1.宁夏大学 物理学院,宁夏 银川 750021
2.宁夏大学 信息工程学院,宁夏 银川 750021
3.宁夏大学 材料与新能源学院,宁夏 银川 750021
申奥(1998—),男,博士研究生,主要从事AI for Science研究,(电子信箱)shen1ao1@stu.nxu.edu.cn。
刘昊(1988—),男,教授,博士,博士研究生导师,主要从事计算机视觉与模式识别、AI for Science研究,(电子信箱)liuhao@nxu.edu.cn。
收稿:2025-04-06,
纸质出版:2026-03-15
移动端阅览
申奥,马梅,高乐,等.人工智能在材料发现中的应用[J].宁夏大学学报(自然科学版中英文),2026,47(2):116-157.
SHEN Ao,MA Mei,GAO Le,et al.Application of Artificial Intelligence in Materials Discovery[J].Journal of Ningxia University (Natural Science Edition in Chinese and English),2026,47(2):116-157.
申奥,马梅,高乐,等.人工智能在材料发现中的应用[J].宁夏大学学报(自然科学版中英文),2026,47(2):116-157. DOI: 10.20176/j.cnki.nxdz.20260205.
SHEN Ao,MA Mei,GAO Le,et al.Application of Artificial Intelligence in Materials Discovery[J].Journal of Ningxia University (Natural Science Edition in Chinese and English),2026,47(2):116-157. DOI: 10.20176/j.cnki.nxdz.20260205.
综述了人工智能(AI)在材料发现领域的应用现状,重点探讨其在材料表征、材料生成及属性预测三大核心方向的最新研究进展。首先,系统阐述材料表征中的描述符设计原理,聚焦如何将材料的微观结构、化学组成等复杂信息转化为机器可处理的量化特征。其次,深入分析生成模型在材料逆向设计中的技术路径,详细探讨生成对抗网络(GAN)、图神经网络(GNN)、变分自编码器(VAE)、扩散模型及大语言模型(LLMs)的具体应用场景与技术优势。再次,综述基于GNN与Transformer架构的材料属性预测技术,从预测精度、计算效率及模型可解释性3个维度总结各类方法的性能表现。最后,剖析AI驱动材料发现面临的核心挑战与发展潜力,并对未来研究方向进行展望。
This paper reviews the application of artificial intelligence (AI) in materials discovery, focusing on the latest advancements in three core areas: material characterization, generation, and property prediction. First, the principles of descriptor design for material characterization were introduced, emphasizing the transformation of complex information, such as micro-structure and chemical composition, into machine-readable quantitative features. Then, an in-depth analysis of the technical pathways employed by generative models in the inverse design of materials was provided, detailing the specific applications and advantages of the generative adversarial networks (GANs), graph neural networks (GNNs), variational autoencoders (VAEs) diffusion models, and large language models (LLMs). Furthermore, material property prediction technologies based on GNN and Transformer architectures were reviewed, summarizing the performance of these methods in terms of prediction accuracy, computational efficiency, and model interpretability. Finally, the core challenges and potentials of AI-driven materials discovery were discussed, offering insights into future research directions.
PATHAK Y , JUNEJA K S , VARMA G , et al . Deep learning enabled inorganic material generator [J]. Physical Chemistry Chemical Physics , 2020 , 22 ( 46 ): 26935 - 26943 .
WEININGER D , WEININGER A , WEININGER J L . SMILES. 2:Algorithm for generation of unique SMILES notation [J]. Journal of Chemical Information and Computer Sciences , 1989 , 29 ( 2 ): 97 - 101 .
GÓMEZ-BOMBARELLI R , WEI J N , DUVENAUD D , et al . Automatic chemical design using a data-driven continuous representation of molecules [J]. ACS Central Science , 2018 , 4 ( 2 ): 268 - 276 .
SKINNIDER M A . Invalid SMILES are beneficial rather than detrimental to chemical language models [J]. Nature Machine Intelligence , 2024 , 6 ( 4 ): 437 - 448 .
KIM S , CHEN Jie , CHENG Tiejun , et al . PubChem 2023 update [J]. Nucleic Acids Research , 2023 , 51 ( D1 ): D1373 - D1380 .
MICHELS J , BANDARUPALLI R , AHANGAR AKBARI A , et al . Natural language processing methods for the study of protein-ligand interactions [J]. Journal of Chemical Information and Modeling , 2025 , 65 ( 5 ): 2191 - 2213 .
GE Wei , DE SILVA R , FAN Yanan , et al . Machine learning in polymer research [J]. Advanced Materials , 2025 , 37 ( 11 ): 2413695 . DOI: 10.1002/adma.202413695 http://dx.doi.org/10.1002/adma.202413695 .
DANGAYACH R , JEONG N , DEMIREL E , et al . Machine learning-aided inverse design and discovery of novel polymeric materials for membrane separation [J]. Environmental Science & Technology , 2025 , 59 ( 2 ): 993 - 1012 .
DALMAU D , ALEGRE-REQUENA J V . ROBERT: Bridging the gap between machine learning and chemistry [J]. WIREs Computational Molecular Science , 2024 , 14 ( 5 ): e1733 . DOI: 10.1002/wcms.1733 http://dx.doi.org/10.1002/wcms.1733 .
SHI Yunfei , YANG Zhengxin , MA Sicong , et al . Machine learning for chemistry: Basics and applications [J]. Engineering , 2023 , 27 : 70 - 83 .
EHRT C , KRAUSE B , SCHMIDT R , et al . SMARTS.plus:A toolbox for chemical pattern design [J]. Molecular Informatics , 2020 , 39 ( 12 ): e2000216 . DOI: 10.1002/minf.202000216 http://dx.doi.org/10.1002/minf.202000216 .
KRENN M , HÄSE F , NIGAM A , et al . Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation [J]. Machine Learning: Science and Technology , 2020 , 1 ( 4 ): 045024 . DOI: 10. 1088/2632-2153/aba947 http://dx.doi.org/10.1088/2632-2153/aba947 .
LO A , POLLICE R , NIGAM A , et al . Recent advances in the self-referencing embedded strings (SELFIES) library [J]. Digital Discovery , 2023 , 2 ( 4 ): 897 - 908 .
LI Yibo , ZHANG Liangren , LIU Zhenming . Multi-objective de novo drug design with conditional graph generative model [J]. Journal of Cheminformatics , 2018 , 10 ( 1 ): 33 . DOI: 10.1186/s13321-018-0287-6 http://dx.doi.org/10.1186/s13321-018-0287-6 .
TODESCHINI R , CONSONNI V . Molecular descriptors for chemoinformatics [M]. 2nd ed . Weinheim : Wiley-VCH , 2009 .
LIM J , RYU S , KIM J W , et al . Molecular generative model based on conditional variational autoencoder for de novo molecular design [J]. Journal of Cheminformatics , 2018 , 10 ( 1 ): 31 . DO I: 10.1186/s13321- 018-0286-7 http://dx.doi.org/10.1186/s13321-018-0286-7 .
WAN Yue , WU Jialu , HOU Tingjun , et al . Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation [J]. Nature Communications , 2025 , 16 ( 1 ): 413 . DOI: 10.1038/ s41467-024-55082-4 http://dx.doi.org/10.1038/s41467-024-55082-4 .
FANG Xiaomin , LIU Lihang , LEI Jieqiong , et al . Geometry-enhanced molecular representation learning for property prediction [J]. Nature Machine Intelligence , 2022 , 4 ( 2 ): 127 - 134 .
CHEN Chi , YE Weike , ZUO Yunxing , et al . Graph networks as a universal machine learning framework for molecules and crystals [J]. Chemistry of Materials , 2019 , 31 ( 9 ): 3564 - 3572 .
KIM S , NOH J , GU G H , et al . Generative adversarial networks for crystal structure prediction [J]. ACS Central Science , 2020 , 6 ( 8 ): 1412 - 1420 .
RUPP M , TKATCHENKO A , MÜLLER K R , et al . Fast and accurate modeling of molecular atomization energies with machine learning [J]. Physical Review Letters , 2012 , 108 ( 5 ): 058301 . DOI: 10.1103/ PhysRevLett.108.058301 http://dx.doi.org/10.1103/PhysRevLett.108.058301 .
HANSEN K , MONTAVON G , BIEGLER F , et al . Assessment and validation of machine learning methods for predicting molecular atomization energies [J]. Journal of Chemical Theory and Computation , 2013 , 9 ( 8 ): 3404 - 3419 .
MONTAVON G , RUPP M , GOBRE V , et al . Machine learning of molecular electronic properties in chemical compound space [J]. New Journal of Physics , 2013 , 15 ( 9 ): 095003 . DOI: 10.1088/1367-2630/15/9/095003 http://dx.doi.org/10.1088/1367-2630/15/9/095003 .
HANSEN K , BIEGLER F , RAMAKRISHNAN R , et al . Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space [J]. The Journal of Physical Chemistry Letters , 2015 , 6 ( 12 ): 2326 - 2331 .
FABER F , LINDMAA A , VON LILIENFELD O A , et al . Crystal structure representations for machine learning models of formation energies [J]. International Journal of Quantum Chemistry , 2015 , 115 ( 16 ): 1094 - 1101 .
BARKER J , BULIN J , HAMAEKERS J , et al . LC-GAP: Localized coulomb descriptors for the Gaussian approximation potential [M]// Scientific Computing and Algorithms in Industrial Simulations . Cham : Springer International Publishing , 2017 : 25 - 42 .
HIMANEN L , JÄGER M O J , MOROOKA E V , et al . DScribe: Library of descriptors for machine learning in materials science [J]. Computer Physics Communications , 2020 , 247 : 106949 . DOI: 10.1016/j.cpc.2019. 106949 http://dx.doi.org/10.1016/j.cpc.2019.106949 .
HUO Haoyan , RUPP M . Unified representation of molecules and crystals for machine learning [J]. Machine Learning: Science and Technology , 2022 , 3 ( 4 ): 045017 . DOI: 10.1088/2632-2153/aca005 http://dx.doi.org/10.1088/2632-2153/aca005 .
ISAYEV O , OSES C , TOHER C , et al . Universal fragment descriptors for predicting properties of inorganic crystals [J]. Nature Communications , 2017 , 8 : 15679 . DOI: 10.1038/ncomms15679 http://dx.doi.org/10.1038/ncomms15679 .
SCHMIDT J , MARQUES M R G , BOTTI S , et al . Recent advances and applications of machine learning in solid-state materials science [J]. npj Computational Materials , 2019 , 5 : 83 . DOI: 10.1038/s41524-019-0221-0 http://dx.doi.org/10.1038/s41524-019-0221-0 .
WENG Mouyi , WANG Zhi , QIAN Guoyu , et al . Identify crystal structures by a new paradigm based on graph theory for building materials big data [J]. Science China Chemistry , 2019 , 62 ( 8 ): 982 - 986 .
CANG Zixuan , WEI Guowei . Integration of element specific persistent homology and machine learning for protein-ligand binding affinity prediction [J]. International Journal for Numerical Methods in Biomedical Engineering , 2018 , 34 ( 2 ): e2914 . DOI: 10.1002/cnm.2914 http://dx.doi.org/10.1002/cnm.2914 .
