A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Deep-learning enhancement of large scale numerical simulations
[article]
2020
arXiv
pre-print
Recently deep learning has been employed to enhance solving problems that traditionally are solved with large-scale numerical simulations using HPC. ...
Our goal is to provide concrete guidelines to scientists and others that would like to explore opportunities for applying deep learning approaches in their own large-scale numerical simulations. ...
Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," NIPS, 2012. ...
arXiv:2004.03454v1
fatcat:l4vs2ham6ngdjdvio66uieb5my
The Potential of Machine Learning to Enhance Computational Fluid Dynamics
[article]
2021
arXiv
pre-print
This paper highlights some of the areas of highest potential impact, including to accelerate direct numerical simulations, to improve turbulence closure modelling, and to develop enhanced reduced-order ...
Machine learning is rapidly becoming a core technology for scientific computing, with numerous opportunities to advance the field of computational fluid dynamics. ...
areas where machine learning can enhance CFD, in the context of direct numerical simulations, turbulence modelling and reduced-order models. ...
arXiv:2110.02085v1
fatcat:fu4b2dym6bd53ihnpqprdpwefu
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
[article]
2020
arXiv
pre-print
In this paper, we aim to predict turbulent flow by learning its highly nonlinear dynamics from spatiotemporal velocity fields of large-scale fluid flow simulations of relevance to turbulence modeling and ...
We adopt a hybrid approach by marrying two well-established turbulent flow simulation techniques with deep learning. ...
ACKNOWLEDGEMENT This research used resources of the National Energy Research Scientific Computing Center, a DOE Office of Science User Facility supported by the Office of Science of the U.S. ...
arXiv:1911.08655v4
fatcat:qnjvnynhbja6rjhcmrx77r3jfu
Combining high performance hardware, cloud computing, and deep learning frameworks to accelerate physical simulations: probing the Hopfield Network
2020
European journal of physics
We then introduce the Hopfield Network and explain how to produce large-scale simulations & visualizations for free in the cloud with very little code (fully self-contained in the text). ...
The synthesis of high performance computing (particularly Graphics Processing Units), cloud computing services (like Google Colab), and high-level deep learning frameworks (such as PyTorch) has powered ...
CONCLUSION In this tutorial, we have suggested the use of cloud computing, GPUs, and deep learning frameworks to accelerate large-scale physical simulations and make high performance computing accessible ...
doi:10.1088/1361-6404/ab7027
fatcat:rersmx6jt5gzjfmhafuzroydju
Message from the Workshop Chairs
2019
2019 IEEE/ACM 1st Annual Workshop on Large-scale Experiment-in-the-Loop Computing (XLOOP)
and deep space; advanced machine learning techniques automate parts of the scientific workflow. ...
This is an exciting time for large-scale experimental science-physics experiments are being scaled up in energy and resolution; new and higher quality images are available for the observation of earth ...
When coupled, these emerging infrastructure realities create a powerful new approachexperiment-in-the-loop computing (EILC), in which large-scale computer simulations and learning models assimilate observed ...
doi:10.1109/xloop49562.2019.00004
fatcat:hemdlfyskbda3jcsrzkmihrtsa
Knowledge-Enhanced Deep Learning for Simulation of Extratropical Cyclone Wind Risk
2022
Atmosphere
To this end, a knowledge-enhanced deep learning (KEDL) is developed in this study to estimate the ETC boundary-layer winds over eastern North America. ...
the deep neural network. ...
Booth for providing the synthetic track database for the ETC risk simulation.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/atmos13050757
fatcat:hmrjf5jdtfhbha3z6zphk7eeae
Prospective Interest of Deep Learning for Hydrological Inference
2017
Ground Water
Deep learning can find robust invariants from large, high dimensional datasets, leading to improved interpolation and generalization (Hinton and Salakhutdinov 2006) . ...
Among numerous methods, supervised-learning algorithms and, especially, artificial neural networks became popular in the 90s in hydrology. ...
doi:10.1111/gwat.12557
pmid:28732108
fatcat:jl6wpwcu4zhw7duksfrnqvl52u
A data-driven proxy to Stoke's flow in porous media
[article]
2019
arXiv
pre-print
The developed model can truly capture the physics of the problem and enhance prediction capabilities of the simulations at a much lower cost. ...
The proposed model can capture the flow field and permeability in a large verity of digital porous media based on solid grain geometry and pore size distribution by detailed analyses of the local pore ...
