AI-empowered digital design of zeolites: Progress, challenges, and perspectives
Source abstract
Abstract
The rise of artificial intelligence (AI) as a powerful research tool in materials science has been extensively acknowledged. Particularly, exploring zeolites with target properties is of vital significance for industrial applications, integrating AI technologies into zeolite design undoubtedly brings immense promise for the advancements in this field. Here, we provide a comprehensive review in the AI-empowered digital design of zeolites. It showcases the state-of-the-art progress in predicting zeolite-related properties, employing machine learning potentials for zeolite simulations, using generative models for the inverse design, and aiding the experimental synthesis of zeolites. The challenges and perspectives are also discussed, emphasizing the new opportunities at the intersection of AI technologies and zeolites. This review is expected to offer crucial guidance for advancing innovations in materials science through AI in the future.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Zeolite Catalysis and Synthesis · Catalysis and Oxidation Reactions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University 1 , Shanghai 200092,
Center for Phononics and Thermal Energy Science, Shanghai Key Laboratory of Special Artificial Microstructure Materials and Technology, School of Physics Science and Engineering, Tongji University 2 , Shanghai 200092,
School of Biomedical Engineering, Shanghai Jiao Tong University 3 , Shanghai 200240,
Funding
National Natural Science Foundation of China · Interdisciplinary Program of the Shanghai Jiao Tong University · Opening Project of the Shanghai Key Laboratory of Special Artificial Microstucture Materials and Technology · Natural Science Foundation of Shanghai · Program of Shanghai Academic Research Leader
References (100+)
Show source-provided references
1. Ion exchange in zeolites
2. Metal ion exchange by natural and modified zeolites10.1016/s0043-1354(96)00411-3 ↗
3. Ion exchange of ammonium in zeolites: A literature review10.1061/(asce)0733-9372(2001)127:8(673) ↗
4. Gas storage in nanoporous materials10.1002/anie.200703934 ↗
5. Porous adsorbents for vehicular natural gas storage: A review10.1023/a:1009673830619 ↗
6. Zeolites: An emerging material for gas storage and separation applications
7. Hydrogen storage in ion-exchanged zeolites10.1016/j.jallcom.2004.12.193 ↗
8. Heterogeneous catalysis in zeolites, mesoporous silica, and metal–organic frameworks10.1002/adma.201701139 ↗
9. Hierarchically nanoporous zeolites and their heterogeneous catalysis: Current status and future perspectives10.1007/s10562-014-1411-5 ↗
10. Synthesis of mesoporous zeolites and their opportunities in heterogeneous catalysis10.3390/catal11121541 ↗
11. Toward a molecular description of heterogeneous catalysis: Transition metal ions in zeolites10.1016/s0021-9517(02)00110-0 ↗