CANG Zixuan , WEI Guowei . Analysis and prediction of protein folding energy changes upon mutation by element specific persistent homology [J]. Bioinformatics , 2017 , 33 ( 22 ): 3549 - 3557 .
CANG Zixuan , WEI Guowei . TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions [J]. PLoS Computational Biology , 2017 , 13 ( 7 ): e1005690 . DOI: 10.1371/journal.pcbi.1005690 http://dx.doi.org/10.1371/journal.pcbi.1005690 .
WU Kedi , ZHAO Zhixiong , WANG Renxiao , et al . TopP-S: Persistent homology-based multi-task deep neural networks for simultaneous predictions of partition coefficient and aqueous solubility [J]. Journal of Computational Chemistry , 2018 , 39 ( 20 ): 1444 - 1454 .
JIANG Yi , CHEN Dong , CHEN Xin , et al . Topological representations of crystalline compounds for the machine-learning prediction of materials properties [J]. npj Computational Materials , 2021 , 7 : 28 . DOI: 10. 1038/s41524-021-00493-w http://dx.doi.org/10.1038/s41524-021-00493-w .
CHEN Xin , CHEN Dong , WENG Mouyi , et al . Topology-based machine learning strategy for cluster structure prediction [J]. The Journal of Physical Chemistry Letters , 2020 , 11 ( 11 ): 4392 - 4401 .
LEE Y J , BARTHEL S D , DŁOTKO P , et al . Quantifying similarity of pore-geometry in nanoporous materials [J]. Nature Communications , 2017 , 8 : 15396 . DOI: 10.1038/ncomms15396 http://dx.doi.org/10.1038/ncomms15396 .
COURT C J , YILDIRIM B , JAIN A , et al . 3-D inorganic crystal structure generation and property prediction via representation learning [J]. Journal of Chemical Information and Modeling , 2020 , 60 ( 10 ): 4518 - 4535 .
NOH J , KIM J , STEIN H S , et al . Inverse design of solid-state materials via a continuous representation [J]. Matter , 2019 , 1 ( 5 ): 1370 - 1384 .
DAMEWOOD J , KARAGUESIAN J , LUNGER J R , et al . Representations of materials for machine learning [J]. Annual Review of Materials Research , 2023 , 53 : 399 - 426 .
MORTAZAVI B . Recent advances in machine learning-assisted multiscale design of energy materials [J]. Advanced Energy Materials , 2025 , 15 ( 9 ): 2403876 . DOI: 10.1002/aenm.202403876 http://dx.doi.org/10.1002/aenm.202403876 .
PARK H , LI Zhenzhu , WALSH A . Has generative artificial intelligence solved inverse materials design? [J]. Matter , 2024 , 7 ( 7 ): 2355 - 2367 .
ZILETTI A , KUMAR D , SCHEFFLER M , et al . Insightful classification of crystal structures using deep learning [J]. Nature Communications , 2018 , 9 : 2775 . DOI: 10.1038/s41467-018-05169-6 http://dx.doi.org/10.1038/s41467-018-05169-6 .
REN Zekun , NOH J , TIAN Siyu , et al . Inverse design of crystals using generalized invertible crystallographic representation [EB/OL].( 2020-05-15 )[ 2025-04-06 ]. https://arxiv.org/abs/2005.07609 https://arxiv.org/abs/2005.07609 .
REN Zekun , TIAN S I P , NOH J , et al . An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties [J]. Matter , 2022 , 5 ( 1 ): 314 - 335 .
RAGONE M , SHAHABAZIAN-YASSAR R , MASHAYEK F , et al . Deep learning modeling in microscopy imaging: A review of materials science applications [J]. Progress in Materials Science , 2023 , 138 : 101165 . DOI: 10.1016/j.pmatsci.2023.101165 http://dx.doi.org/10.1016/j.pmatsci.2023.101165 .
LU Shizhao , JAYARAMAN A . Machine learning for analyses and automation of structural characterization of polymer materials [J]. Progress in Polymer Science , 2024 , 153 : 101828 . DOI: 10.1016/j.progpolymsci.2024. 101828 http://dx.doi.org/10.1016/j.progpolymsci.2024.101828 .
BEHLER J , PARRINELLO M . Generalized neural-network representation of high-dimensional potential-energy surfaces [J]. Physical Review Letters , 2007 , 98 ( 14 ): 146401 . DOI: 10.1103/PhysRevLett.98. 146401 http://dx.doi.org/10.1103/PhysRevLett.98.146401 .
BARTÓK A P , KONDOR R , CSÁNYI G . On representing chemical environments [J]. Physical Review B , 2013 , 87 ( 18 ): 184115 . DOI: 10.1103/PhysRevB.87.184115 http://dx.doi.org/10.1103/PhysRevB.87.184115 .
WANG Xijun , YE Sheng , HU Wei , et al . Electric dipole descriptor for machine learning prediction of catalyst surface-molecular adsorbate interactions [J]. Journal of the American Chemical Society , 2020 , 142 ( 17 ): 7737 - 7743 .
CHONG S S , NG Y S , WANG Huiqiong , et al . Advances of machine learning in materials science: Ideas and techniques [J]. Frontiers of Physics , 2023 , 19 ( 1 ): 13501 . DOI: 10.1007/s11467-023-1325-z http://dx.doi.org/10.1007/s11467-023-1325-z .
LI Shunning , LIU Yuanji , CHEN Dong , et al . Encoding the atomic structure for machine learning in materials science [J]. WIREs Computational Molecular Science , 2022 , 12 ( 1 ): e1558 . DOI: 10.1002/wcms. 1558 http://dx.doi.org/10.1002/wcms.1558 .
CHEN Litao , ZHANG Wentao , NIE Zhiwei , et al . Generative models for inverse design of inorganic solid materials [J]. Journal of Materials Informatics , 2021 , 1 : 4 . DOI: 10.20517/jmi.2021.07 http://dx.doi.org/10.20517/jmi.2021.07 .
MANSOURI TEHRANI A , OLIYNYK A O , PARRY M , et al . Machine learning directed search for ultraincompressible, superhard materials [J]. Journal of the American Chemical Society , 2018 , 140 ( 31 ): 9844 - 9853 .
REN Qi , CHEN Dali , RAO Lixiang , et al . Machine-learning-assisted discovery of 212-Zintl-phase compounds with ultra-low lattice thermal conductivity [J]. Journal of Materials Chemistry A , 2024 , 12 ( 2 ): 1157 - 1165 .
POGUE E A , NEW A , MCELROY K , et al . Closed-loop superconducting materials discovery [J]. npj Computational Materials , 2023 , 9 : 181 . DOI: 10.1038/s41524-023-01131-3 http://dx.doi.org/10.1038/s41524-023-01131-3 .
LOTFI S , ZHANG Ziyan , VISWANATHAN G , et al . Targeting productive composition space through machine-learning-directed inorganic synthesis [J]. Matter , 2020 , 3 ( 1 ): 261 - 272 .
AMENT S , AMSLER M , SUTHERLAND D R , et al . Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams [J]. Science Advances , 2021 , 7 ( 51 ): eabg4930 . DOI: 10.1126/ sciadv.abg4930 http://dx.doi.org/10.1126/sciadv.abg4930 .
JHA D , WARD L , YANG Zijiang , et al . IRNet: A general purpose deep residual regression framework for materials discovery [C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . Anchorage, AK, USA : ACM , 2019 : 2385 - 2394 . DOI: 10.1145/3292500.3330932 http://dx.doi.org/10.1145/3292500.3330932 .
GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J]. Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 .
HOFFMANN M , NOÉ F . Generating valid Euclidean distance matrices [EB/OL]. ( 2019-11-15 )[ 2025-04-06 ]. https://arxiv.org/abs/1910.03131 https://arxiv.org/abs/1910.03131 .
DAN Yabo , ZHAO Yong , LI Xiang , et al . Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials [J]. npj Computational Materials , 2020 , 6 : 84 . DOI: 10.1038/s41524-020-00352-0 http://dx.doi.org/10.1038/s41524-020-00352-0 .
SONG Yuqi , SIRIWARDANE E M D , ZHAO Y , et al . Computational discovery of new 2D materials using deep learning generative models [J]. ACS Applied Materials & Interfaces , 2021 , 13 ( 45 ): 53303 - 53313 .
LONG Teng , FORTUNATO N M , OPAHLE I , et al . Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures [J]. npj Computational Materials , 2021 , 7 : 66 . DOI: 10.1038/s41524-021-00526-4 http://dx.doi.org/10.1038/s41524-021-00526-4 .
RADFORD A , METZ L , CHINTALA S . Unsupervised representation learning with deep convolutional generative adversarial networks [EB/OL].( 2016-01-07 )[ 2025-04-06 ]. https://arxiv.org/abs/1511.06434 https://arxiv.org/abs/1511.06434 .
KIM B , LEE S , KIM J . Inverse design of porous materials using artificial neural networks [J]. Science Advances , 2020 , 6 ( 1 ): eaax9324 . DOI: 10.1126/sciadv.aax9324 http://dx.doi.org/10.1126/sciadv.aax9324 .
ZHAO Yong , SIRIWARDANE E M D , WU Zhenyao , et al . Physics guided deep learning for generative design of crystal materials with symmetry constraints [J]. npj Computational Materials , 2023 , 9 : 38 . DOI: 10.1038/s41524-023-00987-9 http://dx.doi.org/10.1038/s41524-023-00987-9 .
CHUN S , ROY S , NGUYEN Y T , et al . Deep learning for synthetic microstructure generation in a materials-by-design framework for heterogeneous energetic materials [J]. Scientific Reports , 2020 , 10 : 13307 . DOI: 10.1038/s41598-020-70149-0 http://dx.doi.org/10.1038/s41598-020-70149-0 .
SHEN S C , BUEHLER M J . Nature-inspired architected materials using unsupervised deep learning [J]. Communications Engineering , 2022 , 1 : 37 . DOI: 10.1038/s44172-022-00037-0 http://dx.doi.org/10.1038/s44172-022-00037-0 .
FUCHS L , FURAT O , FINEGAN D P , et al . Generating multi-scale Li-ion battery cathode particles with radial grain architectures using stereological generative adversarial networks [J]. Communications Materials , 2025 , 6 : 4 . DOI: 10.1038/s43246-024-00728-5 http://dx.doi.org/10.1038/s43246-024-00728-5 .
HSU Y C , YANG Zhenze , BUEHLER M J . Generative design, manufacturing, and molecular modeling of 3D architected materials based on natural language input [J]. APL Materials , 2022 , 10 ( 4 ): 041107 . DOI: 10.1063/ 5.0082338 http://dx.doi.org/10.1063/5.0082338 .
ZHAO Yong , AL-FAHDI M , HU Ming , et al . High-throughput discovery of novel cubic crystal materials using deep generative neural networks [J]. Advanced Science , 2021 , 8 ( 20 ): 2100566 . DOI: 10.1002/advs. 202100566 http://dx.doi.org/10.1002/advs.202100566 .
MAO Yunwei , HE Qi , ZHAO Xuanhe . Designing complex architectured materials with generative adversarial networks [J]. Science Advances , 2020 , 6 ( 17 ): eaaz4169 . DOI: 10.1126/sciadv.aaz4169 http://dx.doi.org/10.1126/sciadv.aaz4169 .
SCARSELLI F , GORI M , TSOI A C , et al . The graph neural network model [J]. IEEE Transactions on Neural Networks , 2009 , 20 ( 1 ): 61 - 80 .
MERCHANT A , BATZNER S , SCHOENHOLZ S S , et al . Scaling deep learning for materials discovery [J]. Nature , 2023 , 624 ( 7990 ): 80 - 85 .
OJIH J , AL-FAHDI M , YAO Yagang , et al . Graph theory and graph neural network assisted high-throughput crystal structure prediction and screening for energy conversion and storage [J]. Journal of Materials Chemistry A , 2024 , 12 ( 14 ): 8502 - 8515 .
YANG Zhenze , BUEHLER M J . High-throughput generation of 3D graphene metamaterials and property quantification using machine learning [J]. Small Methods , 2022 , 6 ( 9 ): 2200537 . DOI: 10.1002/smtd. 202200537 http://dx.doi.org/10.1002/smtd.202200537 .
GOODALL R E A , PARACKAL A S , FABER F A , et al . Rapid discovery of stable materials by coordinate-free coarse graining [J]. Science Advances , 2022 , 8 ( 30 ): eabn4117 . DOI: 10.1126/sciadv. abn4117 http://dx.doi.org/10.1126/sciadv.abn4117 .
ZENI C , PINSLER R , ZÜGNER D , et al . A generative model for inorganic materials design [J]. Nature , 2025 , 639 ( 8055 ): 624 - 632 .
DAS K , KHASTAGIR S , GOYAL P , et al . Periodic materials generation using text-guided joint diffusion model [EB/OL]. ( 2025-03-01 )[ 2025-04-06 ]. https://arxiv.org/abs/2503.00522 https://arxiv.org/abs/2503.00522 .
KLIPFEL A , FREGIER Y , SAYEDE A , et al . Vector field oriented diffusion model for crystal material generation [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 20 ): 22193 - 22201 .
ZUO Yunxing , QIN Mingde , CHEN Chi , et al . Accelerating materials discovery with Bayesian optimization and graph deep learning [J]. Materials Today , 2021 , 51 : 126 - 135 .
KINGMA D P , WELLING M . Auto-encoding variational Bayes [EB/OL].( 2022-12-10 )[ 2025-04-06 ]. https://arxiv.org/abs/1312.6114 https://arxiv.org/abs/1312.6114 .
KIM E , HUANG K , JEGELKA S , et al . Virtual screening of inorganic materials synthesis parameters with deep learning [J]. npj Computational Materials , 2017 , 3 : 53 . DOI: 10.1038/s41524-017-0055-6 http://dx.doi.org/10.1038/s41524-017-0055-6 .
HOFFMANN J , MAESTRATI L , SAWADA Y , et al . Data-driven approach to encoding and decoding 3-D crystal structures [EB/OL].( 2019-09-03 ) [ 2025-04-06 ]. https://arxiv.org/abs/1909.00949 https://arxiv.org/abs/1909.00949 .
XIE Tian , FU Xiang , GANEA O E , et al . Crystal diffusion variational autoencoder for periodic material generation [EB/OL].( 2022-03-14 ) [ 2025-04-06 ]. https://arxiv.org/abs/2110.06197 https://arxiv.org/abs/2110.06197 .
LYNGBY P , THYGESEN K S . Data-driven discovery of 2D materials by deep generative models [J]. npj Computational Materials , 2022 , 8 : 232 . DOI: 10.1038/ s41524-022-00923-3 http://dx.doi.org/10.1038/s41524-022-00923-3 .
PAKORNCHOTE T , CHOOMPHON-ANOMAKHUN N , ARRERUT S , et al . Diffusion probabilistic models enhance variational autoencoder for crystal structure generative modeling [J]. Scientific Reports , 2024 , 14 : 1275 . DOI: 10.1038/s41598-024-51400-4 http://dx.doi.org/10.1038/s41598-024-51400-4 .
YE Caiyuan , WENG Hongming , WU Quansheng . Con-CDVAE:A method for the conditional generation of crystal structures [J]. Computational Materials Today , 2024 , 1 : 100003 . DOI: 10.1016/j.commt. 2024.100003 http://dx.doi.org/10.1016/j.commt.2024.100003 .
LUO Youzhi , LIU Chengkai , JI Shuiwang . Towards symmetry-aware generation of periodic materials [EB/OL]. ( 2024-05-27 )[ 2025-04-06 ]. https://arxiv.org/abs/2307.02707 https://arxiv.org/abs/2307.02707 .
TSUKAUE K , YASUDA K . Crystal structure generation using a diffusion model conditioned on X-ray diffraction intensities without label learning [C]// Proceedings of the 4th AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE) . Philadelphia : AAAI Press , 2025 : 13711 - 13719 . https://ai-2-ase.github.io/papers/22_Tsukaue_Yasuda.pdf https://ai-2-ase.github.io/papers/22_Tsukaue_Yasuda.pdf .
SINHA A , JIA Shuyi , FUNG V . Representation-space diffusion models for generating periodic materials [EB/OL]. ( 2024-08-13 )[ 2025-04-06 ]. https://arxiv.org/abs/2408.07213 https://arxiv.org/abs/2408.07213 .
