Predictive Modeling of Half-Metallicity in Heusler Compound through Machine Learning Modeling

Abstract:

Heusler alloys are intermetallic compounds formed in two combinations: Full-Heusler (X₂YZ) and Half-Heusler (XYZ). X and Y can be any transition element, and Z belongs to the main group. This shows that there can be a huge variation in the combinations, leading to various properties and applications. We aimed at predicting the combination leading to shape memory properties using machine learning tools and then synthesizing the same. The predictions are done by training the tool with input data. We employed the lattice strain, valence electron concentration ratio, mechanical stress, difference in entropy, and saturation magnetization as input features. The correlation between the martensitic and austenitic temperature was evaluated in terms of regression metrics. The random forest and decision tree modeling were executed. Test scores were obtained using frequency ordering, PCA, linear regression, and correlation matrix to forecast magnetically controlled shape memory effect. The silhouette score matched the transition temperature at which the material showed shape memory behavior. Additionally, from 70% of the training data, a combination of Iron (Fe), Nickel (Ni), and Aluminum (Al) as Full Heusler alloys stimulated the algorithms in gaining the accuracy of predictive modeling by minimizing the error. Through DFT-based bandgap and density of states calculations, the Fe₂NiAl Heusler compound is hypothesized to behave as a half-metallic ferromagnet by considering the atomic number, the number of valence electrons, and the local magnetic moment. The experimental validation will be done along with magnetization studies, magneto-transport, and magneto-caloric measurements.

• Periodical: Applied Mechanics and Materials (Volume 925)
• Pages: 39-50
• DOI: https://doi.org/10.4028/p-m05tHx
• Online since: April 2025
• Authors: Aparna Ashok, Neeru Bhagat*
• Keywords: Dimensionality, Half-Metallicity, Heusler Alloy, Machine Learning, Multifunctionality, Predictive Modelling, Tunability

References

[1] Curtarolo, S., Morgan, D., Persson, K., Rodgers, J., Ceder, G., (2003). Predicting crystal structures with data mining of quantum calculations. Physical review letters, 91, 135503.

DOI: 10.1103/physrevlett.91.135503

[2] Oliynyk, A.O., Antono, E., Sparks, T.D., Ghadbeigi, L., Gaultois, M.W., Meredig, B., Mar, A., (2016). High-throughput machine-learning-driven synthesis of full-Heusler compounds. Chemistry of Materials, 28, 7324-7331.

DOI: 10.1021/acs.chemmater.6b02724

[3] Oganov, A. R., Lyakhov, A. O., Valle, M. (2011). How Evolutionary Crystal Structure Prediction Works and Why. Accounts of chemical research, 44, 227-237.

DOI: 10.1021/ar1001318

[4] Meredig, B., Agrawal, A., Kirklin, S., Saal, J. E., Doak, J. W., Thompson, A., Wolverton, C. (2014). Combinatorial screening for new materials in unconstrained composition space with machine learning. Physical Review B, 89, 094104.

DOI: 10.1103/physrevb.89.094104

[5] Gaultois, M. W., Oliynyk, A. O., Mar, A., Sparks, T. D., Mulholland, G. J., & Meredig, B. (2016). Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties. Apl Materials, 4.

DOI: 10.1063/1.4952607

[6] Sanvito, S., Žic, M., Nelson, J., Archer, T., Oses, C., Curtarolo, S. (2018). Machine learning and high-throughput approaches to magnetism. Handbook of Materials Modeling: Applications: Current and Emerging Materials, 1-23.

DOI: 10.1007/978-3-319-50257-1_108-1

[7] Oliynyk, A. O.,Mar, A. (2018). Discovery of intermetallic compounds from traditional to machine-learning approaches. Accounts of chemical research, 51, 59-68.

DOI: 10.1021/acs.accounts.7b00490

[8] Liu, X., Xu, P., Zhao, J., Lu, W., Li, M., Wang, G. (2022). Material machine learning for alloys: Applications, challenges and perspectives. Journal of Alloys and Compounds, 921, 165984.

DOI: 10.1016/j.jallcom.2022.165984

[9] Islam, N., Huang, W., Zhuang, H. L. (2018). Machine learning for phase selection in multi-principal element alloys. Computational Materials Science, 150, 230-235.

DOI: 10.1016/j.commatsci.2018.04.003

[10] Žic, M., Archer, T., Sanvito, S. (2017). Designing magnetism in Fe-based Heusler alloys: a machine learning approach. arXiv preprint arXiv:1706.01840.

[11] Raccuglia, P., Elbert, K. C., Adler, P. D. F., Falk, C., Wenny, M. B., Mollo, A., & Green, W. H. (2016). Machine-learning-assisted materials discovery using failed experiments. Nature, 533(7601), 73-76.

DOI: 10.1038/nature17439

[12] Goyal, R., Singh, S., & Saini, D. (2020). Machine learning for designing Heusler compounds: A case study of half-metallic ferromagnetism in Fe2NiAl. The Journal of Chemical Physics, 153(14), 144705.

[13] Roy, P. V., Thapa, R., & Rungger, I. (2019). Machine Learning Study of Half-Metallic Ferromagnetism in Fe2NiAl and Fe2CoAl Full Heusler Alloys. Physica Status Solidi (B), 256(6), 1800716.

[14] Goyal, R., Singh, S., & Saini, D. (2020). Machine learning for designing Heusler compounds: A case study of half-metallic ferromagnetism in Fe2NiAl. The Journal of Chemical Physics, 153(14), 144705.

[15] Sahu, B., & Sanyal, S. P. (2018). High throughput search for Heusler compounds with favorable mechanical properties using machine learning. Journal of Physics: Condensed Matter, 30(38), 385403.

[16] Goyal, R., & Saini, D. (2019). High-throughput design of half-metallic ferromagnets in full-Heusler alloys using machine learning. The Journal of Chemical Physics, 151(10), 104702.

[17] Ashok, A., Desai, A. S., Mahadeva, R., Patole, S. P., & Bhagat, N. (2023). Research network analysis and machine learning on Heusler alloys. Engineered Science, 25(3), 954.