Transfer learning-enabled performance prediction of metallic materials: Methods, applications and prospects

Abstract

In the era of materials genome engineering, data-driven machine learning has become a powerful tool for accelerating the research and development of metallic materials. However, the predictive accuracy and generalization ability of traditional machine learning models are often limited by the scarcity and heterogeneity of available data, especially in small-sample scenarios. To address these challenges, transfer learning has emerged as an effective strategy to leverage knowledge from related domains, thereby enhancing model performance with limited target data. This review systematically summarizes the fundamental concepts, methodologies, and representative applications of transfer learning in the prediction of metallic materials’ properties. Transfer learning can be categorized into feature-based, instance-based, parameter-based, and knowledge-based methods. This work discusses their respective mechanisms, advantages, and limitations. Case studies demonstrate that transfer learning can significantly improve prediction accuracy, data efficiency, and model interpretability in tasks such as mechanical property prediction and alloy design. Furthermore, this work highlights emerging trends including hybrid, multi-task, meta, and adaptive transfer learning, which further expand the applicability of these techniques. Finally, this work outlines future research directions, emphasizing the need for data standardization, algorithmic innovation, multimodal data fusion, and the integration of physical principles to achieve robust, interpretable, and generalizable models. The perspectives presented aim to advance the intelligent design and discovery of metallic materials, promoting efficient knowledge transfer and collaborative innovation in materials science.

Keywords

small-sample data / machine learning / transfer learning / performance prediction

References

[1] Q.F. Yao, X. Yuan, T.K. Chen, D.T. Leong, and J.P. Xie, Engineering functional metal materials at the atomic level, Adv. Mater., 30(2018), No. 47, art. No. e1802751.

[2] Z.Z. Liu, Q.H. Zhou, X.K. Liang, et al., Alloy design for laser powder bed fusion additive manufacturing: A critical review, Int. J. Extreme Manuf., 6(2024), No. 2, art. No. 022002.

[3] Jawahar M, Reddy CS, Srinivas C. A review of performance optimization and current research in PMEDM. Mater. Today Proc.. 2019, 19742.

[4] Qiu GZ, Guo YF. Current situation and development trend of titanium metal industry in China. Int. J. Miner. Metall. Mater.. 2022, 294599.

[5] Kalidindi SR, Brough DB, Li Set al. . Role of materials data science and informatics in accelerated materials innovation. MRS Bull.. 2016, 418596.

[6] Fu HD, Zhang HT, Wang CS, Yong W, Xie JX. Recent progress in the machine learning-assisted rational design of alloys. Int. J. Miner. Metall. Mater.. 2022, 294635.

[7] Juan YF, Dai YB, Yang Y, Zhang J. Accelerating materials discovery using machine learning. J. Mater. Sci. Technol.. 2021, 79178.

[8] S. Lee, J. Noh, and H.J. Ryu, Discovery of multi-metal-layered double hydroxides for decontamination of iodate by machine learning-assisted experiments, J. Hazard. Mater., 494(2025), art. No. 138735.

[9] Pan GF, Wang FY, Shang CLet al. . Advances in machine learning and artificial intelligence-assisted material design of steels. Int. J. Miner. Metall. Mater.. 2023, 3061003.

[10] Breneman CM, Brinson LC, Schadler LSet al. . Stalking the materials genome: A data-driven approach to the virtual design of nanostructured polymers. Adv. Funct. Mater.. 2013, 23465746.

[11] M.J. Luo, R.D. Li, D. Zheng, et al., Formation mechanism of inherent spatial heterogeneity of microstructure and mechanical properties of NiTi SMA prepared by laser directed energy deposition, Int. J. Extreme Manuf., 5(2023), No. 3, art. No. 035005.

[12] L. Himanen, A. Geurts, A.S. Foster, and P. Rinke, Data-driven materials science: Status, challenges, and perspectives, Adv. Sci., 6(2019), No. 21, art. No. 1900808.