LEVY D , PANIGRAHI S S , KABA S O , et al . SymmCD: Symmetry-preserving crystal generation with diffusion models [EB/OL].( 2025-05-23 )[ 2025-05-26 ]. https://arxiv.org/abs/2502.03638 https://arxiv.org/abs/2502.03638 .
CHEN J W , GUO J , SCHWALLER P . MatInvent: Reinforcement learning for 3D crystal diffusion generation [C]// Proceedings of the Workshop on AI for Accelerated Materials Design (AI4Mat) at the 13th International Conference on Learning Representations (ICLR 2025) . Singapore : PMLR , 2025 : 1 - 14 . https://openreview.net/forum?id=Ovxfri7l5L https://openreview.net/forum?id=Ovxfri7l5L .
KHASTAGIR S , DAS K , GOYAL P , et al . CrysLDM: Latent diffusion model for crystal material generation [C]// Proceedings of the Workshop on AI for Accelerated Materials Design (AI4Mat) at the 13th International Conference on Learning Representations (ICLR 2025) . Singapore : PMLR , 2025 : 1 - 14 . https://openreview.net/forum?id=mhe4EejyAS https://openreview.net/forum?id=mhe4EejyAS .
PARK J , GILL A P S , MOOSAVI S M , et al . Inverse design of porous materials: A diffusion model approach [J]. Journal of Materials Chemistry A , 2024 , 12 ( 11 ): 6507 - 6514 .
LIM H , LEE K H , YUN G J . Microstructure design of multifunctional particulate composite materials using conditional diffusion models [EB/OL]. ( 2023-01-23 )[ 2025-04-06 ]. https://arxiv.org/abs/2301.09051v1 https://arxiv.org/abs/2301.09051v1 .
GHAFAROLLAHI A , BUEHLER M J . AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence [EB/OL]. ( 2024-07-13 )[ 2025-04-06 ]. https://arxiv.org/abs/ 2407.10022 https://arxiv.org/abs/2407.10022 .
ZHANG Huan , SONG Yu , HOU Ziyu , et al . HoneyComb: A flexible LLM-based agent system for materials science [C]// Findings of the Association for Computational Linguistics: EMNLP 2024 . Miami, Florida, USAAssociation for Computational Linguistics , 2024 : 3369 - 3382 .
KANG Y , KIM J . ChatMOF: An artificial intelligence system for predicting and generating metal-organic frameworks using large language models [J]. Nature Communications , 2024 , 15 : 4705 . DOI: 10.1038/s41467- 024-48998-4 http://dx.doi.org/10.1038/s41467-024-48998-4 .
DING Qianggang , MIRET S , LIU Bang . MatExpert: Decomposing materials discovery by mimicking human experts [EB/OL]. ( 2024-10-26 )[ 2025-04-06 ]. https://arxiv.org/abs/2410.21317 https://arxiv.org/abs/2410.21317 .
CHEN R , MILLER B , SRIRAM A , et al . FlowLLM: Flow matching for material generation with large language models as base distributions [C]// Advances in Neural Information Processing Systems 37 . Vancouver, BC, Canada. Neural Information Processing Systems Foundation, Inc. (NeurIPS) , 2024 : 46025 - 46046 .
MOK D H , BACK S . Generative language model for catalyst discovery [EB/OL].( 2024-07-19 )[ 2025-04-06 ]. https://arxiv.org/abs/2407.14040 https://arxiv.org/abs/2407.14040 .
TIAN Shaohan , JIANG Xue , WANG Weiren , et al . Steel design based on a large language model [J]. Acta Materialia , 2025 , 285 : 120663 . DOI: 10.1016/j.actamat.2024.120663 http://dx.doi.org/10.1016/j.actamat.2024.120663 .
DAS K , SAMANTA B , GOYAL P , et al . CrysXPP: An explainable property predictor for crystalline materials [J]. npj Computational Materials , 2022 , 8 : 43 . DOI: 10.1038/s41524-022-00716-8 http://dx.doi.org/10.1038/s41524-022-00716-8 .
SONG Zixing , MENG Ziqiao , KING I . A diffusion-based pre-training framework for crystal property prediction [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 8 ): 8993 - 9001 .
YAN Keqiang , LIU Yi , LIN Yuchao , et al . Periodic graph transformers for crystal material property prediction [EB/OL]. ( 2022-06-20 )[ 2025-04-06 ]. https://arxiv.org/abs/2209.11807 https://arxiv.org/abs/2209.11807 .
YAN Keqiang , FU Chengxi , QIAN Xiaoning , et al . Complete and efficient graph transformers for crystal material property prediction [EB/OL]. ( 2024-03-19 )[ 2025-04-06 ]. https://arxiv.org/abs/2403.11857 https://arxiv.org/abs/2403.11857 .
TANIAI T , IGARASHI R , SUZUKI Y , et al . Crystalformer: Infinitely connected attention for periodic structure encoding [EB/OL]. ( 2024-03-18 )[ 2025-04-06 ]. https://arxiv.org/abs/2403.11686 https://arxiv.org/abs/2403.11686 .
LEE N , NOH H , KIM S , et al . Density of states prediction of crystalline materials via prompt-guided multi-modal transformer [EB/OL].( 2023-11-23 ) [ 2025-04-06 ]. https://arxiv.org/abs/2311.12856 https://arxiv.org/abs/2311.12856 .
LIN LIN Yuchao , YAN Keqiang , LUO Youzhi , et al . Efficient approximations of complete interatomic potentials for crystal property prediction [EB/OL]. ( 2023-06-17 )[ 2025-04-06 ]. https://arxiv.org/abs/2306. 10045 https://arxiv.org/abs/2306.10045 .
