Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials

Dan, Yabo; Zhao, Yong; Li, Xiang; Li, Shaobo; Hu, Ming; Hu, Jianjun

doi:10.1038/s41524-020-00352-0

Title: Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials

Journal Article · Fri Jun 26 00:00:00 EDT 2020 · npj Computational Materials

DOI:https://doi.org/10.1038/s41524-020-00352-0· OSTI ID:1647313

Dan, Yabo ^[1];

^[2]; Li, Xiang ^[1]; Li, Shaobo ^[3]; Hu, Ming ^[2];

^[4]

Guizhou Univ., Guiyang (China)
Univ. of South Carolina, Columbia, SC (United States)
Guizhou Univ., Guiyang (China). Key Lab. of Advanced Manufacturing Technology, Ministry of Education
Guizhou Univ., Guiyang (China); Univ. of South Carolina, Columbia, SC (United States)

A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties. One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database. Here, we propose a generative machine learning model (MatGAN) based on a generative adversarial network (GAN) for efficient generation of new hypothetical inorganic materials. Trained with materials from the ICSD database, our GAN model can generate hypothetical materials not existing in the training dataset, reaching a novelty of 92.53% when generating 2 million samples. The percentage of chemically valid (charge-neutral and electronegativity-balanced) samples out of all generated ones reaches 84.5% when generated by our GAN trained with such samples screened from ICSD, even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules to form compounds. Our algorithm is expected to be used to greatly expand the range of the design space for inverse design and large-scale computational screening of inorganic materials.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Univ. of South Carolina, Columbia, SC (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES); National Science Foundation (NSF); National Natural Science Foundation of China (NSFC)

Grant/Contract Number:: SC0020272; 1940099; 1905775; OIA-1655740; 51741101; 2018AAA0101803

OSTI ID:: 1647313

Journal Information:: npj Computational Materials, Vol. 6, Issue 1; ISSN 2057-3960

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 62 works

Citation information provided by
Web of Science

References (24)