12. Solar energy application of natural zeolites
13. Photoelectron transfer in zeolite cages and its relevance to solar energy conversion10.1021/jz101500z ↗
14. Natural zeolites in solar energy heating, cooling, and energy storage10.2138/rmg.2001.45.17 ↗
15. Metal sites in zeolites: Synthesis, characterization, and catalysis10.1021/acs.chemrev.2c00315 ↗
16. Ordered porous materials for emerging applications10.1038/nature00785 ↗
17. Our journey in zeolite science10.1016/j.micromeso.2022.112368 ↗
18. Interchain-expanded extra-large-pore zeolites10.1038/s41586-024-07194-6 ↗
19. Novel two-dimensional silicon dioxide with in-plane negative Poisson’s ratio10.1021/acs.nanolett.6b03921 ↗
20. Natural zeolite and minerals
21. Toward a database of hypothetical zeolite structures10.1021/ie0510728 ↗
22. A database of new zeolite-like materials10.1039/c0cp02255a ↗
23. M. Foster and M.Treacy, Atlas of prospective zeolite structures (2005), http://www.hypotheticalzeolites.net.
24. 2007
25. IZA Structure Commission, Database of zeolite structures (2008), http://www.iza-structure.org/databases/.
26. Machine learning for the design and discovery of zeolites and porous crystalline materials10.1016/j.coche.2021.100739 ↗
27. Big-data science in porous materials: Materials genomics and machine learning10.1021/acs.chemrev.0c00004 ↗
28. Machine learning in materials informatics: Recent applications and prospects10.1038/s41524-017-0056-5 ↗
29. A strategy to apply machine learning to small datasets in materials science10.1038/s41524-018-0081-z ↗
30. Machine learning for molecular and materials science10.1038/s41586-018-0337-2 ↗
31. Machine learning in materials science10.1002/inf2.12028 ↗
32. Innovative materials science via machine learning10.1002/adfm.202108044 ↗
33. Machine learning paves the way for high entropy compounds exploration: Challenges, progress, and outlook10.1002/adma.202305192 ↗
34. Understanding the importance of individual samples and their effects on materials data using explainable artificial intelligence10.1039/d3dd00171g ↗
35. M. Wu , S.Yan, and J.Ren, “Hierarchy-boosted funnel learning for identifying semiconductors with ultralow lattice thermal conductivity,” arXiv:2501.06775 (2025).
36. Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations10.1103/physrevb.96.024104 ↗
37. Predicting the band gaps of inorganic solids by machine learning10.1021/acs.jpclett.8b00124 ↗
38. Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm10.1038/s41524-019-0203-2 ↗
39. Predicting lattice thermal conductivity via machine learning: A mini review10.1038/s41524-023-00964-2 ↗
40. A critical examination of robustness and generalizability of machine learning prediction of materials properties10.1038/s41524-023-01012-9 ↗
41. Target-driven design of deep-UV nonlinear optical materials via interpretable machine learning10.1002/adma.202300848 ↗
42. Inverse design of two-dimensional graphene/h-BN hybrids by a regressional and conditional gan10.1016/j.carbon.2020.07.013 ↗
43. Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials10.1038/s41524-020-00352-0 ↗
44. Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry10.1038/s41467-021-25343-7 ↗
45. Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures10.1038/s41524-021-00526-4 ↗
46. Generative adversarial networks for crystal structure prediction10.1021/acscentsci.0c00426 ↗
47. T. Xie , X.Fu, O.-E.Ganea, R.Barzilay, and T.Jaakkola, “Crystal diffusion variational autoencoder for periodic material generation,” arXiv:2110.06197 (2021).
48. Inverse design of next-generation superconductors using data-driven deep generative models10.1021/acs.jpclett.3c01260 ↗
49. Physics guided deep learning for generative design of crystal materials with symmetry constraints10.1038/s41524-023-00987-9 ↗
50. Data-driven discovery of 2D materials by deep generative models10.1038/s41524-022-00923-3 ↗
51. Deep generative design of porous organic cages via a variational autoencoder10.1039/d3dd00154g ↗
52. Machine learning interatomic potentials as emerging tools for materials science10.1002/adma.201902765 ↗
53. Perspective: Machine learning potentials for atomistic simulations10.1063/1.4966192 ↗
54. Large-scale atomic simulation via machine learning potentials constructed by global potential energy surface exploration10.1021/acs.accounts.0c00472 ↗
55. A universal graph deep learning interatomic potential for the periodic table10.1038/s43588-022-00349-3 ↗
56. Hyperactive learning for data-driven interatomic potentials10.1038/s41524-023-01104-6 ↗
57. Stability and equilibrium structures of unknown ternary metal oxides explored by machine-learned potentials10.1021/jacs.3c06210 ↗
58. Thermodynamics of water and ice from a fast and scalable first-principles neuroevolution potential10.1021/acs.jced.3c00561 ↗
59. Machine learning interatomic potentials for amorphous zeolitic imidazolate frameworks10.1039/d3dd00236e ↗
60. Unified deep learning network for enhanced accuracy in predicting thermal conductivity of bilayer graphene, hexagonal boron nitride, and their heterostructures10.1063/5.0201698 ↗
61. Predictive models on potential energies of zeolite ZK-5 using bond weighted information entropy measures10.1016/j.molstruc.2024.137945 ↗
62. Screening cu-zeolites for methane activation using curriculum-based training10.1021/acscatal.3c05275 ↗
63. Active learning of neural network potentials for rare events10.1039/d3dd00216k ↗
64. Machine-learning-assisted materials discovery using failed experiments10.1038/nature17439 ↗
65. Materials synthesis insights from scientific literature via text extraction and machine learning10.1021/acs.chemmater.7b03500 ↗
66. Virtual screening of inorganic materials synthesis parameters with deep learning10.1038/s41524-017-0055-6 ↗
67. Machine learning in computer-aided synthesis planning10.1021/acs.accounts.8b00087 ↗
68. Accelerated development of perovskite-inspired materials via high-throughput synthesis and machine-learning diagnosis10.1016/j.joule.2019.05.014 ↗
69. Nanoparticle synthesis assisted by machine learning10.1038/s41578-021-00337-5 ↗
70. 2023
71. Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science10.1063/1.4946894 ↗
72. Cognitive materials discovery and onset of the 5th discovery paradigm
73. Fifth paradigm in science: A case study of an intelligence-driven material design10.1016/j.eng.2022.06.027 ↗
74. Attention is all you need
75. Bert: Pre-training of deep bidirectional transformers for language understanding
76. Language models are few-shot learners
77. H. Touvron , T.Lavril, G.Izacard, X.Martinet, M.-A.Lachaux, T.Lacroix, B.Rozière, N.Goyal, E.Hambro, F.Azhar, “LLaMA: Open and efficient foundation language models,” arXiv:2302.13971 (2023).
