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
 

Physically Informed Machine Learning Prediction of Electronic Density of States

Journal Article · · Chemistry of Materials
 [1];  [1];  [1]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
+ Show Author Affiliations
The electronic structure of a material, such as its density of states (DOS), provides key insights into its physical and functional properties and serves as a valuable source of high-quality features for many materials screening and discovery workflows. Still, the computational cost of calculating the DOS, most commonly with density functional theory (DFT), becomes prohibitive for meeting high-fidelity or high-throughput requirements, necessitating a cheaper but sufficiently accurate surrogate. To fulfill this demand, we develop a general machine learning method based on graph neural networks for predicting the DOS purely from atomic positions, six orders of magnitude faster than DFT. This approach can effectively use large materials databases and be applied generally across the entire periodic table to materials classes of arbitrary compositional and structural diversity. We furthermore devise a highly adaptable scheme for physically informed learning which encourages the DOS prediction to favor physically reasonable solutions defined by any set of desired constraints. This functionality provides a means for ensuring that the predicted DOS is reliable enough to be used as an input to downstream materials screening workflows to predict more complex functional properties, which rely on accurate physical features.
Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
Grant/Contract Number:
AC05-00OR22725; AC02-05CH11231
OSTI ID:
1870241
Journal Information:
Chemistry of Materials, Journal Name: Chemistry of Materials Journal Issue: 11 Vol. 34; ISSN 0897-4756
Publisher:
American Chemical Society (ACS)Copyright Statement
Country of Publication:
United States
Language:
English

References (51)

Direct Prediction of Phonon Density of States With Euclidean Neural Networks journal March 2021
Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) journal September 2013
Prediction of the Electron Density of States for Crystalline Compounds with Atomistic Line Graph Neural Networks (ALIGNN) journal March 2022
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set journal July 1996
Graph neural networks: A review of methods and applications journal January 2020
A high-throughput infrastructure for density functional theory calculations journal June 2011
AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations journal June 2012
DScribe: Library of descriptors for machine learning in materials science journal February 2020
An electronic structure descriptor for oxygen reactivity at metal and metal-oxide surfaces journal March 2019
Adsorption Enthalpies for Catalysis Modeling through Machine-Learned Descriptors journal June 2021
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals journal April 2019
Machine Learning Force Fields journal March 2021
Wide Band Gap Chalcogenide Semiconductors journal April 2020
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach journal April 2015
An Efficient Deep Learning Scheme To Predict the Electronic Structure of Materials and Molecules: The Example of Graphene-Derived Allotropes journal November 2020
New Bonding Model of Radical Adsorbate on Lattice Oxygen of Perovskites journal October 2018
Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts journal July 2019
Materials discovery at high pressures journal February 2017
The high-throughput highway to computational materials design journal February 2013
Robust and synthesizable photocatalysts for CO2 reduction: a data-driven materials discovery journal January 2019
Bayesian learning of chemisorption for bridging the complexity of electronic descriptors journal November 2020
Machine learned features from density of states for accurate adsorption energy prediction journal January 2021
Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings journal February 2022
The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design journal November 2020
A Bayesian framework for adsorption energy prediction on bimetallic alloy catalysts journal November 2020
Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides journal April 2020
Benchmarking graph neural networks for materials chemistry journal June 2021
Atomistic Line Graph Neural Network for improved materials property predictions journal November 2021
Electronic-structure methods for materials design journal May 2021
Point defect engineering in thin-film solar cells journal June 2018
Origins of structural and electronic transitions in disordered silicon journal January 2021
High-throughput calculations of catalytic properties of bimetallic alloy surfaces journal May 2019
Pattern Learning Electronic Density of States journal April 2019
Accelerated mapping of electronic density of states patterns of metallic nanoparticles via machine-learning journal June 2021
Physics-informed machine learning journal May 2021
Quantum chemistry structures and properties of 134 kilo molecules journal August 2014
Electronic band contraction induced low temperature methane activation on metal alloys journal January 2020
Comparing molecules and solids across structural and alchemical space journal January 2016
Active learning with non- ab initio input features toward efficient CO 2 reduction catalysts journal January 2018
Communications: Exceptions to the d-band model of chemisorption on metal surfaces: The dominant role of repulsion between adsorbate states and metal d-states journal June 2010
Atom-centered symmetry functions for constructing high-dimensional neural network potentials journal February 2011
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation journal July 2013
Density functional theory in surface chemistry and catalysis journal January 2011
Solar fuels photoanode materials discovery by integrating high-throughput theory and experiment journal March 2017
Learning the electronic density of states in condensed matter journal December 2020
Special points for Brillouin-zone integrations journal June 1976
Projector augmented-wave method journal December 1994
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set journal October 1996
Electron-energy-loss spectra and the structural stability of nickel oxide: An LSDA+U study journal January 1998
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties journal April 2018
Generalized Gradient Approximation Made Simple journal October 1996

Similar Records

Machine learned features from density of states for accurate adsorption energy prediction
Journal Article · Sun Jan 03 23:00:00 EST 2021 · Nature Communications · OSTI ID:1756263
Accelerating Multiscale Materials Modeling with Machine Learning
Technical Report · Thu Sep 01 00:00:00 EDT 2022 · OSTI ID:1889336

Related Subjects

36 MATERIALS SCIENCE
alloys
crystals
density functional theory
materials
neural networks