Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Phase behavior of continuous-space systems: A supervised machine learning approach

Journal Article · · Journal of Chemical Physics
DOI:https://doi.org/10.1063/5.0014194· OSTI ID:1803182
 [1];  [2]
  1. University of Wisconsin, Madison, Wisconsin (United States). Theoretical Chemistry Institute and Department of Chemistry; OSTI
  2. University of Wisconsin, Madison, Wisconsin (United States). Theoretical Chemistry Institute and Department of Chemistry
+ Show Author Affiliations
The phase behavior of complex fluids is a challenging problem for molecular simulations. Supervised machine learning (ML) methods have shown potential for identifying the phase boundaries of lattice models. In this work, we extend these ML methods to continuous-space systems. We propose a convolutional neural network model that utilizes grid-interpolated coordinates of molecules as input data of ML and optimizes the search for phase transitions with different filter sizes. We test the method for the phase diagram of two off-lattice models, namely, the Widom–Rowlinson model and a symmetric freely jointed polymer blend, for which results are available from standard molecular simulations techniques. The ML results show good agreement with results of previous simulation studies with the added advantage that there is no critical slowing down. We find that understanding intermediate structures near a phase transition and including them in the training set is important to obtain the phase boundary near the critical point. The method is quite general and easy to implement and could find wide application to study the phase behavior of complex fluids.
Research Organization:
Univ. of Wisconsin, Madison, WI (United States)
Sponsoring Organization:
USDOE; USDOE Office of Science (SC)
Grant/Contract Number:
SC0017877
OSTI ID:
1803182
Alternate ID(s):
OSTI ID: 1646929
Journal Information:
Journal of Chemical Physics, Journal Name: Journal of Chemical Physics Journal Issue: 6 Vol. 153; ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)Copyright Statement
Country of Publication:
United States
Language:
English

References (33)

GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers journal September 2015
Machine learning phases of matter journal February 2017
Learning phase transitions by confusion journal February 2017
Machine learning quantum phases of matter beyond the fermion sign problem journal August 2017
Machine learning-aided analysis for complex local structure of liquid crystal polymers journal November 2019
A generalized deep learning approach for local structure identification in molecular simulations journal January 2019
Strongly charged flexible polyelectrolytes in poor solvents: Molecular dynamics simulations with explicit solvent journal April 2003
The interfacial tension and phase diagram of the Widom-Rowlinson mixture via Monte Carlo simulations journal January 2008
Phase behavior of the Widom–Rowlinson mixture journal May 1996
Phase equilibria in binary polymer blends: Integral equation approach journal December 1998
Neural networks for local structure detection in polymorphic systems journal October 2013
A simulation method for the phase diagram of complex fluid mixtures journal June 2018
Unsupervised machine learning for detection of phase transitions in off-lattice systems. I. Foundations journal November 2018
Unsupervised machine learning for detection of phase transitions in off-lattice systems. II. Applications journal November 2018
Unsupervised learning for local structure detection in colloidal systems journal October 2019
Machine learning for collective variable discovery and enhanced sampling in biomolecular simulation journal March 2020
Phase equilibria by simulation in the Gibbs ensemble: Alternative derivation, generalization and application to mixture and membrane equilibria journal March 1988
Gibbs-Duhem integration: a new method for direct evaluation of phase coexistence by molecular simulation journal April 1993
Direct Determination of Fluid Phase Equilibria by Simulation in the Gibbs Ensemble: A Review journal January 1992
Machine learning and data science in soft materials engineering journal December 2017
Finite-size scaling at first-order phase transitions journal August 1984
Identifying quantum phase transitions with adversarial neural networks journal April 2018
Parameter diagnostics of phases and phase transition learning by neural networks journal May 2018
Critical-point and coexistence-curve properties of the Lennard-Jones fluid: A finite-size scaling study journal July 1995
Identifying polymer states by machine learning journal March 2017
Machine learning topological defects of confined liquid crystals in two dimensions journal June 2019
Identifying Structural Flow Defects in Disordered Solids Using Machine-Learning Methods journal March 2015
Finite-Size Scaling and Correlation Lengths for Disordered Systems journal December 1986
Machine Learning Phases of Strongly Correlated Fermions journal August 2017
Beyond the Van Der Waals loop: What can be learned from simulating Lennard-Jones fluids inside the region of phase coexistence journal December 2012
Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions journal April 2017
Detection of Phase Transition via Convolutional Neural Networks journal June 2017
Phase Diagrams of Three-Dimensional Anderson and Quantum Percolation Models Using Deep Three-Dimensional Convolutional Neural Network journal November 2017

Similar Records

A simulation method for the phase diagram of complex fluid mixtures
Journal Article · Sun Jun 24 20:00:00 EDT 2018 · Journal of Chemical Physics · OSTI ID:1540216
Critical behavior of the Widom--Rowlinson lattice model
Journal Article · Thu Jun 01 00:00:00 EDT 1995 · Journal of Chemical Physics · OSTI ID:46417

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Artificial intelligence
Complex fluids
Machine learning
Molecular simulations
Phase transitions
Polymers