[13] X.Y. Sun, M.N. Chen, T.T. Liu, et al., Characterization, preparation, and reuse of metallic powders for laser powder bed fusion: A review, Int. J. Extreme Manuf., 6(2024), No. 1, art. No. 012003.

[14] C. Chen, Y.X. Zuo, W.K. Ye, X.G. Li, Z. Deng, and S.P. Ong, A critical review of machine learning of energy materials, Adv. Energy Mater., 10(2020), No. 8, art. No. 1903242.

[15] S.S. Chong, Y.S. Ng, H.Q. Wang, and J.C. Zheng, Advances of machine learning in materials science: Ideas and techniques, Front. Phys., 19(2024), No. 1, art. No. 13501.

[16] P.F. Wu, C.X. Zhao, E.D. Cui, et al., Advances in magnetic-assisted triboelectric nanogenerators: Structures, materials and self-sensing systems, Int. J. Extreme Manuf., 6(2024), No. 5, art. No. 052007.

[17] Winkler DA. Probing the properties of molecules and complex materials using machine learning. Aust. J. Chem.. 2022, 7511906.

[18] Zhang XH, Ran X, Wang Zet al. . Designing laser powder bed fusion low-alloyed titanium with superior strength-ductility trade-off via machine learning. J. Mater. Sci. Technol.. 2025, 237323.

[19] Liu R, Zhang P, Zhang ZJ, Wang B, Zhang ZF. A practical model for efficient anti-fatigue design and selection of metallic materials: I. Model building and fatigue strength prediction. J. Mater. Sci. Technol.. 2021, 70233.

[20] J.L. Su, F.L. Jiang, J. Teng, et al., Recent innovations in laser additive manufacturing of titanium alloys, Int. J. Extreme Manuf., 6(2024), No. 3, art. No. 032001.

[21] Yang XJ, Jia JH, Li Qet al. . Stress-assisted corrosion mechanism of 3Ni steel by using gradient boosting decision tree machining learning method. Int. J. Miner. Metall. Mater.. 2024, 3161311.

[22] Bai PH, Shang CL, Zhu DXet al. . The interpretable descriptors for fatigue performance of wrought aluminum alloys. J. Mater. Res. Technol.. 2024, 323423.

[23] H.J. Wang, B. Li, J.G. Gong, and F.Z. Xuan, Machine learning-based fatigue life prediction of metal materials: Perspectives of physics-informed and data-driven hybrid methods, Eng. Fract. Mech., 284(2023), art. No. 109242.

[24] C.J. Hargreaves, M.W. Gaultois, L.M. Daniels, et al., A database of experimentally measured lithium solid electrolyte conductivities evaluated with machine learning, npj Comput. Mater., 9(2023), art. No. 9.

[25] Liu Y, Zhao TL, Ju WW, Shi SQ. Materials discovery and design using machine learning. J. Materiomics. 2017, 33159.

[26] Z.C. Zhang, J. Femi-Oyetoro, I. Fidan, M. Ismail, and M. Allen, Prediction of dimensional changes of low-cost metal material extrusion fabricated parts using machine learning techniques, Metals, 11(2021), No. 5, art. No. 690.

[27] Gaikwad A, Chang T, Giera Bet al. . In-process monitoring and prediction of droplet quality in droplet-on-demand liquid metal jetting additive manufacturing using machine learning. J. Intell. Manuf.. 2022, 3372093.

[28] Wei J, Chu X, Sun XYet al. . Machine learning in materials science. InfoMat. 2019, 13338.

[29] C.L. Chen, P. Zhang, H.X. Zhang, et al., Deep learning on computational-resource-limited platforms: A survey, Mob. Inf. Syst., 2020(2020), No. 1, art. No. 8454327.

[30] Zhuang FZ, Luo P, He Q, Shi ZZ. Survey on transfer learning research. J. Softw.. 2015, 26126

[31] Niu ST, Liu YX, Wang J, Song HB. A decade survey of transfer learning (2010–2020). IEEE Trans. Artif. Intell.. 2020, 12151.