Recently, there have been numerous studies on application of machine learning machine learning (ML) in CFD, most of which are limited to building interpretable reduced order models (ROMs). ...
arXiv:1905.06327v1
fatcat:lls72jxa4zbm5d4f7bdzu6wzee
A Physics-Informed Vector Quantized Autoencoder for Data Compression of Turbulent Flow
[article]
2022
arXiv
pre-print
Analyzing large-scale data from simulations of turbulent flows is memory intensive, requiring significant resources. This major challenge highlights the need for data compression techniques. ...
In this study, we apply a physics-informed Deep Learning technique based on vector quantization to generate a discrete, low-dimensional representation of data from simulations of three-dimensional turbulent ...
Numerical Simulation (DNS). ...
arXiv:2201.03617v2
fatcat:lrvpob632jbjvhf735b2jtzsse
Prediction of laminar vortex shedding over a cylinder using deep learning
[article]
2017
arXiv
pre-print
The present study suggests that a deep learning technique can be utilized for prediction of laminar wake flow in lieu of solving the Navier-Stokes equations. ...
Numerical simulations at two different Reynolds numbers with different time-step sizes are conducted to produce training datasets of flow field variables. ...
Those previous studies showed high potential of deep learning techniques for enhancing simulation accuracy and reducing computational costs. ...
arXiv:1712.07854v1
fatcat:estqh4wjsrhabaoxh4lb4suu2u
Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
[article]
2021
arXiv
pre-print
The combination of graphics processing units, deep learning, and the availability of open source, high-quality datasets, have powered the rise of artificial intelligence. ...
In tandem with the advent of large-scale scientific facilities, the last decade has experienced an unprecedented transformation in computing and signal processing algorithms. ...
numerically simulate multi-scale and multi-physics processes, such as neutron star mergers [30] . ...
arXiv:2105.06479v1
fatcat:6kmobkx7ojgsfi3isc6i6bhlui
SpiNNaker 2: A 10 Million Core Processor System for Brain Simulation and Machine Learning
[article]
2019
arXiv
pre-print
Additional numerical accelerators will enhance the utility of SpiNNaker2 for simulation of spiking neural networks as well as for executing conventional deep neural networks. ...
Power management of the cores allows a wide range of workload adaptivity, i.e. processor power scales with the complexity and activity of the spiking network. ...
In addition to the above four main development lines, multiply accumulate arrays (MAC) have been incorporated in the latest prototype chip to enhance the usefulness of SpiNNaker2 beyond simulation of spiking ...
arXiv:1911.02385v1
fatcat:inhdg4fyybg4ro2hehx525aodu
Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations
[article]
2020
arXiv
pre-print
We introduce a machine learning (ML) technique based on a deep neural network architecture that corrects the numerical errors induced by a coarse-grid simulation of turbulent flows at high-Reynolds numbers ...
Direct Numerical Simulation (DNS) of the Navier-Stokes equations with sufficient numerical resolution to capture all the relevant scales of the turbulent motions can be prohibitively expensive. ...
This research used resources of the National ...
arXiv:2010.00072v2
fatcat:zw7c2cr6xrg2rdjqf5hf5vchr4
Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data
[article]
2021
arXiv
pre-print
Within the domain of Computational Fluid Dynamics, Direct Numerical Simulation (DNS) is used to obtain highly accurate numerical solutions for fluid flows. ...
Thus our implementation improves the solution accuracy of LR solutions while incurring only a marginal increase in computational cost required for deploying the trained deep learning model. ...
Introduction Direct Numerical Simulation (DNS) is a highly accurate but expensive method for computationally solving the Navier-Stokes equations. ...
arXiv:2010.11348v2
fatcat:may6m754qrcbto3nr3jgzg732i
Message from the Workshop Chairs
2020
2020 IEEE/ACM 2nd Annual Workshop on Extreme-scale Experiment-in-the-Loop Computing (XLOOP)
and deep space; advanced machine learning techniques automate parts of the scientific workflow. ...
This is an exciting time for large-scale experimental science-physics experiments are being scaled up in energy and resolution; new and higher quality images are available for the observation of earth ...
When coupled, these emerging infrastructure realities create a powerful new approachexperiment-in-the-loop computing (EILC), in which large-scale computer simulations and learning models assimilate observed ...
doi:10.1109/xloop51963.2020.00004
fatcat:4ntdnzlwlzdtvkwshcs7i3iv6u
« Previous
Showing results 1 — 15 out of 73,414 results