Predicting charge density distribution of materials using a local-environment-based graph convolutional network

The electron charge density distribution of materials is one of the key quantities in computational materials science as theoretically it determines the ground state energy and practically it is used in many materials analyses. However, the scaling of density functional theory calculations with number of atoms limits the usage of charge-density-based calculations and analyses. Here we introduce a machine-learning scheme with local-environment-based graphs and graph convolutional neural networks to predict charge density on grid points from the crystal structure. We show the accuracy of this scheme through a comparison of predicted charge densities as well as properties derived from the charge density, and that the scaling is $O$($N$). More importantly, the transferability is shown to be high with respect to different compositions and structures, which results from the explicit encoding of geometry.

[1]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[2]  M. Baskes,et al.  Embedded-atom method: Derivation and application to impurities, surfaces, and other defects in metals , 1984 .

[3]  R. Bader,et al.  Toward a theory of chemical reactivity based on the charge density , 1985 .

[4]  The Laplacian of the charge density as a probe of reaction paths and reactivity: a comparison of SN2 reactions at carbon and silicon , 1991 .

[5]  Blöchl,et al.  Projector augmented-wave method. , 1994, Physical review. B, Condensed matter.

[6]  Claude Lecomte,et al.  On Building a Data Bank of Transferable Experimental Electron Density Parameters Applicable to Polypeptides , 1995 .

[7]  Burke,et al.  Generalized Gradient Approximation Made Simple. , 1996, Physical review letters.

[8]  Kresse,et al.  Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. , 1996, Physical review. B, Condensed matter.

[9]  Andreas Savin,et al.  ELF: The Electron Localization Function , 1997 .

[10]  S. Nayak,et al.  Charge distribution and stability of charged carbon nanotubes. , 2002, Physical review letters.

[11]  Donggeun Lee,et al.  A new parameter to control heat transport in nanofluids: surface charge state of the particle in suspension. , 2006, The journal of physical chemistry. B.

[12]  Stefan Grimme,et al.  Semiempirical GGA‐type density functional constructed with a long‐range dispersion correction , 2006, J. Comput. Chem..

[13]  غلامحسین رنجبر عمرانی,et al.  10 , 1910, The Streel.

[14]  Laplacian-level density functionals for the kinetic energy density and exchange-correlation energy , 2006, cond-mat/0612430.

[15]  Douglas B Kell,et al.  Optimal construction of a fast and accurate polarisable water potential based on multipole moments trained by machine learning. , 2009, Physical chemistry chemical physics : PCCP.

[16]  Julia Contreras-García,et al.  Revealing noncovalent interactions. , 2010, Journal of the American Chemical Society.

[17]  Peter Politzer,et al.  The electrostatic potential: an overview , 2011 .

[18]  S. Martin,et al.  Classifying organic materials by oxygen-to-carbon elemental ratio to predict the activation regime of cloud condensation nuclei (CCN). , 2012 .

[19]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[20]  O. A. von Lilienfeld,et al.  Transferable Atomic Multipole Machine Learning Models for Small Organic Molecules. , 2015, Journal of chemical theory and computation.

[21]  Anmol Kumar,et al.  On the electrostatic nature of electrides. , 2015, Physical chemistry chemical physics : PCCP.

[22]  K. Moffett,et al.  Remote Sens , 2015 .

[23]  Gerbrand Ceder,et al.  An efficient algorithm for finding the minimum energy path for cation migration in ionic materials. , 2016, The Journal of chemical physics.

[24]  Engineering,et al.  Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques , 2016 .

[25]  Zhenyu Li,et al.  Electride: from computational characterization to theoretical design , 2016 .

[26]  Li Li,et al.  Bypassing the Kohn-Sham equations with machine learning , 2016, Nature Communications.

[27]  James E. Gubernatis,et al.  Multi-fidelity machine learning models for accurate bandgap predictions of solids , 2017 .

[28]  Qian Wang,et al.  Ground-State Structure of YN2 Monolayer Identified by Global Search , 2017 .

[29]  Qian Wang,et al.  Boron-Doped Graphene as a Promising Anode Material for Potassium-Ion Batteries with a Large Capacity, High Rate Performance, and Good Cycling Stability , 2017 .

[30]  Alexie M. Kolpak,et al.  Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods , 2017, Scientific Reports.

[31]  Florbela Pereira,et al.  Machine learning for the prediction of molecular dipole moments obtained by density functional theory , 2018, Journal of Cheminformatics.

[32]  Maciej Haranczyk,et al.  Electrostatic Estimation of Intercalant Jump-Diffusion Barriers Using Finite-Size Ion Models. , 2018, The journal of physical chemistry letters.

[33]  Tian Xie,et al.  Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks , 2018, The Journal of chemical physics.

[34]  Rafael Gómez-Bombarelli.  Reaction: The Near Future of Artificial Intelligence in Materials Discovery , 2018, Chem.

[35]  Ying Zhang,et al.  A strategy to apply machine learning to small datasets in materials science , 2018, npj Computational Materials.

[36]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[37]  James A. Elliott,et al.  Learning models for electron densities with Bayesian regression , 2018, Computational Materials Science.

[38]  Jeffrey C Grossman,et al.  Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. , 2017, Physical review letters.

[39]  Dirk Tiede,et al.  Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data , 2018, Remote. Sens..

[40]  K-R Müller,et al.  SchNet - A deep learning architecture for molecules and materials. , 2017, The Journal of chemical physics.

[41]  J. Grossman,et al.  Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Suppression of Dendrite Formation in Lithium Metal Anodes , 2018, ACS central science.

[42]  Qian Wang,et al.  Classifying superheavy elements by machine learning , 2019, Physical Review A.

[43]  Junyi Liu,et al.  Maximizing Ether Oxygen Content in Polymers for Membrane CO2 Removal from Natural Gas. , 2019, ACS applied materials & interfaces.

[44]  K. Sohn,et al.  Predicting the Electrochemical Properties of Lithium-Ion Battery Electrode Materials with the Quantum Neural Network Algorithm , 2019, The Journal of Physical Chemistry C.

[45]  Antonio-José Almeida,et al.  NAT , 2019, Springer Reference Medizin.

[46]  Anand Chandrasekaran,et al.  Solving the electronic structure problem with machine learning , 2019, npj Computational Materials.

[47]  Alberto Fabrizio,et al.  Transferable Machine-Learning Model of the Electron Density , 2018, ACS central science.

[48]  Chem. , 2020, Catalysis from A to Z.

[49]  Yaliang Li,et al.  SCI , 2021, Proceedings of the 30th ACM International Conference on Information & Knowledge Management.