[32] D. Jha, K. Choudhary, F. Tavazza, et al., Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning, Nat. Commun., 10(2019), No. 1, art. No. 5316.

[33] K. Weiss, T.M. Khoshgoftaar, and D.D. Wang, A survey of transfer learning, J. Big Data, 3(2016), No. 1, art. No. 9.

[34] M.L. Hutchinson, E. Antono, B.M. Gibbons, S. Paradiso, J.L. Ling, and B. Meredig, Overcoming data scarcity with transfer learning, arXiv: 1711.05099. Doi: https://doi.org/10.48550/arXiv.1711.05099.

[35] Yamada H, Liu C, Wu Set al. . Predicting materials properties with little data using shotgun transfer learning. ACS Cent. Sci.. 2019, 5101717.

[36] Zhou CL, Yuan RH, Su BLet al. . Creep rupture life prediction of high-temperature titanium alloy using cross-material transfer learning. J. Mater. Sci. Technol.. 2024, 17839.

[37] Lu J, Behbood V, Hao P, Zuo H, Xue S, Zhang GQ. Transfer learning using computational intelligence: A survey. Knowl. Based Syst.. 2015, 8014.

[38] Panigrahi S, Nanda A, Swarnkar T. Mishra D, Buyya R, Mohapatra P. A survey on transfer learning. Intelligent and Cloud Computing, Smart Innovation, Systems and Technologies. 2020, Singapore, Springer781

[39] W. Zhao, Research on the deep learning of the small sample data based on transfer learning, AIP Conf. Proc., (2017), art. No. 020018.

[40] Saha B, Gupta S, Phung D, Venkatesh S. Multiple task transfer learning with small sample sizes. Knowl. Inf. Syst.. 2016, 462315.

[41] P.C. Xu, X.B. Ji, M.J. Li, and W.C. Lu, Small data machine learning in materials science, npj Comput. Mater., 9(2023), art. No. 42.

[42] Xu G, He JS, Lü ZM, Li M, Xu JW. Prediction of mechanical properties for deep drawing steel by deep learning. Int. J. Miner. Metall. Mater.. 2023, 301156.

[43] Y.C. Ma, S. Chen, S. Ermon, and D.B. Lobell, Transfer learning in environmental remote sensing, Remote Sens. Environ., 301(2024), art. No. 113924.

[44] Laurer M, van Atteveldt W, Casas A, Welbers K. Less annotating, more classifying: Addressing the data scarcity issue of supervised machine learning with deep transfer learning and BERT-NLI. Polit. Anal.. 2024, 32184.

[45] Wang DC, Zhou HP, Guo ZY, Guo K. Spectrum prediction and inverse design of metasurfaces via transfer learning based on material similarity. Opt. Lett.. 2025, 50134178.

[46] Z.Y. Zhang, Q.Y. Liu, and D.Z. Wu, Predicting stress–strain curves using transfer learning: Knowledge transfer across polymer composites, Mater. Des., 218(2022), art. No. 110700.

[47] Y.J. Xu, H.B. Weng, X.Z. Ju, et al., A method for predicting mechanical properties of composite microstructure with reduced dataset based on transfer learning, Compos. Struct., 275(2021), art. No. 114444.

[48] C. Liu, X.B. Xu, J. Wu, H.P. Zhu, and C. Wang, Deep transfer learning-based damage detection of composite structures by fusing monitoring data with physical mechanism, Eng. Appl. Artif. Intell., 123(2023), art. No. 106245.

[49] A. Goetz, A.R. Durmaz, M. Müller, et al., Addressing materials’ microstructure diversity using transfer learning, npj Comput. Mater., 8(2022), art. No. 27.

[50] A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M.A. Azim, Transfer learning: A friendly introduction, J. Big Data, 9(2022), No. 1, art. No. 102.

[51] Zhuang FZ, Qi ZY, Duan KYet al. . A comprehensive survey on transfer learning. Proc. IEEE. 2021, 109143.

[52] Wang J, Zhao CH, Gim JS, Yang HG, Turng LS. Mode-cloud data analytics based transfer learning for soft sensor of manufacturing surface quality in injection molding. J. Manuf. Process.. 2023, 87111.

[53] R.C. Zhu, T.S. Qiu, J.F. Wang, et al., Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning, Nat. Commun., 12(2021), No. 1, art. No. 2974.

[54] V. Pandiyan, R. Drissi-Daoudi, S. Shevchik, et al., Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process, J. Mater. Process. Technol., 303(2022), art. No. 117531.

[55] L. Xiao, X.Y. Xue, N. Wang, Q.B. Ren, J.M. Hua, and F. Wang, A transfer learning-based approach to fatigue life prediction of corroded bimetallic steel bars using small samples, Constr. Build. Mater., 400(2023), art. No. 132679.

[56] Hoffmann N, Schmidt J, Botti S, Marques MAL. Transfer learning on large datasets for the accurate prediction of material properties. Digit. Discov.. 2023, 251368.

[57] J. Lee and R. Asahi, Transfer learning for materials informatics using crystal graph convolutional neural network, Comput. Mater. Sci., 190(2021), art. No. 110314.

[58] Shao H, Tong B, Suzuki E. Extended MDL principle for feature-based inductive transfer learning. Knowl. Inf. Syst.. 2013, 352365.

[59] Wang F, Gursoy MC, Velipasalar S. Feature-based federated transfer learning: Communication efficiency, robustness and privacy. IEEE Trans. Mach. Learn. Commun. Netw.. 2024, 2823.

[60] Sevani N, Azizah K, Jatmiko W. A feature-based transfer learning to improve the image classification with support vector machine. Int. J. Adv. Comput. Sci. Appl.. 2023, 1461

[61] A.P.P. Abdul Majeed, M.A. Abdullah, A.F.Ab. Nasir, M.A. Mohd Razman, W. Chen, and E.H. Yap, Surface defect detection: A feature-based transfer learning approach, J. Phys. Conf. Ser., 2762(2024), No. 1, art. No. 012088.

[62] Li AY, Poudel A, Shao S, Shamsaei N, Liu J. Nondestructive fatigue life prediction for additively manufactured metal parts through a multimodal transfer learning framework. IISE Trans.. 2025, 57111344.

[63] Eslaminia A, Meng YQ, Nahrstedt K, Shao CH. Federated domain generalization for condition monitoring in ultrasonic metal welding. J. Manuf. Syst.. 2024, 771.

[64] X.X. Wang, C.F. He, P. Li, X.C. Liu, Z.X. Xing, and M.S. Ning, Micromagnetic and quantitative prediction of yield and tensile strength of carbon steels using transfer learning method, J. Nondestruct. Eval., 43(2024), No. 2, art. No. 69.

[65] D.X. Zhu, H.H. Wu, F.G. Hou, et al., A transfer learning strategy for tensile strength prediction in austenitic stainless steel across temperatures, Scripta Mater., 251(2024), art. No. 116210.

[66] Shan XX, Lu Y, Li QL, Wen Y. Model-based transfer learning and sparse coding for partial face recognition. IEEE Trans. Circuits Syst. Video Technol.. 2021, 31114347.

[67] W. Zheng, F.M. Xue, Z.Y. Chen, et al., Disruption prediction for future tokamaks using parameter-based transfer learning, Commun. Phys., 6(2023), art. No. 181.

[68] Aduwenye P, Nutakor C, Roininen L, Sopanen J. Parameter-based transfer learning for bearing fault diagnosis using small samples under variable working conditions. IEEE Access. 2025, 1344214.

[69] C. Peng, L.L. Li, Q. Chen, Z.H. Tang, W.H. Gui, and J. He, A fault diagnosis method for rolling bearings based on parameter transfer learning under imbalance data sets, Energies, 14(2021), No. 4, art. No. 944.

[70] Li CK, Pan Y, Shi Y, Wang WK. Optimization of process prediction models for hot-wire laser metal deposition using transfer learning strategies based on simulation datasets. Weld. World. 2025, 6951193.

[71] Ferguson M, Ronay Ak, Lee YT, Law KH. Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning. Smart Sustain. Manuf. Syst.. 2018, 210137.

[72] M.M. Yu and X. Xie, Ultra-low cycle fatigue life prediction of stainless steel based on transfer learning guided artificial neural network, Eng. Appl. Artif. Intell., 136(2024), art. No. 109054.

[73] X.Y. Xue, F. Wang, N. Wang, J.M. Hua, and W.J. Deng, Transfer-learning prediction model for low-cycle fatigue life of bimetallic steel bars, Buildings, 14(2024), No. 8, art. No. 2275.

[74] K.T. Chui, V. Arya, S.S. Band, M. Alhalabi, R.W. Liu, and H.R. Chi, Facilitating innovation and knowledge transfer between homogeneous and heterogeneous datasets: Generic incremental transfer learning approach and multidisciplinary studies, J. Innov. Knowl., 8(2023), No. 2, art. No. 100313.

[75] G.S. Na, One-shot heterogeneous transfer learning from calculated crystal structures to experimentally observed materials, Comput. Mater. Sci., 235(2024), art. No. 112791.

[76] Zhao PL, Hoi SCH, Wang JL, Li B. Online transfer learning. Artif. Intell.. 2014, 21676.

[77] Kang WJ, Xiao JY, Xue JJ. Generative knowledge-based transfer learning for few-shot health condition estimation. Complex Intell. Syst.. 2023, 91965.

[78] R.Z. Dong, Y.B. Dan, X. Li, and J.J. Hu, Inverse design of composite metal oxide optical materials based on deep transfer learning and global optimization, Comput. Mater. Sci., 188(2021), art. No. 110166.

[79] L. Ai, B. Zhang, and P. Ziehl, A transfer learning approach for acoustic emission zonal localization on steel plate-like structure using numerical simulation and unsupervised domain adaptation, Mech. Syst. Signal Process., 192(2023), art. No. 110216.

[80] X.L. Wei, S. van der Zwaag, Z.X. Jia, C.C. Wang, and W. Xu, On the use of transfer modeling to design new steels with excellent rotating bending fatigue resistance even in the case of very small calibration datasets, Acta Mater., 235(2022), art. No. 118103.

[81] H. Sun, H.Y. Zhang, G.L. Ren, and C. Zhang, A knowledge transfer framework for general alloy materials properties prediction, Materials, 15(2022), No. 21, art. No. 7442.

[82] Lin D, An X, Zhang J. Double-bootstrapping source data selection for instance-based transfer learning. Pattern Recognit. Lett.. 2013, 34111279.

[83] Wang TY, Huan J, Zhu M. Instance-based deep transfer learning. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). 2019367.

[84] L. Cai, J. Gu, J.H. Ma, and Z.J. Jin, Probabilistic wind power forecasting approach via instance-based transfer learning embedded gradient boosting decision trees, Energies, 12(2019), No. 1, art. No. 159.

[85] X.G. Li, W.T. Ji, and J.D. Huang, Local instance-based transfer learning for reinforcement learning, Eng. Appl. Artif. Intell., 133(2024), art. No. 108488.

[86] Yang JH, Li XM, Lu HL, Xu JW, Li HX. An LIBS quantitative analysis method for alloy steel at high temperature based on transfer learning. J. Anal. At. Spectrom.. 2018, 3371184.

[87] K. Lee, S. Han, V.H. Pham, et al., Multi-objective instance weighting-based deep transfer learning network for intelligent fault diagnosis, Appl. Sci., 11(2021), No. 5, art. No. 2370.

[88] L. Jiang, Z.H. Zhang, H. Hu, X.Q. He, H.D. Fu, and J.X. Xie, A rapid and effective method for alloy materials design via sample data transfer machine learning, npj Comput. Mater., 9(2023), art. No. 26.

[89] J. Chen, X. Cheng, Y.J. Jia, and S. Tan, Cloud–edge collaborative model adaptation based on deep Q-network and transfer feature extraction, Appl. Sci., 15(2025), No. 15, art. No. 8335.

[90] Y.W. Wei, J.J. He, C. Yang, W. Yu, J. Feng, X.J. Liu, and X.Y. Chong, Accelerated multi-property screening of lead-free halide double perovskite via transfer learning, Adv. Funct. Mater., n/a(2025), art. No. e14377.

[91] Shabbir S, Zhang YQ, Sun Cet al. . Transfer learning improves the prediction performance of a LIBS model for metals with an irregular surface by effectively correcting the physical matrix effect. J. Anal. At. Spectrom.. 2021, 3671441.

[92] Liang ZP, Liang WQ, Wang ZQ, Ma XL, Liu L, Zhu ZX. Multiobjective evolutionary multitasking with two-stage adaptive knowledge transfer based on population distribution. IEEE Trans. Syst. Man Cybern, Syst.. 2022, 5274457.

[93] Xiao ZJ, Zhu MH, Chen JW, You ZC. Integrated transfer learning and multitask learning strategies to construct graph neural network models for predicting bioaccumulation parameters of chemicals. Environ. Sci. Technol.. 2024, 583515650.

[94] A. Rauschenberger, P.V. Nazarov, and E. Glaab, Estimating sparse regression models in multi-task learning and transfer learning through adaptive penalisation, Bioinformatics, 41(2025), No. 10, art. No. btaf406.

[95] Pang SN, Liu F, Kadobayashi Y, Ban T, Inoue D. A learner-independent knowledge transfer approach to multi-task learning. Cogn. Comput.. 2014, 63304.

[96] S.F. Kong, D. Guevarra, C.P. Gomes, and J.M. Gregoire, Materials representation and transfer learning for multi-property prediction, Appl. Phys. Rev., 8(2021), No. 2, art. No. 021409.

[97] Chen A, Wang ZL, Vidaurre KLLet al. . Knowledge-reused transfer learning for molecular and materials science. J. Energy Chem.. 2024, 98149.

[98] Chen SM, Hong ZM, Hou WJet al. . TransZero: Cross attribute-guided transformer for zero-shot learning. IEEE Trans. Pattern Anal. Mach. Intell.. 2023, 451112844

[99] C. He, H.M. Shi, X.R. Liu, and J.B. Li, Interpretable physics-informed domain adaptation paradigm for cross-machine transfer diagnosis, Knowl. Based Syst., 288(2024), art. No. 111499.

[100] Li QK, Wang YM, Zhang YN, Zuo ZY, Chen JX, Wang W. Fuzzy-ViT: A deep neuro-fuzzy system for cross-domain transfer learning from large-scale general data to medical image. IEEE Trans. Fuzzy Syst.. 2025, 331231.

[101] V. Gupta, K. Choudhary, F. Tavazza, et al., Cross-property deep transfer learning framework for enhanced predictive analytics on small materials data, Nat. Commun., 12(2021), art. No. 6595.

[102] L.Z. Chen, Z.L. Yu, and J. Yang, SPD-CNN: A plain CNN-based model using the symmetric positive definite matrices for cross-subject EEG classification with meta-transfer-learning, Front. Neurorobot., 16(2022), art. No. 958052.

[103] Sun QR, Liu YY, Chua TS, Schiele B. Meta-transfer learning for few-shot learning. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019403.

[104] Y. Chen, X.B. Xu, and C. Liu, Few-shot meta transfer learning-based damage detection of composite structures, Smart Mater. Struct., 33(2024), No. 2, art. No. 025027.

[105] Soh JW, Cho S, Cho NI. Meta-transfer learning for zero-shot super-resolution. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20203513.

[106] H. Zhong, D.Q He, Z.X. Wei, et al., A novel meta-learning network with adversarial domain-adaptation and attention mechanism for cross-domain for train bearing fault diagnosis, Meas. Sci. Technol, 35(2024), No. 12, art. No. 125109.

RIGHTS & PERMISSIONS

University of Science and Technology Beijing