Artificial intelligence-driven materials science: Evolution, framework, dilemmas, and breakthroughs

Authors

Yanglili ZHOU, Dongguan Institute of Materials Science and Technology, Chinese Academy of Sciences, Dongguan 523830, China; Songshan Lake Materials Laboratory, Dongguan 523830, ChinaFollow
Weihua WANG, Dongguan Institute of Materials Science and Technology, Chinese Academy of Sciences, Dongguan 523830, China
Ziwei ZHAO, Dongguan Institute of Materials Science and Technology, Chinese Academy of Sciences, Dongguan 523830, China; Songshan Lake Materials Laboratory, Dongguan 523830, ChinaFollow

Keywords

AIMS, artificial intelligence, materials science

Document Type

Disciplinary Development

Abstract

Artificial intelligence-driven materials science (AIMS) represents a revolutionary and disruptive paradigm in materials research, promising to fundamentally break through the traditional bottlenecks of research cycles and efficiency. Historically, the evolution of materials science research paradigms from empirical trial and error, theoretical modeling, and computational simulation to the new data-driven stage has been driven by innovations in cognitive tools and methods. Currently, artificial intelligence, as a disruptive cognitive tool, is fundamentally reconstructing the core elements and interaction logic of materials science: the research process achieves intelligent iteration and full-process closed-loop; the capabilities of researchers are reshaped and teams are organized; and the depth and breadth of research objects are expanded and precise demands are locked in, thus forming a new model and paradigm for materials research. This is precisely the manifestation of the emergence and development of new quality productivity in the field of materials science. Nevertheless, China still faces bottlenecks such as multi-scale modeling, multi-modal data fusion, and model generalization in the AIMS field. These need to be overcome through solidifying the data foundation, tackling core technologies, and improving ecological support, in order to achieve a fundamental transformation of the materials science research paradigm. This study reviews the evolution and current status of research paradigms in materials science, constructs a theoretical framework for the transformation of elements in AIMS, analyzes the difficulties and bottlenecks faced by AIMS, and proposes strategic paths and strategies for promoting the development of AIMS in China, with the aim of providing theoretical and practical references for accelerating the formation of the AIMS paradigm system and fostering new material productivity.

First page

393

Last Page

405

Language

Chinese

Publisher

Bulletin of Chinese Academy of Sciences

References

1. Amil M, Simon B, Samuel S. Scaling deep learning for materials discovery. Nature, 2023, 624: 80-85.

2. Claudio Z, Robert P, Daniel Z, et al. A generative model for inorganic materials design. Nature, 2025, 639: 624-632.

3. Nathan J. An autonomous laboratory for the accelerated synthesis of novel materials. Nature, 2023, 624: 86-91.

4. Zhong X, Gallagher B, Liu S, et al. Explainable machine learning in materials science. NPJ Computational Materials, 2022, 8: 204.

5. Xu P, Ji X, Li M, et al. Small data machine learning in materials science. NPJ Computational Materials, 2023, 9: 42.

6. Sun W, Bartel C J, Arca E, et al. A map of the inorganic ternary metal nitrides. Nature Materials, 2019, 18(7): 732-739.

7. Li M X, Zhao S F, Lu Z, et al. High-temperature bulk metallic glasses developed by combinatorial methods. Nature, 2019, 569: 99-103.

8. Heisenberg W. Über quantentheoretische Umdeutung kinematischer und mechanischer Beziehungen. Zeitschrift für Physik, 1925, 33: 879-893. Heisenberg W. On quantum theoretical reinterpretation of kinematic and mechanical relations. Journal of Physics, 1925, 33: 879-893. (in German)

9. Pauli W. Zur Quantenmechanik des Mehr-elektronenproblems. Zeitschrift für Physik, 1928, 49(11), 616-625. Pauli W. Quantum mechanics of the multi-electron problem. Journal of Physics, 1928, 49(11), 616-625. (in German)

10. Pauling L. The nature of the chemical bond. Application of results obtained from the quantum mechanics and from a theory of paramagnetic susceptibility to the structure of molecules. Journal of the American Chemical Society, 1931, 53(4): 1367-1400.

