Enabling Immersive Engagement in Energy System Models with Deep Learning

Brian Bush; Kenny Gruchalla; Kristin Potter; Nicholas Brunhart-Lupo; Venkat Krishnan; Bruce Bugbee

doi:10.1002/sam.11419

Enabling Immersive Engagement in Energy System Models with Deep Learning

Brian Bush, Kenny Gruchalla, Kristin Potter, Nicholas Brunhart-Lupo, Venkat Krishnan, Bruce Bugbee

Research output: Contribution to journal › Article › peer-review

8 Scopus Citations

Abstract

Complex ensembles of energy simulation models have become significant components of renewable energy research in recent years. Often the significant computational cost, high-dimensional structure, and other complexities hinder researchers from fully utilizing these data sources for knowledge building. Researchers at National Renewable Energy Laboratory have developed an immersive visualization workflow to dramatically improve user engagement and analysis capability through a combination of low-dimensional structure analysis, deep learning, and custom visualization methods. We present case studies for two energy simulation platforms.

Original language	American English
Pages (from-to)	325-337
Number of pages	13
Journal	Statistical Analysis and Data Mining
Volume	12
Issue number	4
DOIs	https://doi.org/10.1002/sam.11419 https://doi.org/10.1002/sam.11419
State	Published - 2019

Bibliographical note

Publisher Copyright:
© 2019 The Authors. Statistical Analysis and Data Mining: The ASA Data Science Journal published by Wiley Periodicals, Inc.

NREL Publication Number

NREL/JA-6A20-73878

Keywords

high-dimensional data
interactive visualization
neural networks
renewable energy
t-SNE
Tucker decomposition

Access to Document

https://www.nrel.gov/docs/fy19osti/73878.pdf

Cite this

@article{9fee7f1a362340b8a1d34003e066f1ac,

title = "Enabling Immersive Engagement in Energy System Models with Deep Learning",

abstract = "Complex ensembles of energy simulation models have become significant components of renewable energy research in recent years. Often the significant computational cost, high-dimensional structure, and other complexities hinder researchers from fully utilizing these data sources for knowledge building. Researchers at National Renewable Energy Laboratory have developed an immersive visualization workflow to dramatically improve user engagement and analysis capability through a combination of low-dimensional structure analysis, deep learning, and custom visualization methods. We present case studies for two energy simulation platforms.",

keywords = "high-dimensional data, interactive visualization, neural networks, renewable energy, t-SNE, Tucker decomposition",

author = "Brian Bush and Kenny Gruchalla and Kristin Potter and Nicholas Brunhart-Lupo and Venkat Krishnan and Bruce Bugbee",

note = "Publisher Copyright: {\textcopyright} 2019 The Authors. Statistical Analysis and Data Mining: The ASA Data Science Journal published by Wiley Periodicals, Inc.",

year = "2019",

doi = "10.1002/sam.11419",

language = "American English",

volume = "12",

pages = "325--337",

journal = "Statistical Analysis and Data Mining",

issn = "1932-1864",

publisher = "John Wiley and Sons Inc.",

number = "4",

}

TY - JOUR

T1 - Enabling Immersive Engagement in Energy System Models with Deep Learning

AU - Bush, Brian

AU - Gruchalla, Kenny

AU - Potter, Kristin

AU - Brunhart-Lupo, Nicholas

AU - Krishnan, Venkat

AU - Bugbee, Bruce

PY - 2019

Y1 - 2019

N2 - Complex ensembles of energy simulation models have become significant components of renewable energy research in recent years. Often the significant computational cost, high-dimensional structure, and other complexities hinder researchers from fully utilizing these data sources for knowledge building. Researchers at National Renewable Energy Laboratory have developed an immersive visualization workflow to dramatically improve user engagement and analysis capability through a combination of low-dimensional structure analysis, deep learning, and custom visualization methods. We present case studies for two energy simulation platforms.

AB - Complex ensembles of energy simulation models have become significant components of renewable energy research in recent years. Often the significant computational cost, high-dimensional structure, and other complexities hinder researchers from fully utilizing these data sources for knowledge building. Researchers at National Renewable Energy Laboratory have developed an immersive visualization workflow to dramatically improve user engagement and analysis capability through a combination of low-dimensional structure analysis, deep learning, and custom visualization methods. We present case studies for two energy simulation platforms.

KW - high-dimensional data

KW - interactive visualization

KW - neural networks

KW - renewable energy

KW - t-SNE

KW - Tucker decomposition

UR - http://www.scopus.com/inward/record.url?scp=85067673807&partnerID=8YFLogxK

U2 - 10.1002/sam.11419

DO - 10.1002/sam.11419

M3 - Article

AN - SCOPUS:85067673807

SN - 1932-1864

VL - 12

SP - 325

EP - 337

JO - Statistical Analysis and Data Mining

JF - Statistical Analysis and Data Mining

IS - 4

ER -

Enabling Immersive Engagement in Energy System Models with Deep Learning

Abstract

Bibliographical note

NREL Publication Number

Keywords

Access to Document

Other files and links

Fingerprint

Cite this