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

Title: Nonnegative tensor decomposition with custom clustering for microphase separation of block copolymers

Abstract

High–dimensional datasets are becoming ubiquitous in many applications and therefore unsupervised tensor methods to interrogate them are needed. Here, we report a new unsupervised machine learning (ML) approach (NTFk) based on nonnegative tensor factorization integrated with a custom k–means clustering. We demonstrate the ability of NTFk to extracting temporal and spatial features of phase separation of copolymers as they are modeled by self–consistent field theory. Microphase separation of block copolymers has been extensively studied both experimentally and theoretically. However, the interpretation of computer simulations and/or experimental data, representing temporal and spatial changes of molecular species concentration is still a challenging task. Thus, extracting the phase diagram from simulations or experimental data as well as the interpretation of data requires discernment of the model/experimental parameters (such as, temperature, concentrations, the number of molecular species and the interaction between species) impact on the microphase separation process. An attractive and unique aspect of the introduced ML method is that it ensures the nonnegativity of the extracted latent features. Nonnegativity is an essential constraint needed to obtain interpretable and sparse latent features that are parts–based representation of the data. The custom clustering in NTFk serves to estimate the number of latent features in themore » data.« less

Authors:
ORCiD logo [1];  [2]; ORCiD logo [1]; ORCiD logo [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. Univ. of Maryland, College Park, MD (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1525850
Report Number(s):
LA-UR-18-25176
Journal ID: ISSN 1932-1864
Grant/Contract Number:  
89233218CNA000001
Resource Type:
Accepted Manuscript
Journal Name:
Statistical Analysis and Data Mining
Additional Journal Information:
Journal Volume: 12; Journal Issue: 4; Journal ID: ISSN 1932-1864
Publisher:
Wiley
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Computer Science; Mathematics; dimension reduction; feature extraction; nonnegative tensor factorization; phase separation; unsupervised learning

Citation Formats

Alexandrov, Boian S., Stanev, Valentin G., Vesselinov, Velimir Valentinov, and Rasmussen, Kim Ørskov. Nonnegative tensor decomposition with custom clustering for microphase separation of block copolymers. United States: N. p., 2019. Web. doi:10.1002/sam.11407.
Alexandrov, Boian S., Stanev, Valentin G., Vesselinov, Velimir Valentinov, & Rasmussen, Kim Ørskov. Nonnegative tensor decomposition with custom clustering for microphase separation of block copolymers. United States. doi:10.1002/sam.11407.
Alexandrov, Boian S., Stanev, Valentin G., Vesselinov, Velimir Valentinov, and Rasmussen, Kim Ørskov. Tue . "Nonnegative tensor decomposition with custom clustering for microphase separation of block copolymers". United States. doi:10.1002/sam.11407. https://www.osti.gov/servlets/purl/1525850.
@article{osti_1525850,
title = {Nonnegative tensor decomposition with custom clustering for microphase separation of block copolymers},
author = {Alexandrov, Boian S. and Stanev, Valentin G. and Vesselinov, Velimir Valentinov and Rasmussen, Kim Ørskov},
abstractNote = {High–dimensional datasets are becoming ubiquitous in many applications and therefore unsupervised tensor methods to interrogate them are needed. Here, we report a new unsupervised machine learning (ML) approach (NTFk) based on nonnegative tensor factorization integrated with a custom k–means clustering. We demonstrate the ability of NTFk to extracting temporal and spatial features of phase separation of copolymers as they are modeled by self–consistent field theory. Microphase separation of block copolymers has been extensively studied both experimentally and theoretically. However, the interpretation of computer simulations and/or experimental data, representing temporal and spatial changes of molecular species concentration is still a challenging task. Thus, extracting the phase diagram from simulations or experimental data as well as the interpretation of data requires discernment of the model/experimental parameters (such as, temperature, concentrations, the number of molecular species and the interaction between species) impact on the microphase separation process. An attractive and unique aspect of the introduced ML method is that it ensures the nonnegativity of the extracted latent features. Nonnegativity is an essential constraint needed to obtain interpretable and sparse latent features that are parts–based representation of the data. The custom clustering in NTFk serves to estimate the number of latent features in the data.},
doi = {10.1002/sam.11407},
journal = {Statistical Analysis and Data Mining},
number = 4,
volume = 12,
place = {United States},
year = {2019},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 1 work
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Alternating proximal gradient method for sparse nonnegative Tucker decomposition
journal, May 2014


Self-consistent mean field theory of the microphases of diblock copolymers
journal, September 1992


"General Intelligence," Objectively Determined and Measured
journal, April 1904

  • Spearman, C.
  • The American Journal of Psychology, Vol. 15, Issue 2
  • DOI: 10.2307/1412107

Clock-like mutational processes in human somatic cells
journal, November 2015

  • Alexandrov, Ludmil B.; Jones, Philip H.; Wedge, David C.
  • Nature Genetics, Vol. 47, Issue 12
  • DOI: 10.1038/ng.3441

