Inverse design of crystal structures for multicomponent systems
Source abstract
Abstract
We developed an inverse design framework, constrained crystal deep convolutional generative adversarial networks (CCDCGAN), enabling automated generation of stable multicomponent crystal structures. Their formation energy can be optimized in the latent space based on reversible crystal images with continuous representation. After training by 52,615 crystal structures from Materials Project, the CCDCGAN model is able to generate new crystal structure. It is demonstrated that when 9160 crystal structures are generated by CCDCGAN, 8310 of them have not been reported in the training set. Detailed analysis on 15 selected materials systems of the generated structures reveals that unreported crystal structures below the convex hull can be discovered in 6 of them. Moreover, the generation efficiency can be further improved by considering extra hypothetical structures in the training. This paves the way to perform inverse design of multicomponent materials with possible multi-objective optimization.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Thermography and Photoacoustic Techniques · X-ray Diffraction in Crystallography
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. New frontiers for the materials genome initiative10.1038/s41524-019-0173-4 ↗
2. Cabinet-level National Science and Technology Council, Materials genome initiative for global competitiveness, (2011).
3. Inverse molecular design using machine learning: generative models for matter engineering10.1126/science.aat2663 ↗
4. Machine-enabled inverse design of inorganic solid materials: promises and challenges10.1039/D0SC00594K ↗
5. Materials informatics: from the atomic-level to the continuum10.1016/j.actamat.2019.01.051 ↗
6. Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD)10.1007/s11837-013-0755-4 ↗
7. A high-throughput infrastructure for density functional theory calculations10.1016/j.commatsci.2011.02.023 ↗
8. High-throughput computational screening of new Li-Ion battery anode materials10.1002/aenm.201200593 ↗
9. High-throughput design of magnetic materials
10. A complete catalogue of high-quality topological materials10.1038/s41586-019-0954-4 ↗
11. High-throughput screening and automated processing toward novel topological insulators10.1021/acs.jpclett.8b02800 ↗
12. Structure prediction drives materials discovery10.1038/s41578-019-0101-8 ↗
13. CALYPSO: a method for crystal structure prediction10.1016/j.cpc.2012.05.008 ↗
14. USPEX—evolutionary crystal structure prediction10.1016/j.cpc.2006.07.020 ↗
15. Uranium polyhydrides at moderate pressures: prediction, synthesis, and expected superconductivity | Science Advances, (n.d.). https://advances.sciencemag.org/content/4/10/eaat9776?utm_source=TrendMD&utm_medium=cpc&utm_campaign=TrendMD_1 (accessed March 31, 2021).
16. CALYPSO structure prediction method and its wide application10.1016/j.commatsci.2015.09.037 ↗
17. Coevolutionary search for optimal materials in the space of all possible compounds
18. Commentary: the materials project: a materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
19. The open quantum materials database (OQMD): assessing the accuracy of DFT formation energies10.1038/npjcompumats.2015.10 ↗
20. NOMAD: the FAIR concept for big data-driven materials science10.1557/mrs.2018.208 ↗
21. AFLOW: an automatic framework for high-throughput materials discovery10.1016/j.commatsci.2012.02.005 ↗
22. Crystal structure prediction accelerated by Bayesian optimization
23. Bayesian optimization for materials design with mixed quantitative and qualitative variables10.1038/s41598-020-60652-9 ↗
24. Inverse design of solid-state materials via a continuous representation10.1016/j.matt.2019.08.017 ↗
25. Generative adversarial networks for crystal structure prediction10.1021/acscentsci.0c00426 ↗
26. Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures10.1038/s41524-021-00526-4 ↗
27. Automatic chemical design using a data-driven continuous representation of molecules10.1021/acscentsci.7b00572 ↗
28. J. Hoffmann, L. Maestrati, Y. Sawada, J. Tang, J.M. Sellier, Y. Bengio, Data-driven approach to encoding and decoding 3-D crystal structures, ArXiv:1909.00949 [Cond-Mat, Physics:physics, Stat]. (2019). http://arxiv.org/abs/1909.00949 (accessed January 18, 2021).
29. Comparing molecules and solids across structural and alchemical space10.1039/C6CP00415F ↗
30. K. Kaufmann, C. Zhu, A.S. Rosengarten, D. Maryanovsky, T.J. Harrington, E. Marin, K.S. Vecchio, Paradigm shift in electron-based crystallography via machine learning, ArXiv:1902.03682 [Cond-Mat]. (2019). http://arxiv.org/abs/1902.03682 (accessed June 4, 2019).
31. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties10.1103/PhysRevLett.120.145301 ↗
32. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery
33. D.P. Kingma, M. Welling, Auto-encoding variational bayes, ArXiv:1312.6114 [Cs, Stat]. (2014). http://arxiv.org/abs/1312.6114 (accessed March 31, 2021).
34. Generative adversarial nets
35. D. Schwalbe-Koda, R. Gómez-Bombarelli, Generative models for automatic chemical design, ArXiv:1907.01632 [Physics, Stat]. (2019). http://arxiv.org/abs/1907.01632 (accessed September 5, 2019).
36. Z. Ren, J. Noh, S. Tian, F. Oviedo, G. Xing, Q. Liang, A. Aberle, Y. Liu, Q. Li, S. Jayavelu, K. Hippalgaonkar, Y. Jung, T. Buonassisi, Inverse design of crystals using generalized invertible crystallographic representation, ArXiv:2005.07609 [Cond-Mat, Physics:physics]. (2020). http://arxiv.org/abs/2005.07609 (accessed June 25, 2020).
37. 3-D inorganic crystal structure generation and property prediction via representation learning10.1021/acs.jcim.0c00464 ↗
38. A. Nouira, N. Sokolovska, J.C. Crivello, CrystalGAN: learning to discover crystallographic structures with generative adversarial networks, ArXiv:1810.11203 [Cs, Stat]. (2018). http://arxiv.org/abs/1810.11203 (accessed September 9, 2019).
39. Inverse design of porous materials using artificial neural networks10.1126/sciadv.aax9324 ↗
40. D.P. Kingma, M. Welling, Auto-encoding variational bayes, ArXiv:1312.6114 [Cs, Stat]. (2013). http://arxiv.org/abs/1312.6114 (accessed September 11, 2019).
41. 1990
42. Formation enthalpies by mixing GGA and GGA $+$ $U$ calculations10.1103/PhysRevB.84.045115 ↗