Deep neural networks for accurate predictions of crystal stability Ye, Weike; Chen, Chi; Wang, Zhenbin Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-018-06322-x	journal	September 2018
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition Jha, Dipendra; Ward, Logan; Paul, Arindam Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-35934-y	journal	December 2018
A Combinatorial Genetic Algorithm for Computational Doping based Material Design Atilgan, Emrah; Hu, Jianjun Proceedings of the Companion Publication of the 2015 on Genetic and Evolutionary Computation Conference - GECCO Companion '15 https://doi.org/10.1145/2739482.2764700	conference	January 2015
Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) Saal, James E.; Kirklin, Scott; Aykol, Muratahan JOM, Vol. 65, Issue 11 https://doi.org/10.1007/s11837-013-0755-4	journal	September 2013
CALYPSO: A method for crystal structure prediction Wang, Yanchao; Lv, Jian; Zhu, Li Computer Physics Communications, Vol. 183, Issue 10 https://doi.org/10.1016/j.cpc.2012.05.008	journal	October 2012
Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data Cubuk, Ekin D.; Sendek, Austin D.; Reed, Evan J. The Journal of Chemical Physics, Vol. 150, Issue 21 https://doi.org/10.1063/1.5093220	journal	June 2019
Inverse molecular design using machine learning: Generative models for matter engineering Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán Science, Vol. 361, Issue 6400 https://doi.org/10.1126/science.aat2663	journal	July 2018
Computational Screening of All Stoichiometric Inorganic Materials Davies, Daniel W.; Butler, Keith T.; Jackson, Adam J. Chem, Vol. 1, Issue 4 https://doi.org/10.1016/j.chempr.2016.09.010	journal	October 2016
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies Kirklin, Scott; Saal, James E.; Meredig, Bryce npj Computational Materials, Vol. 1, Issue 1 https://doi.org/10.1038/npjcompumats.2015.10	journal	December 2015
Accelerated search for materials with targeted properties by adaptive design Xue, Dezhen; Balachandran, Prasanna V.; Hogden, John Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms11241	journal	April 2016
First-principle-based computational doping of SrTiO $$_{3}$$ 3 using combinatorial genetic algorithms Atilgan, Emrah; Hu, Jianjun Bulletin of Materials Science, Vol. 41, Issue 1 https://doi.org/10.1007/s12034-017-1515-9	journal	February 2018
The inorganic crystal structure data base Bergerhoff, G.; Hundt, R.; Sievers, R. Journal of Chemical Information and Modeling, Vol. 23, Issue 2 https://doi.org/10.1021/ci00038a003	journal	May 1983
Conditional Molecular Design with Deep Generative Models Kang, Seokho; Cho, Kyunghyun Journal of Chemical Information and Modeling, Vol. 59, Issue 1 https://doi.org/10.1021/acs.jcim.8b00263	journal	July 2018
Statistical inference and adaptive design for materials discovery Lookman, Turab; Balachandran, Prasanna V.; Xue, Dezhen Current Opinion in Solid State and Materials Science, Vol. 21, Issue 3 https://doi.org/10.1016/j.cossms.2016.10.002	journal	June 2017
USPEX—Evolutionary crystal structure prediction Glass, Colin W.; Oganov, Artem R.; Hansen, Nikolaus Computer Physics Communications, Vol. 175, Issue 11-12 https://doi.org/10.1016/j.cpc.2006.07.020	journal	December 2006
Inverse Design of Solid-State Materials via a Continuous Representation Noh, Juhwan; Kim, Jaehoon; Stein, Helge S. Matter, Vol. 1, Issue 5 https://doi.org/10.1016/j.matt.2019.08.017	journal	November 2019
An application of Pettifor structure maps for the identification of pseudo-binary quasicrystalline intermetallics Ranganathan, S.; Inoue, A. Acta Materialia, Vol. 54, Issue 14 https://doi.org/10.1016/j.actamat.2006.01.041	journal	August 2006
The Origin of the Ionic-Radius Ratio Rules Jensen, William B.; Jensen, William B. Journal of Chemical Education, Vol. 87, Issue 6 https://doi.org/10.1021/ed100258f	journal	June 2010
Deep learning for molecular generation Xu, Youjun; Lin, Kangjie; Wang, Shiwei Future Medicinal Chemistry, Vol. 11, Issue 6 https://doi.org/10.4155/fmc-2018-0358	journal	March 2019
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy APL Materials, Vol. 1, Issue 1 https://doi.org/10.1063/1.4812323	journal	July 2013
The exotically stoichiometric compounds in Al–S system under high pressure Shao, Sen; Zhu, Wenji; Lv, Jian npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-0278-9	journal	February 2020
A general-purpose machine learning framework for predicting properties of inorganic materials Ward, Logan; Agrawal, Ankit; Choudhary, Alok npj Computational Materials, Vol. 2, Issue 1 https://doi.org/10.1038/npjcompumats.2016.28	journal	August 2016
Machine learning enabled autonomous microstructural characterization in 3D samples Chan, Henry; Cherukara, Mathew; Loeffler, Troy D. npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-019-0267-z	journal	January 2020
Deep learning for molecular design—a review of the state of the art Elton, Daniel C.; Boukouvalas, Zois; Fuge, Mark D. Molecular Systems Design & Engineering, Vol. 4, Issue 4 https://doi.org/10.1039/c9me00039a	journal	January 2019

Cited By (3)

Machine Learning based prediction of noncentrosymmetric crystal materials Song, Yuqi; Lindsay, Joseph; Zhao, Yong Computational Materials Science, Vol. 183 https://doi.org/10.1016/j.commatsci.2020.109792	journal	October 2020
Distance Matrix-Based Crystal Structure Prediction Using Evolutionary Algorithms Hu, Jianjun; Yang, Wenhui; Dilanga Siriwardane, Edirisuriya M. The Journal of Physical Chemistry A, Vol. 124, Issue 51 https://doi.org/10.1021/acs.jpca.0c08775	journal	December 2020
Contact Map based Crystal Structure Prediction using Global Optimization Hu, Jianjun; Yang, Wenhui; Dong, Rongzhi arXiv https://doi.org/10.48550/arxiv.2008.07016	preprint	January 2020

Similar Records

Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks

Journal Article · Fri Jun 12 00:00:00 EDT 2020 · Journal of Physical Chemistry. C · OSTI ID:1647313

Zhao, Yong; Yuan, Kunpeng; Liu, Yinqiao; +3 more

Predicting energy and stability of known and hypothetical crystals using graph neural network

Journal Article · Mon Nov 01 00:00:00 EDT 2021 · Patterns · OSTI ID:1647313

Pandey, Shubham; Qu, Jiaxing; Stevanović, Vladan; +2 more

Predicting Lattice Vibrational Frequencies Using Deep Graph Neural Networks

Journal Article · Thu Jul 21 00:00:00 EDT 2022 · ACS Omega · OSTI ID:1647313

Nguyen, Nghia; Louis, Steph-Yves V.; Wei, Lai; +3 more

Related Subjects

36 MATERIALS SCIENCE
Batteries
computational methods

Title: Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials

Citation Formats

References (24)

Cited By (3)

Similar Records

Related Subjects