Multi-component background learning automates signal detection for spectroscopic data
Abstract
Abstract Automated experimentation has yielded data acquisition rates that supersede human processing capabilities. Artificial Intelligence offers new possibilities for automating data interpretation to generate large, high-quality datasets. Background subtraction is a long-standing challenge, particularly in settings where multiple sources of the background signal coexist, and automatic extraction of signals of interest from measured signals accelerates data interpretation. Herein, we present an unsupervised probabilistic learning approach that analyzes large data collections to identify multiple background sources and establish the probability that any given data point contains a signal of interest. The approach is demonstrated on X-ray diffraction and Raman spectroscopy data and is suitable to any type of data where the signal of interest is a positive addition to the background signals. While the model can incorporate prior knowledge, it does not require knowledge of the signals since the shapes of the background signals, the noise levels, and the signal of interest are simultaneously learned via a probabilistic matrix factorization framework. Automated identification of interpretable signals by unsupervised probabilistic learning avoids the injection of human bias and expedites signal extraction in large datasets, a transformative capability with many applications in the physical sciences and beyond.
- Publication Date:
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1619644
- Resource Type:
- Published Article
- Journal Name:
- npj Computational Materials
- Additional Journal Information:
- Journal Name: npj Computational Materials Journal Volume: 5 Journal Issue: 1; Journal ID: ISSN 2057-3960
- Publisher:
- Nature Publishing Group
- Country of Publication:
- United Kingdom
- Language:
- English
Citation Formats
Ament, Sebastian E., Stein, Helge S., Guevarra, Dan, Zhou, Lan, Haber, Joel A., Boyd, David A., Umehara, Mitsutaro, Gregoire, John M., and Gomes, Carla P. Multi-component background learning automates signal detection for spectroscopic data. United Kingdom: N. p., 2019.
Web. doi:10.1038/s41524-019-0213-0.
Ament, Sebastian E., Stein, Helge S., Guevarra, Dan, Zhou, Lan, Haber, Joel A., Boyd, David A., Umehara, Mitsutaro, Gregoire, John M., & Gomes, Carla P. Multi-component background learning automates signal detection for spectroscopic data. United Kingdom. https://doi.org/10.1038/s41524-019-0213-0
Ament, Sebastian E., Stein, Helge S., Guevarra, Dan, Zhou, Lan, Haber, Joel A., Boyd, David A., Umehara, Mitsutaro, Gregoire, John M., and Gomes, Carla P. Fri .
"Multi-component background learning automates signal detection for spectroscopic data". United Kingdom. https://doi.org/10.1038/s41524-019-0213-0.
@article{osti_1619644,
title = {Multi-component background learning automates signal detection for spectroscopic data},
author = {Ament, Sebastian E. and Stein, Helge S. and Guevarra, Dan and Zhou, Lan and Haber, Joel A. and Boyd, David A. and Umehara, Mitsutaro and Gregoire, John M. and Gomes, Carla P.},
abstractNote = {Abstract Automated experimentation has yielded data acquisition rates that supersede human processing capabilities. Artificial Intelligence offers new possibilities for automating data interpretation to generate large, high-quality datasets. Background subtraction is a long-standing challenge, particularly in settings where multiple sources of the background signal coexist, and automatic extraction of signals of interest from measured signals accelerates data interpretation. Herein, we present an unsupervised probabilistic learning approach that analyzes large data collections to identify multiple background sources and establish the probability that any given data point contains a signal of interest. The approach is demonstrated on X-ray diffraction and Raman spectroscopy data and is suitable to any type of data where the signal of interest is a positive addition to the background signals. While the model can incorporate prior knowledge, it does not require knowledge of the signals since the shapes of the background signals, the noise levels, and the signal of interest are simultaneously learned via a probabilistic matrix factorization framework. Automated identification of interpretable signals by unsupervised probabilistic learning avoids the injection of human bias and expedites signal extraction in large datasets, a transformative capability with many applications in the physical sciences and beyond.},
doi = {10.1038/s41524-019-0213-0},
journal = {npj Computational Materials},
number = 1,
volume = 5,
place = {United Kingdom},
year = {2019},
month = {7}
}
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1038/s41524-019-0213-0
https://doi.org/10.1038/s41524-019-0213-0
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 2 works
Citation information provided by
Web of Science
Web of Science
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Automatic collection of powder data from photographs
journal, February 1975
- Sonneveld, E. J.; Visser, J. W.
- Journal of Applied Crystallography, Vol. 8, Issue 1
Inelastic background intensities in XPS spectra
journal, August 1984
- Tougaard, S.; Jørgensen, B.
- Surface Science, Vol. 143, Issue 2-3
Discovering Ce-rich oxygen evolution catalysts, from high throughput screening to water electrolysis
journal, January 2014
- Haber, Joel A.; Cai, Yun; Jung, Suho
- Energy Environ. Sci., Vol. 7, Issue 2
What are the shapes of response time distributions in visual search?
journal, January 2011
- Palmer, Evan M.; Horowitz, Todd S.; Torralba, Antonio
- Journal of Experimental Psychology: Human Perception and Performance, Vol. 37, Issue 1
XCIII. On the theory of X-ray absorption and of the continuous X-ray spectrum
journal, November 1923
- Kramers, H. A.
- The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, Vol. 46, Issue 275
Solar fuel photoanodes prepared by inkjet printing of copper vanadates
journal, January 2016
- Newhouse, P. F.; Boyd, D. A.; Shinde, A.
- Journal of Materials Chemistry A, Vol. 4, Issue 19
Saddlepoint methods for option pricing
journal, September 2009
- Carr, Peter; Madan, Dilip
- The Journal of Computational Finance, Vol. 13, Issue 1
The quantitative analysis of surfaces by XPS: A review
journal, December 1980
- Seah, M. P.
- Surface and Interface Analysis, Vol. 2, Issue 6
The 2019 materials by design roadmap
journal, October 2018
- Alberi, Kirstin; Nardelli, Marco Buongiorno; Zakutayev, Andriy
- Journal of Physics D: Applied Physics, Vol. 52, Issue 1
Accelerating the discovery of materials for clean energy in the era of smart automation
journal, April 2018
- Tabor, Daniel P.; Roch, Loïc M.; Saikin, Semion K.
- Nature Reviews Materials, Vol. 3, Issue 5
Automated Autofluorescence Background Subtraction Algorithm for Biomedical Raman Spectroscopy
journal, November 2007
- Zhao, Jianhua; Lui, Harvey; McLean, David I.
- Applied Spectroscopy, Vol. 61, Issue 11
Calculation of the electron–electron bremsstrahlung cross-section in the field of atomic electrons
journal, February 2008
- Tessier, Frédéric; Kawrakow, Iwan
- Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, Vol. 266, Issue 4
Perspective: Composition–structure–property mapping in high-throughput experiments: Turning data into knowledge
journal, May 2016
- Hattrick-Simpers, Jason R.; Gregoire, John M.; Kusne, A. Gilad
- APL Materials, Vol. 4, Issue 5
Combinatorial metallurgical synthesis and processing of high-entropy alloys
journal, July 2018
- Li, Zhiming; Ludwig, Alfred; Savan, Alan
- Journal of Materials Research, Vol. 33, Issue 19
Algorithm for automatic x-ray photoelectron spectroscopy data processing and x-ray photoelectron spectroscopy imaging
journal, July 2005
- Tougaard, Sven
- Journal of Vacuum Science & Technology A: Vacuum, Surfaces, and Films, Vol. 23, Issue 4
Expediting Combinatorial Data Set Analysis by Combining Human and Algorithmic Analysis
journal, December 2016
- Stein, Helge Sören; Jiao, Sally; Ludwig, Alfred
- ACS Combinatorial Science, Vol. 19, Issue 1
Theory of Bremsstrahlung and Pair Production. II. Integral Cross Section for Pair Production
journal, February 1954
- Davies, Handel; Bethe, H. A.; Maximon, L. C.
- Physical Review, Vol. 93, Issue 4
Multivariate Characterization of a Continuous Soot Monitoring System Based on Raman Spectroscopy
journal, September 2015
- Grafen, Markus; Nalpantidis, Konstantinos; Platte, Frank
- Aerosol Science and Technology, Vol. 49, Issue 10
Combinatorial approaches as effective tools in the study of phase diagrams and composition–structure–property relationships
journal, July 2006
- Zhao, J.
- Progress in Materials Science, Vol. 51, Issue 5
Theory of Bremsstrahlung and Pair Production. I. Differential Cross Section
journal, February 1954
- Bethe, H. A.; Maximon, L. C.
- Physical Review, Vol. 93, Issue 4
Exponentially modified Gaussian (EMG) relevance to distributions related to cell proliferation and differentiation
journal, January 2010
- Golubev, A.
- Journal of Theoretical Biology, Vol. 262, Issue 2
Über die Interferenzerscheinungen an planparallelen Platten
journal, January 1904
- Laue, M.
- Annalen der Physik, Vol. 318, Issue 1