78. S. Bubeck , V.Chandrasekaran, R.Eldan, J.Gehrke, E.Horvitz, E.Kamar, P.Lee, Y. T.Lee, Y.Li, S.Lundberg, “Sparks of artificial general intelligence: Early experiments with GPT-4,” arXiv:2303.12712 (2023).
79. Artificial neural network methods for the prediction of framework crystal structures of zeolites from XRD data10.1007/s00521-010-0386-4 ↗
80. Machine learning approach for structure-based zeolite classification10.1016/j.micromeso.2008.07.027 ↗
81. Identifying zeolite frameworks with a machine learning approach10.1021/jp907017u ↗
82. Perturbation theory–machine learning study of zeolite materials desilication10.1021/acs.jcim.8b00383 ↗
83. Thermodynamic rules for zeolite formation from machine learning based global optimization10.1039/d0sc03918g ↗
84. Machine learning prediction of transition-state energies in small-pore zeolites combining acidity and topology descriptors10.1021/acs.jpcc.4c00082 ↗
85. Quantitative structural description of zeolites by machine learning analysis of infrared spectra10.1021/acs.inorgchem.2c04395 ↗
86. Structural features and zeolite stability: A linearized equation approach10.1021/acs.cgd.3c00893 ↗
87. Structure–energy relationship prediction of the HZSM-5 zeolite with different acid site distributions by the neural network model10.1021/acsomega.3c06689 ↗
88. Systematic study of the thermal properties of zeolitic frameworks10.1021/acs.jpcc.1c03975 ↗
89. Prediction of thermal properties of zeolites through machine learning10.1021/acs.jpcc.1c09737 ↗
90. Systematic investigation of the mechanical properties of pure silica zeolites: Stiffness, anisotropy, and negative linear compressibility10.1039/c3cp51817e ↗
91. Systematic exploration of the mechanical properties of 13621 inorganic compounds10.1039/c9sc01682a ↗
92. Predicting the mechanical properties of zeolite frameworks by machine learning10.1021/acs.chemmater.7b02532 ↗
93. Speeding up discovery of auxetic zeolite frameworks by machine learning10.1021/acs.chemmater.0c00434 ↗
94. Accelerated discovery of zeolite structures with superior mechanical properties via active learning10.1021/acs.jpclett.1c00339 ↗
95. Optimal machine learning feature selection for assessing the mechanical properties of a zeolite framework10.1039/d2cp02949a ↗
96. ZeoNet: 3D convolutional neural networks for predicting adsorption in nanoporous zeolites10.1039/d3ta01911j ↗
97. Nitrogen reduction reaction energy and pathways in metal-zeolites: Deep learning and explainable machine learning with local acidity and hydrogen bonding features10.1039/d2ta03563d ↗
98. Fingerprinting diverse nanoporous materials for optimal hydrogen storage conditions using meta-learning10.1126/sciadv.abg3983 ↗
99. Neural network modeling of adsorption equilibria of mixtures in supercritical fluids10.1021/ie049010p ↗
100. Novel graph machine based QSAR approach for the prediction of the adsorption enthalpies of alkanes on zeolites10.1016/j.cattod.2010.07.029 ↗