835 citations · 3.7k across the 23 of their papers we have counts for
20 papers · 1 filter
Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
Kai Fukami, Koji Fukagata, Kunihiko Taira
This paper surveys machine-learning-based super-resolution reconstruction for vortical flows. Super resolution aims to find the high-resolution flow fields from low-resolution data…
Robust training approach of neural networks for fluid flow state estimations
Taichi Nakamura, Koji Fukagata
State estimation from limited sensor measurements is ubiquitously found as a common challenge in a broad range of fields including mechanics, astronomy, and geophysics. Fluid mecha…
Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
Masaki Morimoto, Kai Fukami, Romit Maulik +2
We use Gaussian stochastic weight averaging (SWAG) to assess the model-form uncertainty associated with neural-network-based function approximation relevant to fluid flows. SWAG ap…
Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
Naoki Moriya, Kai Fukami, Yusuke Nabae +3
We propose a supervised-machine-learning-based wall model for coarse-grid wall-resolved large-eddy simulation (LES). Our consideration is made on LES of turbulent channel flows wit…
Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
Taichi Nakamura, Kai Fukami, Koji Fukagata
Neural networks (NNs) and linear stochastic estimation (LSE) have widely been utilized as powerful tools for fluid-flow regressions. We investigate fundamental differences between…
Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
Mitsuaki Matsuo, Kai Fukami, Taichi Nakamura +2
The recent development of high-performance computing enables us to generate spatio-temporal high-resolution data of nonlinear dynamical systems and to analyze them for a deeper und…
Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
Masaki Morimoto, Kai Fukami, Kai Zhang +2
We focus on a convolutional neural network (CNN), which has recently been utilized for fluid flow analyses, from the perspective on the influence of various operations inside it by…
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
Kai Fukami, Romit Maulik, Nesar Ramachandra +2
Achieving accurate and robust global situational awareness of a complex time-evolving field from a limited number of sensors has been a longstanding challenge. This reconstruction…
Probabilistic neural network-based reduced-order surrogate for fluid flows
Kai Fukami, Romit Maulik, Nesar Ramachandra +2
In recent years, there have been a surge in applications of neural networks (NNs) in physical sciences. Although various algorithmic advances have been proposed, there are, thus fa…
Generalization techniques of neural networks for fluid flow estimation
Masaki Morimoto, Kai Fukami, Kai Zhang +1
We demonstrate several techniques to encourage practical uses of neural networks for fluid flow estimation. In the present paper, three perspectives which are remaining challenges…
Model order reduction with neural networks: Application to laminar and turbulent flows
Kai Fukami, Kazuto Hasegawa, Taichi Nakamura +2
We investigate the capability of neural network-based model order reduction, i.e., autoencoder (AE), for fluid flows. As an example model, an AE which comprises of a convolutional…
Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
Taichi Nakamura, Kai Fukami, Kazuto Hasegawa +2
We investigate the applicability of machine learning based reduced order model (ML-ROM) to three-dimensional complex flows. As an example, we consider a turbulent channel flow at t…
Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
Kai Fukami, Takaaki Murata, Kai Zhang +1
We perform a sparse identification of nonlinear dynamics (SINDy) for low-dimensionalized complex flow phenomena. We first apply the SINDy with two regression methods, the threshold…
Probabilistic neural networks for fluid flow surrogate modeling and data recovery
Romit Maulik, Kai Fukami, Nesar Ramachandra +2
We consider the use of probabilistic neural networks for fluid flow {surrogate modeling} and data recovery. This framework is constructed by assuming that the target variables are…
Experimental velocity data estimation for imperfect particle images using machine learning
Masaki Morimoto, Kai Fukami, Koji Fukagata
We propose a method using supervised machine learning to estimate velocity fields from particle images having missing regions due to experimental limitations. As a first example, a…
Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
Kai Fukami, Koji Fukagata, Kunihiko Taira
We present a new turbulent data reconstruction method with supervised machine learning techniques inspired by super resolution and inbetweening, which can recover high-resolution t…
Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
Kazuto Hasegawa, Kai Fukami, Takaaki Murata +1
We propose a method to construct a reduced order model with machine learning for unsteady flows. The present machine-learned reduced order model (ML-ROM) is constructed by combinin…
Assessment of supervised machine learning methods for fluid flows
Kai Fukami, Koji Fukagata, Kunihiko Taira
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 characteris…
Super-resolution reconstruction of turbulent flows with machine learning
Kai Fukami, Koji Fukagata, Kunihiko Taira
We use machine learning to perform super-resolution analysis of grossly under-resolved turbulent flow field data to reconstruct the high-resolution flow field. Two machine-learning…
Synthetic turbulent inflow generator using machine learning
Kai Fukami, Yusuke Nabae, Ken Kawai +1
We propose a methodology for generating time-dependent turbulent inflow data with the aid of machine learning (ML), which has a possibility to replace conventional driver simulatio…