Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing
From MaRDI portal
Publication:2222331
DOI10.1016/J.JCP.2019.05.039zbMATH Open1452.68160arXiv1805.06454OpenAlexW2803691637WikidataQ118593857 ScholiaQ118593857MaRDI QIDQ2222331FDOQ2222331
Authors: M. K. Mudunuru, Daniel O'Malley, Boian S. Alexandrov, Velimir V. Vesselinov, Satish Karra 
Publication date: 26 January 2021
Published in: Journal of Computational Physics (Search for Journal in Brave)
Abstract: Analysis of reactive-diffusion simulations requires a large number of independent model runs. For each high-fidelity simulation, inputs are varied and the predicted mixing behavior is represented by changes in species concentration. It is then required to discern how the model inputs impact the mixing process. This task is challenging and typically involves interpretation of large model outputs. However, the task can be automated and substantially simplified by applying Machine Learning (ML) methods. In this paper, 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 hidden features in product concentration. An attractive aspect of the proposed ML method is that it ensures the extracted features are non-negative, which are important to obtain a meaningful deconstruction of the mixing processes. The ML method is applied to a large set of high-resolution FEM simulations representing reaction-diffusion processes in perturbed vortex-based velocity fields. The applied FEM ensures that species concentration are always non-negative. The simulated reaction is a fast irreversible bimolecular reaction. The reactive-diffusion model input parameters that control mixing include properties of velocity field, anisotropic dispersion, and molecular diffusion. We demonstrate the applicability of the ML 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. The presented ML analysis allowed us to identify additive features that characterize mixing behavior.
Full work available at URL: https://arxiv.org/abs/1805.06454
Recommendations
- Physics-informed machine learning models for predicting the progress of reactive-mixing
- A deep learning modeling framework to capture mixing patterns in reactive-transport systems
- A full order, reduced order and machine learning model pipeline for efficient prediction of reactive flows
- Unsupervised learning of anomalous diffusion data: an anomaly detection approach
- Nonlinear Laplacian spectral analysis of Rayleigh-Bénard convection
nonnegative solutionsnonnegative tensor factorizationanisotropic dispersionunsupervised machine learningreactive-mixingstructure-preserving feature extraction
Learning and adaptive systems in artificial intelligence (68T05) Multilinear algebra, tensor calculus (15A69) Classical flows, reactions, etc. in chemistry (92E20)
Cites Work
- Silhouettes: a graphical aid to the interpretation and validation of cluster analysis
- PARAFAC: Parallel factor analysis
- Julia: A Fresh Approach to Numerical Computing
- A practical guide to splines
- A Multilinear Singular Value Decomposition
- Learning the parts of objects by non-negative matrix factorization
- A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion
- Title not available (Why is that?)
- Title not available (Why is that?)
- Incompressible flow and the finite element method. Vol. 1: Advection-diffusion. Vol. 2: Isothermal laminar flow
- Algorithms for Sparse Nonnegative Tucker Decompositions
- A numerical framework for diffusion-controlled bimolecular-reactive systems to enforce maximum principles and the non-negative constraint
- Introduction: mixing in microfluidics
- Title not available (Why is that?)
- Alternating proximal gradient method for sparse nonnegative Tucker decomposition
- On enforcing maximum principles and achieving element-wise species balance for advection-diffusion-reaction equations under the finite element method
- Large-scale optimization-based non-negative computational framework for diffusion equations: parallel implementation and performance studies
- Inverse source problem in a one-dimensional evolution linear transport equation with spatially varying coefficients: application to surface water pollution
- Point source identification in nonlinear advection–diffusion–reaction systems
- Identification of release sources in advection-diffusion system by machine learning combined with Green's function inverse method
Cited In (4)
- A comparative study of machine learning models for predicting the state of reactive mixing
- Physics-informed machine learning models for predicting the progress of reactive-mixing
- Generating hidden Markov models from process models through nonnegative tensor factorization
- A Deep Learning Modeling Framework to Capture Mixing Patterns in Reactive-Transport Systems
Uses Software
This page was built for publication: Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2222331)