LI Chuannan , LIANG Hanpu , ZHANG Xie , et al . Graph deep learning accelerated efficient crystal structure search and feature extraction [J]. npj Computational Materials , 2023 , 9 : 176 . DOI: 10.1038/s41524- 023- 01122-4 http://dx.doi.org/10.1038/s41524-023-01122-4 .
ZHOU Jie , CUI Ganqu , HU Shengding , et al . Graph neural networks: A review of methods and applications [J]. AI Open , 2020 , 1 : 57 - 81 .
HAN Kai , XIAO An , WU Enhua , et al . Transformer in transformer [C]// Advances in Neural Information Processing Systems . [S.l.] : Neural Information Processing Systems Foundation, Inc. , 2021 , 34 : 15908 - 15919 . https://proceedings.nips.cc/paper_files/ https://proceedings.nips.cc/paper_files/
paper/ 2021 /hash/854d9fca60b4bd07f9bb215d59ef5561-Abstract . html .
SCHÜTT K , KINDERMANS P J , FELIX H E S , et al . SchNet: A continuous-filter convolutional neural network for modeling quantum interactions [J]. Advances in Neural Information Processing Systems , 2017 , 30 : 992 - 1002 .
HUANG Bing , VON LILIENFELD O A . Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity [J]. The Journal of Chemical Physics , 2016 , 145 ( 16 ): 161102 . DOI: 10.1063/1.4964627 http://dx.doi.org/10.1063/1.4964627 .
BARTÓK A P , CSÁNYI G . Gaussian approximation potentials: A brief tutorial introduction [J]. International Journal of Quantum Chemistry , 2015 , 115 ( 16 ): 1051 - 1057 .
SEKO A , TOGO A , HAYASHI H , et al . Prediction of low-thermal-conductivity compounds with first-principles anharmonic lattice-dynamics calculations and Bayesian optimization [J]. Physical Review Letters , 2015 , 115 ( 20 ): 205901 . DOI: 10.1103/PhysRevLett.115.205901 http://dx.doi.org/10.1103/PhysRevLett.115.205901 .
XUE Dezhen , BALACHANDRAN P V , HOGDEN J , et al . Accelerated search for materials with targeted properties by adaptive design [J]. Nature Communications , 2016 , 7 : 11241 . DOI: 10.1038/ ncomms11241 http://dx.doi.org/10.1038/ncomms11241 .
GHIRINGHELLI L M , VYBIRAL J , LEVCHENKO S V , et al . Big data of materials science: critical role of the descriptor [J]. Physical Review Letters , 2015 , 114 ( 10 ): 105503 . DOI: 10.1103/PhysRevLett.114. 105503 http://dx.doi.org/10.1103/PhysRevLett.114.105503 .
ISAYEV O , FOURCHES D , MURATOV E N , et al . Materials cartography: representing and mining materials space using structural and electronic fingerprints [J]. Chemistry of Materials , 2015 , 27 ( 3 ): 735 - 743 .
SEKO A , HAYASHI H , NAKAYAMA K , et al . Representation of compounds for machine-learning prediction of physical properties [J]. Physical Review B , 2017 , 95 ( 14 ): 144110 . DOI: 10.1103/PhysRevB.95. 144110 http://dx.doi.org/10.1103/PhysRevB.95.144110 .
XIE Tian , GROSSMAN J C . Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties [J]. Physical Review Letters , 2018 , 120 ( 14 ): 145301 . DOI: 10.1103/ PhysRevLett.120.145301 http://dx.doi.org/10.1103/PhysRevLett.120.145301 .
LOUIS S Y , ZHAO Yong , NASIRI A , et al . Graph convolutional neural networks with global attention for improved materials property prediction [J]. Physical Chemistry Chemical Physics , 2020 , 22 ( 32 ): 18141 - 18148 .
CHOUDHARY K , DECOST B . Atomistic line graph neural network for improved materials property predictions [J]. npj Computational Materials , 2021 , 7 : 185 . DOI: 10.1038/s41524-021-00650-1 http://dx.doi.org/10.1038/s41524-021-00650-1 .
HUANG Jiao , XING Qianli , JI Jinglong , et al . ADA-GNN: Atom-distance-angle graph neural network for crystal material property prediction [EB/OL].( 2024-01-22 )[ 2025-04-06 ]. https://arxiv.org/abs/2401.11768 https://arxiv.org/abs/2401.11768 .
BATZNER S , MUSAELIAN A , SUN Lixin , et al . E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials [J]. Nature Communications , 2022 , 13 ( 1 ): 2453 . DOI: 10.1038/s41467- 022-29939-5 http://dx.doi.org/10.1038/s41467-022-29939-5 .
HAN Jiaqi , RONG Yu , XU Tingyang , et al . Geometrically equivariant graph neural networks: A survey [EB/OL]. ( 2022-02-22 )[ 2025-04-06 ]. https://arxiv.org/abs/2202.07230 https://arxiv.org/abs/2202.07230 .
KABA S , RAVANBAKHSH S . Equivariant networks for crystal structures [C]// Advances in Neural Information Processing Systems . New Orleans : Neural Information Processing Systems Foundation, Inc. , 2022 : 4150 - 4164 .
HU Weihua , LIU Bowen , GOMES J , et al . Strategies for pre-training graph neural networks [C]// International Conference on Learning Representations . Virtual : ICLR , 2020 : 1 - 18 . https:// openreview. net/forum?id=HJlWWJSFDH https://openreview.net/forum?id=HJlWWJSFDH .
JHA D , CHOUDHARY K , TAVAZZA F , et al . Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning [J]. Nature Communications , 2019 , 10 : 5316 . DOI: 10.1038/s41467-019-13297-w http://dx.doi.org/10.1038/s41467-019-13297-w .
