skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine learning of optical properties of materials – predicting spectra from images and images from spectra

Abstract

Assembling the world's largest materials image and spectroscopy dataset enables training of machine learning models that learn hidden relationships in materials data, providing a key example of the data requirements to capitalize on recent advancements in computer science.

Authors:
ORCiD logo [1];  [1];  [1];  [1]; ORCiD logo [1]
  1. Joint Center for Artificial Photosynthesis, California Institute of Technology, Pasadena, USA
Publication Date:
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
OSTI Identifier:
1480874
Grant/Contract Number:  
SC0004993
Resource Type:
Journal Article: Published Article
Journal Name:
Chemical Science
Additional Journal Information:
Journal Name: Chemical Science; Journal ID: ISSN 2041-6520
Publisher:
Royal Society of Chemistry (RSC)
Country of Publication:
United Kingdom
Language:
English

Citation Formats

Stein, Helge S., Guevarra, Dan, Newhouse, Paul F., Soedarmadji, Edwin, and Gregoire, John M. Machine learning of optical properties of materials – predicting spectra from images and images from spectra. United Kingdom: N. p., 2019. Web. doi:10.1039/C8SC03077D.
Stein, Helge S., Guevarra, Dan, Newhouse, Paul F., Soedarmadji, Edwin, & Gregoire, John M. Machine learning of optical properties of materials – predicting spectra from images and images from spectra. United Kingdom. doi:10.1039/C8SC03077D.
Stein, Helge S., Guevarra, Dan, Newhouse, Paul F., Soedarmadji, Edwin, and Gregoire, John M. Tue . "Machine learning of optical properties of materials – predicting spectra from images and images from spectra". United Kingdom. doi:10.1039/C8SC03077D.
@article{osti_1480874,
title = {Machine learning of optical properties of materials – predicting spectra from images and images from spectra},
author = {Stein, Helge S. and Guevarra, Dan and Newhouse, Paul F. and Soedarmadji, Edwin and Gregoire, John M.},
abstractNote = {Assembling the world's largest materials image and spectroscopy dataset enables training of machine learning models that learn hidden relationships in materials data, providing a key example of the data requirements to capitalize on recent advancements in computer science.},
doi = {10.1039/C8SC03077D},
journal = {Chemical Science},
number = ,
volume = ,
place = {United Kingdom},
year = {Tue Jan 01 00:00:00 EST 2019},
month = {Tue Jan 01 00:00:00 EST 2019}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1039/C8SC03077D

Save / Share: