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

Title: Electronic structure at coarse-grained resolutions from supervised machine learning

Abstract

Computational studies aimed at understanding conformationally dependent electronic structure in soft materials require a combination of classical and quantum-mechanical simulations, for which the sampling of conformational space can be particularly demanding. Coarse-grained (CG) models provide a means of accessing relevant time scales, but CG configurations must be back-mapped into atomistic representations to perform quantum-chemical calculations, which is computationally intensive and inconsistent with the spatial resolution of the CG models. A machine learning approach, denoted as artificial neural network electronic coarse graining (ANN-ECG), is presented here in which the conformationally dependent electronic structure of a molecule is mapped directly to CG pseudo-atom configurations. By averaging over decimated degrees of freedom, ANN-ECG accelerates simulations by eliminating backmapping and repeated quantum-chemical calculations. The approach is accurate, consistent with the CG spatial resolution, and can be used to identify computationally optimal CG resolutions.

Authors:
ORCiD logo [1];  [2];  [2]; ORCiD logo [2];  [3];  [1]
  1. Argonne National Lab. (ANL), Lemont, IL (United States); Univ. of Chicago, Chicago, IL (United States)
  2. Univ. of Chicago, Chicago, IL (United States)
  3. Argonne National Lab. (ANL), Lemont, IL (United States)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22). Materials Sciences & Engineering Division; Midwest Integrated Center for Computational Materials (MICCoM)
OSTI Identifier:
1506239
Grant/Contract Number:  
AC02-06CH11357
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Science Advances
Additional Journal Information:
Journal Volume: 5; Journal Issue: 3; Journal ID: ISSN 2375-2548
Publisher:
AAAS
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 36 MATERIALS SCIENCE; 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Citation Formats

Jackson, Nicholas E., Bowen, Alec S., Antony, Lucas W., Webb, Michael A., Vishwanath, Venkatram, and de Pablo, Juan J. Electronic structure at coarse-grained resolutions from supervised machine learning. United States: N. p., 2019. Web. doi:10.1126/sciadv.aav1190.
Jackson, Nicholas E., Bowen, Alec S., Antony, Lucas W., Webb, Michael A., Vishwanath, Venkatram, & de Pablo, Juan J. Electronic structure at coarse-grained resolutions from supervised machine learning. United States. https://doi.org/10.1126/sciadv.aav1190
Jackson, Nicholas E., Bowen, Alec S., Antony, Lucas W., Webb, Michael A., Vishwanath, Venkatram, and de Pablo, Juan J. Fri . "Electronic structure at coarse-grained resolutions from supervised machine learning". United States. https://doi.org/10.1126/sciadv.aav1190. https://www.osti.gov/servlets/purl/1506239.
@article{osti_1506239,
title = {Electronic structure at coarse-grained resolutions from supervised machine learning},
author = {Jackson, Nicholas E. and Bowen, Alec S. and Antony, Lucas W. and Webb, Michael A. and Vishwanath, Venkatram and de Pablo, Juan J.},
abstractNote = {Computational studies aimed at understanding conformationally dependent electronic structure in soft materials require a combination of classical and quantum-mechanical simulations, for which the sampling of conformational space can be particularly demanding. Coarse-grained (CG) models provide a means of accessing relevant time scales, but CG configurations must be back-mapped into atomistic representations to perform quantum-chemical calculations, which is computationally intensive and inconsistent with the spatial resolution of the CG models. A machine learning approach, denoted as artificial neural network electronic coarse graining (ANN-ECG), is presented here in which the conformationally dependent electronic structure of a molecule is mapped directly to CG pseudo-atom configurations. By averaging over decimated degrees of freedom, ANN-ECG accelerates simulations by eliminating backmapping and repeated quantum-chemical calculations. The approach is accurate, consistent with the CG spatial resolution, and can be used to identify computationally optimal CG resolutions.},
doi = {10.1126/sciadv.aav1190},
url = {https://www.osti.gov/biblio/1506239}, journal = {Science Advances},
issn = {2375-2548},
number = 3,
volume = 5,
place = {United States},
year = {2019},
month = {3}
}

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

Citation Metrics:
Cited by: 5 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
journal, January 2012


Conformational Order in Aggregates of Conjugated Polymers
journal, May 2015


The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics
journal, January 2018


Development and Testing of the OPLS All-Atom Force Field on Conformational Energetics and Properties of Organic Liquids
journal, January 1996


Graph-Based Approach to Systematic Molecular Coarse-Graining
journal, November 2018


Charge Transport in Organic Semiconductors
journal, April 2007


The ORCA program system: The ORCA program system
journal, June 2011


Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach
journal, April 2015


Conformational disorder of conjugated polymers: Implications for optical properties
journal, January 1996


Machine learning unifies the modeling of materials and molecules
journal, December 2017


Intra-molecular Charge Transfer and Electron Delocalization in Non-fullerene Organic Solar Cells
journal, March 2018


Modeling Charge Transport in Organic Photovoltaic Materials
journal, November 2009


Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995


Bypassing the Kohn-Sham equations with machine learning
journal, October 2017


Electronic couplings for molecular charge transfer: Benchmarking CDFT, FODFT, and FODFTB against high-level ab initio calculations
journal, March 2014


Tight binding model of conformational disorder effects on the optical absorption spectrum of polythiophenes
journal, January 2016


Intramolecular Charge Transport along Isolated Chains of Conjugated Polymers:  Effect of Torsional Disorder and Polymerization Defects
journal, August 2002


Organic light-emitting devices (OLEDs) and OLED-based chemical and biological sensors: an overview
journal, June 2008


Poly(3-hexylthiophene): synthetic methodologies and properties in bulk heterojunction solar cells
journal, January 2012


For the Bright Future-Bulk Heterojunction Polymer Solar Cells with Power Conversion Efficiency of 7.4%
journal, May 2010


Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010


Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
conference, December 2015


Perspective: Machine learning potentials for atomistic simulations
journal, November 2016


Quantum-chemical insights from deep tensor neural networks
journal, January 2017


Microscopic Simulations of Charge Transport in Disordered Organic Semiconductors
journal, August 2011


Machine Learning Force Fields: Construction, Validation, and Outlook
journal, December 2016


Versatile Object-Oriented Toolkit for Coarse-Graining Applications
journal, November 2009


NWChem: A comprehensive and scalable open-source solution for large scale molecular simulations
journal, September 2010


Machine learning of accurate energy-conserving molecular force fields
journal, May 2017


Charge Transport in Molecular Materials: An Assessment of Computational Methods
journal, June 2017


Quantum chemistry structures and properties of 134 kilo molecules
journal, August 2014


Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
journal, January 2018


Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics
journal, April 2018


Geometry and Electronic Coupling in Perylenediimide Stacks: Mapping Structure−Charge Transport Relationships
journal, February 2010


Relative orientation
journal, January 1990


Modeling of Organic Light Emitting Diodes: From Molecular to Device Properties
journal, January 2015


Bulk Heterojunction Morphologies with Atomistic Resolution from Coarse-Grain Solvent Evaporation Simulations
journal, March 2017


    Works referencing / citing this record:

    Machine learning predictions of electronic couplings for charge transport calculations of P3HT
    journal, August 2019