DAS K , SAMANTA B , GOYAL P , et al . CrysGNN: Distilling pre-trained knowledge to enhance property prediction for crystalline materials [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 6 ): 7323 - 7331 .
HINTON G , VINYALS O , DEAN J . Distilling the knowledge in a neural network [EB/OL]. ( 2015-03-09 )[ 2025-04-06 ]. https://arxiv.org/abs/1503. 02531 https://arxiv.org/abs/1503.02531 .
ZHONG Yang , YU Hongyu , GONG Xingao , et al . A general tensor prediction framework based on graph neural networks [J]. The Journal of Physical Chemistry Letters , 2023 , 14 ( 28 ): 6339 - 6348 .
GASTEIGER J , GIRI S , MARGRAF J T , et al . Fast and uncertainty-aware directional message passing for non-equilibrium molecules [EB/OL].( 2020-11-28 )[ 2025-04-06 ]. https://arxiv.org/abs/2011.14115 https://arxiv.org/abs/2011.14115 .
YAN Keqiang , SAXTON A , QIAN Xiaofeng , et al . A space group symmetry informed network for O(3) equivariant crystal tensor prediction [C]// International Conference on Machine Learning . Proceedings of Machine Learning Research . Vienna : PMLR , 2024 : 28271 - 28286 . https://proceedings.mlr.press/v235/yan24d.html https://proceedings.mlr.press/v235/yan24d.html .
MAO Zetian , LI Wenwen , TAN J . Dielectric tensor prediction for inorganic materials using latent information from preferred potential [J]. npj Computational Materials , 2024 , 10 : 265 . DOI: 10.1038/s41524- 024-01450-z http://dx.doi.org/10.1038/s41524-024-01450-z .
KOKER T , QUIGLEY K , TAW E , et al . Higher-order equivariant neural networks for charge density prediction in materials [J]. npj Computational Materials , 2024 , 10 : 161 . DOI: 10.1038/s41524-024-01343-1 http://dx.doi.org/10.1038/s41524-024-01343-1 .
CHEN Pin , XU Zexin , MO Qing , et al . ECD: A machine learning benchmark for predicting enhanced precision electronic charge density in crystalline inorganic materials [C]// International Conference on Learning Representations . Singapore : ICLR , 2025 : 1 - 19 . https://openreview.net/ forum?id=SBCMNc3Mq3 https://openreview.net/forum?id=SBCMNc3Mq3 .
MEREDIG B , AGRAWAL A , KIRKLIN S , et al . Combinatorial screening for new materials in unconstrained composition space with machine learning [J]. Physical Review B , 2014 , 89 ( 9 ): 094104 . DOI: 10.1103/PhysRevB.89.094104 http://dx.doi.org/10.1103/PhysRevB.89.094104 .
OLIYNYK A O , ANTONO E , SPARKS T D , et al . High-throughput machine-learning-driven synthesis of full-Heusler compounds [J]. Chemistry of Materials , 2016 , 28 ( 20 ): 7324 - 7331 .
RAMPRASAD R , BATRA R , PILANIA G , et al . Machine learning in materials informatics: Recent applications and prospects [J]. npj Computational Materials , 2017 , 3 : 54 . DOI: 10.1038/s41524-017- 0056-5 http://dx.doi.org/10.1038/s41524-017-0056-5 .
WARD L , AGRAWAL A , CHOUDHARY A , et al . A general-purpose machine learning framework for predicting properties of inorganic materials [J]. npj Computational Materials , 2016 , 2 : 16028 . DOI: 10.1038/ npjcompumats.2016.28 http://dx.doi.org/10.1038/npjcompumats.2016.28 .
WANG Yingheng , KONG Shufeng , GREGOIRE J M , et al . Conformal crystal graph transformer with robust encoding of periodic invariance [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 1 ): 283 - 291 .
JIN Luozhijie , DU Zijian , SHU Le , et al . Transformer-generated atomic embeddings to enhance prediction accuracy of crystal properties with machine learning [J]. Nature Communications , 2025 , 16 : 1210 . DOI: 10.1038/s41467-025-56481-x http://dx.doi.org/10.1038/s41467-025-56481-x .
KONG Shufeng , RICCI F , GUEVARRA D , et al . Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings [J]. Nature Communications , 2022 , 13 : 949 . DOI: 10.1038/ s41467-022-28543-x http://dx.doi.org/10.1038/s41467-022-28543-x .
FREUND R , ZAREMBA O , ARNAUTS G , et al . The current status of MOF and COF applications [J]. Angewandte Chemie International Edition , 2021 , 60 ( 45 ): 23975 - 24001 .
QIAN Qihui , ASINGER P A , LEE M J , et al . MOF-based membranes for gas separations [J]. Chemical Reviews , 2020 , 120 ( 16 ): 8161 - 8266 .
KANG Y , PARK H , SMIT B , et al . A multi-modal pre-training transformer for universal transfer learning in metal-organic frameworks [J]. Nature Machine Intelligence , 2023 , 5 ( 3 ): 309 - 318 .
WANG Jingqi , LIU Jiapeng , WANG Hongshuai , et al . A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metal-organic frameworks [J]. Nature Communications , 2024 , 15 : 1904 . DOI: 10.1038/s41467-024-46276-x http://dx.doi.org/10.1038/s41467-024-46276-x .
WANG Jiantao , LIU Peitao , ZHU Heyu , et al . Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys [J]. Physical Review Materials , 2025 , 9 ( 5 ): 053805 . DOI: 10.1103/PhysRevMaterials.9.053805 http://dx.doi.org/10.1103/PhysRevMaterials.9.053805 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号