A Multilinear Singular Value Decomposition
journal, January 2000

  • De Lathauwer, Lieven; De Moor, Bart; Vandewalle, Joos
  • SIAM Journal on Matrix Analysis and Applications, Vol. 21, Issue 4
  • DOI: 10.1137/S0895479896305696

PARAFAC: Parallel factor analysis
journal, August 1994


Some mathematical notes on three-mode factor analysis
journal, September 1966


Signatures of mutational processes in human cancer
journal, August 2013

  • Alexandrov, Ludmil B.; Nik-Zainal, Serena; Wedge, David C.
  • Nature, Vol. 500, Issue 7463
  • DOI: 10.1038/nature12477

Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
journal, November 1987


The Cocktail Party Problem
journal, September 2005


Recent developments in CANDECOMP/PARAFAC algorithms: a critical review
journal, January 2003

  • Faber, Nicolaas (Klaas) M.; Bro, Rasmus; Hopke, Philip K.
  • Chemometrics and Intelligent Laboratory Systems, Vol. 65, Issue 1
  • DOI: 10.1016/S0169-7439(02)00089-8

Theory of inhomogeneous multicomponent polymer systems
journal, May 1981


Tensor decompositions for feature extraction and classification of high dimensional datasets
journal, January 2010

  • Phan, Anh Huy; Cichocki, Andrzej
  • Nonlinear Theory and Its Applications, IEICE, Vol. 1, Issue 1
  • DOI: 10.1587/nolta.1.37

Tensor Decomposition for Signal Processing and Machine Learning
journal, July 2017

  • Sidiropoulos, Nicholas D.; De Lathauwer, Lieven; Fu, Xiao
  • IEEE Transactions on Signal Processing, Vol. 65, Issue 13
  • DOI: 10.1109/TSP.2017.2690524

Deciphering Signatures of Mutational Processes Operative in Human Cancer
journal, January 2013


Unsupervised phase mapping of X-ray diffraction data by nonnegative matrix factorization integrated with custom clustering
journal, August 2018

  • Stanev, Valentin; Vesselinov, Velimir V.; Kusne, A. Gilad
  • npj Computational Materials, Vol. 4, Issue 1
  • DOI: 10.1038/s41524-018-0099-2

The N-way Toolbox for MATLAB
journal, August 2000


Nonnegative approximations of nonnegative tensors
journal, July 2009

  • Lim, Lek-Heng; Comon, Pierre
  • Journal of Chemometrics, Vol. 23, Issue 7-8
  • DOI: 10.1002/cem.1244

Block Copolymer Theory. 4. Narrow Interphase Approximation
journal, November 1976


Theory of inhomogeneous polymers: Fundamentals of the Gaussian random‐walk model
journal, February 1975

  • Helfand, Eugene
  • The Journal of Chemical Physics, Vol. 62, Issue 3
  • DOI: 10.1063/1.430517

Understanding the origins of human cancer
journal, December 2015


Singular value decomposition and least squares solutions
journal, April 1970

  • Golub, G. H.; Reinsch, C.
  • Numerische Mathematik, Vol. 14, Issue 5
  • DOI: 10.1007/BF02163027

On uniqueness in candecomp/parafac
journal, September 2002

  • ten Berge, Jos M. F.; Sidiropoulos, Nikolaos D.
  • Psychometrika, Vol. 67, Issue 3
  • DOI: 10.1007/BF02294992

Blind source separation for groundwater pressure analysis based on nonnegative matrix factorization
journal, September 2014

  • Alexandrov, Boian S.; Vesselinov, Velimir V.
  • Water Resources Research, Vol. 50, Issue 9
  • DOI: 10.1002/2013WR015037

Learning the parts of objects by non-negative matrix factorization
journal, October 1999

  • Lee, Daniel D.; Seung, H. Sebastian
  • Nature, Vol. 401, Issue 6755
  • DOI: 10.1038/44565

Tensor rank is NP-complete
journal, December 1990


Improved numerical algorithm for exploring block copolymer mesophases
journal, July 2002

  • Rasmussen, K. �.; Kalosakas, G.
  • Journal of Polymer Science Part B: Polymer Physics, Vol. 40, Issue 16
  • DOI: 10.1002/polb.10238

Uniqueness of Nonnegative Tensor Approximations
journal, April 2016

  • Qi, Yang; Comon, Pierre; Lim, Lek-Heng
  • IEEE Transactions on Information Theory, Vol. 62, Issue 4
  • DOI: 10.1109/TIT.2016.2532906

Identification of release sources in advection–diffusion system by machine learning combined with Green’s function inverse method
journal, August 2018


Block Copolymers—Designer Soft Materials
journal, February 1999

  • Bates, Frank S.; Fredrickson, Glenn H.
  • Physics Today, Vol. 52, Issue 2
  • DOI: 10.1063/1.882522

The standard Gaussian model for block copolymer melts
journal, December 2001


Nonnegative Matrix Factorization for identification of unknown number of sources emitting delayed signals
journal, March 2018