Page 218 - Read Online

Wang et al. J. Mater. Inf. 2026, 6, 16 Page 21 of 25

In summary, while MF learning in materials design faces significant challenges, it also offers a unique
confluence of opportunities. Together, these challenges and opportunities define a roadmap for advancing
MF learning as a central tool in next-generation materials discovery.

CONCLUSION
This review provides a structured overview of MF learning methodologies for accelerating data-driven
materials modeling, design, and discovery. We summarize the major classes of MF approaches, including
statistical and parametric models, direct machine learning with fidelity features, correction-based methods
such as co-kriging, deep learning frameworks, and MF active learning and Bayesian optimization. Across
these methods, we highlight how heterogeneous data sources can be integrated to exploit cross-fidelity
correlations, improve predictive accuracy, and reduce reliance on costly HF data. Key practical
considerations are also discussed, including data organization, uncertainty quantification, scalability, and
integration with adaptive sampling. Looking ahead, advances in physics-informed modeling, generative
methods, standardized MF datasets, and autonomous experimentation are expected to further expand the
impact of MF learning. Collectively, these developments position MF approaches as a central component of
efficient, reliable, and closed-loop materials discovery workflows.

DECLARATIONS
Authors’ contributions
Prepared the initial draft of the manuscript. Wang, B.; Xue, D.
Contributed to the conception and design of the review: Wang, B.; Xu, Y.; Zhou, Y.; Xue, D.
All authors participated in revising and improving the manuscript.

Availability of data and materials
Not applicable.

AI and AI-assisted tools statement
Not applicable.

Financial support and sponsorship
This work was supported by the National Key Research and Development Program of China
(2021YFB3802100), the National Natural Science Foundation of China (Nos. 52573255, 92570301, 52271190,
and 524B200280), the Innovation Capability Support Program of Shaanxi (2024ZG-GCZX-01(1)-06), and the
Natural Science Foundation Project of Shaanxi Province (Grant No. 2022JM-205).

Conflicts of interest
Xue, D. is a Youth Editorial Board Member of Journal of Materials Informatics, but was not involved in any
steps of the editorial process, notably including reviewer selection, manuscript handling, or decision making.
The other authors declared that there are no conflicts of interest.

Ethical approval and consent to participate
Not applicable.

Consent for publication
Not applicable.

Copyright
© The Author(s) 2026.

REFERENCES
1. Batra, R.; Song, L.; Ramprasad, R. Emerging materials intelligence ecosystems propelled by machine learning. Nat. Rev. Mater. 2020, 6,
655-78. DOI