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

This content will become publicly available on October 15, 2020

Title: Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing

Abstract

Analysis of reactive-diffusion simulations representing complex mixing processes requires a large number of independent model runs. For each high-fidelity model simulation, the model inputs are varied and the predicted mixing behavior is represented by temporal and spatial changes in species concentration. It is then required to discern how the model inputs (such as diffusivity, dispersion, anisotropy, and velocity field properties) impact the mixing process. This task is challenging and typically involves interpretation of large model outputs representing temporal and spatial changes of species concentration within the model domain. Yet, the task can be automated and substantially simplified by applying Machine Learning (ML) methods. Here, we present an application of an unsupervised ML method (called NTF k) using Non-negative Tensor Factorization (NTF) coupled with a custom clustering procedure based on k-means to reveal the temporal and spatial features in product concentrations. An attractive and unique aspect of the proposed ML method is that it ensures the extracted features are non-negative, which is important to obtain a meaningful deconstruction of the mixing processes. The ML methodology is applied to a large set of high-resolution finite-element model simulations representing anisotropic reaction-diffusion processes in perturbed vortex-based velocity fields. The applied finite-element method ensures thatmore » spatial and temporal species concentration are always non-negative, even in the case of high anisotropic contrasts. The simulated reaction is a fast irreversible bimolecular reaction A+B→C , where species A and B react to form species C. The reactive-diffusion model input parameters that control mixing include properties of the velocity field (such as vortex structures), anisotropic dispersion, and molecular diffusion. We demonstrate the applicability of the ML feature extraction method to produce a meaningful deconstruction of model outputs to discriminate between different physical processes impacting the reactants, their mixing, and the spatial distribution of the product C. The introduced ML analysis allowed us to identify additive temporal and spatial features that characterize mixing behavior. The application of the proposed NTF k approach is not limited to reactive-mixing. NTFk can be readily applied to any observed or simulated datasets that can be represented as tensors (multi-dimensional arrays) and have separable latent signatures or features.« less

Authors:
ORCiD logo [1]; ORCiD logo [1];  [1];  [2];  [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Maryland Baltimore County (UMBC), Baltimore, MD (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation (NA-20)
OSTI Identifier:
1529535
Alternate Identifier(s):
OSTI ID: 1527034
Report Number(s):
LA-UR-18-20868
Journal ID: ISSN 0021-9991
Grant/Contract Number:  
89233218CNA000001; AC52-06NA25396; 11145687; 20150693ECR; 20180060DR; 20190020DR
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Computational Physics
Additional Journal Information:
Journal Volume: 395; Journal Issue: C; Journal ID: ISSN 0021-9991
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
Non-negative tensor factorization; Unsupervised machine learning; Structure-preserving feature extraction; Reactive-mixing; Anisotropic dispersion; Non-negative solutions

Citation Formats

Vesselinov, V. V., Mudunuru, M. K., Karra, S., O'Malley, D., and Alexandrov, B. S. Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing. United States: N. p., 2019. Web. doi:10.1016/j.jcp.2019.05.039.
Vesselinov, V. V., Mudunuru, M. K., Karra, S., O'Malley, D., & Alexandrov, B. S. Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing. United States. doi:10.1016/j.jcp.2019.05.039.
Vesselinov, V. V., Mudunuru, M. K., Karra, S., O'Malley, D., and Alexandrov, B. S. Tue . "Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing". United States. doi:10.1016/j.jcp.2019.05.039.
@article{osti_1529535,
title = {Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing},
author = {Vesselinov, V. V. and Mudunuru, M. K. and Karra, S. and O'Malley, D. and Alexandrov, B. S.},
abstractNote = {Analysis of reactive-diffusion simulations representing complex mixing processes requires a large number of independent model runs. For each high-fidelity model simulation, the model inputs are varied and the predicted mixing behavior is represented by temporal and spatial changes in species concentration. It is then required to discern how the model inputs (such as diffusivity, dispersion, anisotropy, and velocity field properties) impact the mixing process. This task is challenging and typically involves interpretation of large model outputs representing temporal and spatial changes of species concentration within the model domain. Yet, the task can be automated and substantially simplified by applying Machine Learning (ML) methods. Here, we present an application of an unsupervised ML method (called NTFk) using Non-negative Tensor Factorization (NTF) coupled with a custom clustering procedure based on k-means to reveal the temporal and spatial features in product concentrations. An attractive and unique aspect of the proposed ML method is that it ensures the extracted features are non-negative, which is important to obtain a meaningful deconstruction of the mixing processes. The ML methodology is applied to a large set of high-resolution finite-element model simulations representing anisotropic reaction-diffusion processes in perturbed vortex-based velocity fields. The applied finite-element method ensures that spatial and temporal species concentration are always non-negative, even in the case of high anisotropic contrasts. The simulated reaction is a fast irreversible bimolecular reaction A+B→C , where species A and B react to form species C. The reactive-diffusion model input parameters that control mixing include properties of the velocity field (such as vortex structures), anisotropic dispersion, and molecular diffusion. We demonstrate the applicability of the ML feature extraction method to produce a meaningful deconstruction of model outputs to discriminate between different physical processes impacting the reactants, their mixing, and the spatial distribution of the product C. The introduced ML analysis allowed us to identify additive temporal and spatial features that characterize mixing behavior. The application of the proposed NTFk approach is not limited to reactive-mixing. NTFk can be readily applied to any observed or simulated datasets that can be represented as tensors (multi-dimensional arrays) and have separable latent signatures or features.},
doi = {10.1016/j.jcp.2019.05.039},
journal = {Journal of Computational Physics},
number = C,
volume = 395,
place = {United States},
year = {2019},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on October 15, 2020
Publisher's Version of Record

Save / Share: