Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials
- 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.
- 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
Web of Science
Machine Learning based prediction of noncentrosymmetric crystal materials
|
journal | October 2020 |
Distance Matrix-Based Crystal Structure Prediction Using Evolutionary Algorithms
|
journal | December 2020 |
Contact Map based Crystal Structure Prediction using Global Optimization | preprint | January 2020 |
Similar Records
Predicting energy and stability of known and hypothetical crystals using graph neural network
Predicting Lattice Vibrational Frequencies Using Deep Graph Neural Networks