Design of New Inorganic Crystals with the Desired Composition Using Deep LearningClick to copy article linkArticle link copied!
- Seunghee HanSeunghee HanDepartment of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of KoreaMore by Seunghee Han
- Jaewan LeeJaewan LeeLG AI Research, ISC, 30, Magokjungang 10-ro, Gangseogu, Seoul 07796, Republic of KoreaMore by Jaewan Lee
- Sehui HanSehui HanLG AI Research, ISC, 30, Magokjungang 10-ro, Gangseogu, Seoul 07796, Republic of KoreaMore by Sehui Han
- Seyed Mohamad MoosaviSeyed Mohamad MoosaviDepartment of Chemical Engineering & Applied Chemistry, University of Toronto, Ontario M5S 3E5, CanadaMore by Seyed Mohamad Moosavi
- Jihan KimJihan KimDepartment of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of KoreaMore by Jihan Kim
- Changyoung Park*Changyoung Park*Email: [email protected]LG AI Research, ISC, 30, Magokjungang 10-ro, Gangseogu, Seoul 07796, Republic of KoreaMore by Changyoung Park
Abstract
New solid-state materials have been discovered using various approaches from atom substitution in density functional theory (DFT) to generative models in machine learning. Recently, generative models have shown promising performance in finding new materials. Crystal generation with deep learning has been applied in various methods to discover new crystals. However, most generative models can only be applied to materials with specific elements or generate structures with random compositions. In this work, we developed a model that can generate crystals with desired compositions based on a crystal diffusion variational autoencoder. We generated crystal structures for 14 compositions of three types of materials in different applications. The generated structures were further stabilized using DFT calculations. We found the most stable structures in the existing database for all but one composition, even though eight compositions among them were not in the data set trained in a crystal diffusion variational autoencoder. This substantiates the prospect of the generation of an extensive range of compositions. Finally, 205 unique new crystal materials with energy above hull <100 meV/atom were generated. Moreover, we compared the average formation energy of the crystals generated from five compositions, two of which were hypothetical, with that of traditional methods like atom substitution and a generative model. The generated structures had lower formation energy than those of other models, except for one composition. These results demonstrate that our approach can be applied stably in various fields to design stable inorganic materials based on machine learning.
Cited By
Smart citations by scite.ai include citation statements extracted from the full text of the citing article. The number of the statements may be higher than the number of citations provided by ACS Publications if one paper cites another multiple times or lower if scite has not yet processed some of the citing articles.
This article is cited by 7 publications.
- Zian Chen, Zijun Meng, Tao He, Haichao Li, Jian Cao, Lina Xu, Hongping Xiao, Yueyu Zhang, Xiao He, Guoyong Fang. Crystal Structure Prediction Meets Artificial Intelligence. The Journal of Physical Chemistry Letters 2025, 16
(10)
, 2581-2591. https://doi.org/10.1021/acs.jpclett.4c03727
- Ahmed Elrashidy, James Della-Giustina, Jia-An Yan. Accelerated Data-Driven Discovery and Screening of Two-Dimensional Magnets Using Graph Neural Networks. The Journal of Physical Chemistry C 2024, 128
(14)
, 6007-6018. https://doi.org/10.1021/acs.jpcc.3c07246
- Arsen Sultanov, Jean-Claude Crivello, Tabea Rebafka, Nataliya Sokolovska. Data-Driven Score-Based Models for Generating Stable Structures with Adaptive Crystal Cells. Journal of Chemical Information and Modeling 2023, 63
(22)
, 6986-6997. https://doi.org/10.1021/acs.jcim.3c00969
- Sadman Sadeed Omee, Nihang Fu, Rongzhi Dong, Ming Hu, Jianjun Hu. Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study. npj Computational Materials 2024, 10
(1)
https://doi.org/10.1038/s41524-024-01316-4
- Xiaoshan Luo, Zhenyu Wang, Pengyue Gao, Jian Lv, Yanchao Wang, Changfeng Chen, Yanming Ma. Deep learning generative model for crystal structure prediction. npj Computational Materials 2024, 10
(1)
https://doi.org/10.1038/s41524-024-01443-y
- Chenglong Qin, Jinde Liu, Shiyin Ma, Jiguang Du, Gang Jiang, Liang Zhao. Inverse design of semiconductor materials with deep generative models. Journal of Materials Chemistry A 2024, 12
(34)
, 22689-22702. https://doi.org/10.1039/D4TA02872D
- Hongni Jin, Kenneth M. Merz. Toward AI/ML-assisted discovery of transition metal complexes. 2024, 225-267. https://doi.org/10.1016/bs.arcc.2024.10.003
Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to reflect usage leading up to the last few days.
Citations are the number of other articles citing this article, calculated by Crossref and updated daily. Find more information about Crossref citation counts.
The Altmetric Attention Score is a quantitative measure of the attention that a research article has received online. Clicking on the donut icon will load a page at altmetric.com with additional details about the score and the social media presence for the given article. Find more information on the Altmetric Attention Score and how the score is calculated.