11. Volterra V. Sur l'équilibre des corps élastiques multiplement connexes. Annales scientifiques de l'École Normale Supérieure, 1907, 24: 401-517. Volterra V. On the Balance of Multiplely Connected Elastic Bodies. Scientific Annals of the École Normale Supérieure, 1907, 24: 401-517. (in French)

12. Taylor G I. The mechanism of plastic deformation of crystals. Containing Papers of a Mathematical and Physical Character, 1934, 145: 362-387.

13. Polanyi M. On a kind of dislocation and its role in hardening. Zeitschrift für Physik, 1934, 83(1): 1-9.

14. Orowan E. Plasticity of Crystals. Zeitschrift für Physik, 1934, 89(5): 605-613. Orowan E. Plasticity of Crystals. Journal of Physics, 1934, 89(5): 605-613. (in German)

15. Hohenberg P, Kohn W. Inhomogeneous electron gas. Physical Review, 1964, 136(3B): 864-871.

16. Rahman A. Correlations in the motion of atoms in liquid argon. Physical Review, 1964, 136(2A): 405-411.

17. Jain A, Ong S P, Hautier G, et al. Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL Materials, 2013, 1(1): 011002.

18. 刘淼, 王宗国, 王彦棡. 材料科学领域数据与人工智能模型发展与创新应用. 中国科研信息化蓝皮书2024——数据与智能驱动的科研范式变革, 2025, 1(6): 252-263. Liu M, Wang Z G, Wang Y G. Development and Innovative Applications of Data and Artificial Intelligence Models in the Field of Materials Science. Blue Book of China’s Research Informatization 2024—Data and Intelligence Driven Paradigm Transformation in Scientific Research, 2025, 1(6): 252-263. (in Chinese)

19. De Pablo J J, Jackson N E, Webb M A, et al. New frontiers for the materials genome initiative. NPJ Computational Materials, 2019, 5(1): 41.

20. Raccuglia P, Kim H, Jain A., et al.Machine-learning-assisted materials discovery using failed experiments . Nature, 2016, 533: 73-76. *Corresponding author

21. Merchant A, Batzner S, Schoenholz S S, et al. Scaling deep learning for materials discovery. Nature, 2023, 624: 80-85.

22. Szymanski N J, Rendy B, Fei Y, et al. An autonomous laboratory for the accelerated synthesis of novel materials. Nature, 2023, 624: 86-91.

23. Li H, Wang Z, Zou N, et al. Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation. Nature Computational Science, 2022, 2(6): 367-377.

24. Zhong Y, Yu H, Su M, et al. Transferable equivariant graph neural networks for the Hamiltonians of molecules and solids. NPJ Computational Materials, 2023, 9(1): 182.

25. 徐锦程, 陈林江, 江俊. 数据智能驱动的机器化学家探索.中国科学: 化学, 2025, 55(6): 1606-1622. Xu J C, Chen L J, Jiang J. Data-intelligent-driven exploration of robotic chemist systems. Chimica, 2025, 55(6): 1606-1622. (in Chinese)

26. Miao L, Sheng M. Atomly.net materials database and its application in inorganic chemistry. Scientia Sinica Chimica, 2023, 53 (1): 19-25.

27. Zhang S, Tian J, Liu S,et al. Constructing material network representations for intelligent amorphous alloy design. National science review, 2025, 12(11): nwaf398.

Recommended Citation

ZHOU, Yanglili; WANG, Weihua; and ZHAO, Ziwei (2026) "Artificial intelligence-driven materials science: Evolution, framework, dilemmas, and breakthroughs," Bulletin of Chinese Academy of Sciences (Chinese Version): Vol. 41 : Iss. 2 , Article 16.
DOI: https://doi.org/10.3724/j.issn.1000-3045.20250827001
Available at: https://bulletinofcas.researchcommons.org/journal/vol41/iss2/16