activity
20182022
most citedOn closures for reduced order models A spectrum of first-principle to machine-learned avenues

147 citations · 639 across the 19 of their papers we have counts for

collaborators
Showing physics.flu-dynShow all

7 papers · 1 filter

physics.flu-dyn2022

Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling

Shady E. Ahmed, Omer San, Adil Rasheed +2

We propose a new physics guided machine learning (PGML) paradigm that leverages the variational multiscale (VMS) framework and available data to dramatically increase the accuracy…

physics.flu-dyn2021

Multi-fidelity information fusion with concatenated neural networks

Suraj Pawar, Omer San, Prakash Vedula +2

Recently, computational modeling has shifted towards the use of deep learning, and other data-driven modeling frameworks. Although this shift in modeling holds promise in many appl…

physics.flu-dyn2021147 cited

On closures for reduced order models A spectrum of first-principle to machine-learned avenues

Shady E. Ahmed, Suraj Pawar, Omer San +3

For over a century, reduced order models (ROMs) have been a fundamental discipline of theoretical fluid mechanics. Early examples include Galerkin models inspired by the Orr-Sommer…

physics.flu-dyn2019

A long short-term memory embedding for hybrid uplifted reduced order models

Shady E. Ahmed, Omer San, Adil Rasheed +1

In this paper, we introduce an uplifted reduced order modeling (UROM) approach through the integration of standard projection based methods with long short-term memory (LSTM) embed…

physics.flu-dyn201957 cited

Memory embedded non-intrusive reduced order modeling of non-ergodic flows

Shady E. Ahmed, Sk. Mashfiqur Rahman, Omer San +2

Generating a digital twin of any complex system requires modeling and computational approaches that are efficient, accurate, and modular. Traditional reduced order modeling techniq…

physics.flu-dyn2018

Data-driven deconvolution for large eddy simulations of Kraichnan turbulence

Romit Maulik, Omer San, Adil Rasheed +1

In this article, we demonstrate the use of artificial neural networks as optimal maps which are utilized for convolution and deconvolution of coarse-grained fields to account for s…