Comparing theory based and higher-order reduced models for fusion simulation data

E. Bernholdt, David; R. Ciancosa, Mark; L. Green, David; J.H. Law, Kody; Litvinenko, Alexander; M. Park, Jin

doi:10.3934/BigDIA.2018.2.41

Title: Comparing theory based and higher-order reduced models for fusion simulation data

Abstract

We consider using regression to fit a theory-based log-linear ansatz, as well as higher order approximations, for the thermal energy confinement of a Tokamak as a function of device features. We use general linear models based on total order polynomials, as well as deep neural networks. The results indicate that the theory-based model fits the data almost as well as the more sophisticated machines, within the support of the data set. The conclusion we arrive at is that only negligible improvements can be made to the theoretical model, for input data of this type.

Authors:

E. Bernholdt, David ^[1]; R. Ciancosa, Mark ^[1]; L. Green, David ^[1]; J.H. Law, Kody ^[2]; Litvinenko, Alexander ^[3]; M. Park, Jin ^[4]

Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Univ. of Manchester (United Kingdom)
King Abdullah Univ. of Science and Technology, Thuwal (Saudi Arabia)
General Atomics, San Diego, CA (United States)

Publication Date:: 2018-12-06

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1486929

Grant/Contract Number:: AC05-00OR22725

Resource Type:: Accepted Manuscript

Journal Name:: Big Data and Information Analytics (Online)

Additional Journal Information:: Journal Name: Big Data and Information Analytics (Online); Journal Volume: 3; Journal Issue: 2; Journal ID: ISSN 2380-6974

Publisher:: AIMS Press

Country of Publication:: United States

Language:: English

Subject:: 70 PLASMA PHYSICS AND FUSION TECHNOLOGY; 97 MATHEMATICS AND COMPUTING

Citation Formats


                    E. Bernholdt, David, R. Ciancosa, Mark, L. Green, David, J.H. Law, Kody, Litvinenko, Alexander, and M. Park, Jin. Comparing theory based and higher-order reduced models for fusion simulation data.  United States: N. p., 2018. 
Web.  doi:10.3934/BigDIA.2018.2.41.

Copy to clipboard


                    E. Bernholdt, David, R. Ciancosa, Mark, L. Green, David, J.H. Law, Kody, Litvinenko, Alexander, & M. Park, Jin. Comparing theory based and higher-order reduced models for fusion simulation data.  United States.  https://doi.org/10.3934/BigDIA.2018.2.41

Copy to clipboard


                    E. Bernholdt, David, R. Ciancosa, Mark, L. Green, David, J.H. Law, Kody, Litvinenko, Alexander, and M. Park, Jin. Thu .  
"Comparing theory based and higher-order reduced models for fusion simulation data".  United States.  https://doi.org/10.3934/BigDIA.2018.2.41.  https://www.osti.gov/servlets/purl/1486929.

Copy to clipboard


                    
@article{osti_1486929,

  title        = {Comparing theory based and higher-order reduced models for fusion simulation data},

  author       = {E. Bernholdt, David and R. Ciancosa, Mark and L. Green, David and J.H. Law, Kody and Litvinenko, Alexander and M. Park, Jin},

  abstractNote = {We consider using regression to fit a theory-based log-linear ansatz, as well as higher order approximations, for the thermal energy confinement of a Tokamak as a function of device features. We use general linear models based on total order polynomials, as well as deep neural networks. The results indicate that the theory-based model fits the data almost as well as the more sophisticated machines, within the support of the data set. The conclusion we arrive at is that only negligible improvements can be made to the theoretical model, for input data of this type.},

  doi          = {10.3934/BigDIA.2018.2.41},

  journal      = {Big Data and Information Analytics (Online)},

  number       = 2,

  volume       = 3,

  place        = {United States},

  year         = {2018},

  month        = {12}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.3934/BigDIA.2018.2.41

Other availability

Search WorldCat to find libraries that may hold this journal

Figures / Tables:

Figure 1: Comparison of true values with GLM prediction, for log linear (left), and log sixth order (right). The right subplots show the error distribution histogram (difference between values of the truth and the prediction). Out-of-sample, test data.

