maulik, H Sharma, S Patel, B Lusch… - AIAA Scitech 2021 …, 2021 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2021-1485. vid We outline the
development of a data science module within OpenFOAM which allows for the in-situ …