All figures and tables (7 total)

Save / Share:

Export Metadata

Save to My Library

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

Regression-based reduced-order models to predict transient thermal output for enhanced geothermal systems

Journal Article Mudunuru, Maruti Kumar ; Karra, Satish ; Harp, Dylan Robert ; ... - Geothermics

Reduced-order modeling is a promising approach, as many phenomena can be described by a few parameters/mechanisms. An advantage and attractive aspect of a reduced-order model is that it is computational inexpensive to evaluate when compared to running a high-fidelity numerical simulation. A reduced-order model takes couple of seconds to run on a laptop while a high-fidelity simulation may take couple of hours to run on a high-performance computing cluster. The goal of this paper is to assess the utility of regression-based reduced-order models (ROMs) developed from high-fidelity numerical simulations for predicting transient thermal power output for an enhanced geothermal reservoirmore »« less
Cited by 13
https://doi.org/10.1016/j.geothermics.2017.06.013

Full Text Available
Model fusion with physics-guided machine learning: Projection-based reduced-order modeling

Journal Article Pawar, Suraj ; San, Omer ; Nair, Aditya ; ... - Physics of Fluids

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 rapid advancement of data-driven and especially deep learning models in the field of fluid mechanics. Although these methods are proven successful for many applications, there is a grand challenge of improving their generalizability. This is particularly essential when data-driven models are employed within outer-loop applications like optimization. In this work, we put forth a physics-guided machine learning (PGML) framework that leverages the interpretable physics-based model with a deep learning model. Leveraging a concatenated neural network designmore »« less
https://doi.org/10.1063/5.0053349

Full Text Available
Reduced-Order Model for the Geochemical Impacts of Carbon Dioxide, Brine and Trace Metal Leakage into an Unconfined, Oxidizing Carbonate Aquifer, Version 2.1

Technical Report Bacon, Diana H.

The National Risk Assessment Partnership (NRAP) consists of 5 U.S DOE national laboratories collaborating to develop a framework for predicting the risks associated with carbon sequestration. The approach taken by NRAP is to divide the system into components, including injection target reservoirs, wellbores, natural pathways including faults and fractures, groundwater and the atmosphere. Next, develop a detailed, physics and chemistry-based model of each component. Using the results of the detailed models, develop efficient, simplified models, termed reduced order models (ROM) for each component. Finally, integrate the component ROMs into a system model that calculates risk profiles for the site. Thismore »« less
https://doi.org/10.2172/1166688

Full Text Available
An Evolve-Then-Correct Reduced Order Model for Hidden Fluid Dynamics

Journal Article Pawar, Suraj ; Ahmed, Shady E. ; San, Omer ; ... - Mathematics

In this paper, we put forth an evolve-then-correct reduced order modeling approach that combines intrusive and nonintrusive models to take hidden physical processes into account. Specifically, we split the underlying dynamics into known and unknown components. In the known part, we first utilize an intrusive Galerkin method projected on a set of basis functions obtained by proper orthogonal decomposition. We then present two variants of correction formula based on the assumption that the observed data are a manifestation of all relevant processes. The first method uses a standard least-squares regression with a quadratic approximation and requires solving a rank-deficient linearmore »« less
https://doi.org/10.3390/math8040570

Full Text Available
A simplified regression building thermal modelling method for detached two-floor house in U.S.

Conference Cui, Borui ; Dong, Jin ; Munk, Jeffrey D. ; ...

The residential building sector accounts for approximately 37% of total U.S. electricity consumption. Within the residential building sector, heating and cooling is the main target for peak load shifting/reduction since it is the largest contributor to peak demand. In fact, the flexibility of residential HVAC loads can provide continuous variation of demand to provide grid services by varying their demand over a baseline. The performance of HVAC load control to provide grid services relies heavily on the accuracy of indoor air temperature or cooling/heating demand predictions and therefore the quality of building model. Besides forward models, popular building models aremore »« less
Full Text Available

Similar Records