Original Research Articles

Machine Learning Prediction of Magnetic Moments inTransition-Metal Compounds: A Data-Driven ScreeningFramework for Altermagnetic Candidate Materials

Emon Sarder

Received 6 Sep 2026, Published online: 19 Oct 2026

Published in Volume 6, Issue 2, 2026

Open access

View PDF

Abstract

Altermagnetism, a collinear magnetic phase combining zero net magnetization with momentum-space spin-splitting, has emerged as a major target for antiferromagnetic spintronics, yet identifying magnetically compensated candidates within large computational databases remains a bottleneck. We present a machine learning framework that predicts the total magnetic moment per formula unit of transition-metal-bearing binary and ternary compounds using structural, thermodynamic, and composition-based descriptors retrieved from the Materials Project database. A dataset of 29,584 compounds containing one or more of nine magnetic transition metals (Mn, Fe, Cr, Co, Ni, Ru, V, Rh, Os) was assembled and expanded to 142 features per compound using Magpie composition descriptors. Three regression models were compared using 5-fold cross-validation and an independent held-out test set: a linear (Ridge) baseline, Random Forest, and histogram-based Gradient Boosting. Gradient Boosting achieved the best performance (test R-squared = 0.778, MAE = 1.99 mu_B per formula unit), substantially outperforming the linear baseline (R-squared = 0.466). Permutation importance analysis identifies the number of magnetic sites and the mean ground-state magnetic moment of constituent elements as dominant predictors, with electronic, thermodynamic, and symmetry-related descriptors playing secondary roles. We discuss how this model supports first-pass screening for compensated antiferromagnetic candidates while explicitly addressing its limitations, including database bias, target skew, and definitional feature dependence.

Keywords

  • Altermagnetism
  • Machine Learning
  • Magnetic Moment Prediction
  • Materials Project
  • Random Forest
  • Gradient Boosting
  • Spintronics
  • Materials Informatics

References

  1. References
  2. [1] L. Šmejkal, J. Sinova, and T. Jungwirth, “Emerging research landscape of altermagnetism,” Phys. Rev.
  3. X 12, 040501 (2022).
  4. [2] L. Šmejkal, J. Sinova, and T. Jungwirth, “Beyond conventional ferromagnetism and antiferromag-
  5. netism: A phase with nonrelativistic spin and crystal rotation symmetry,” Phys. Rev. X 12, 031042
  6. (2022).
  7. [3] L. Šmejkal, R. González-Hernández, T. Jungwirth, and J. Sinova, “Crystal time-reversal symmetry
  8. breaking and spontaneous Hall effect in collinear antiferromagnets,” Sci. Adv. 6, eaaz8809 (2020).
  9. [4] I. Mazin (The PRX Editors), “Editorial: Altermagnetism—a new punch line of fundamental mag-
  10. netism,” Phys. Rev. X 12, 040002 (2022).
  11. [5] L. Bai, W. Feng, S. Liu, L. Šmejkal, Y. Mokrousov, and Y. Yao, “Altermagnetism: Exploring new
  12. frontiers in magnetism and spintronics,” Adv. Funct. Mater. 34, 2409327 (2024).
  13. [6] S. S. Fender, O. Gonzalez, and D. K. Bediako, “Altermagnetism: A chemical perspective,” ChemRxiv
  14. preprint (2024).
  15. [7] C. Song et al., “Altermagnets as a new class of functional materials,” Nat. Rev. Mater. 10, 473–485
  16. (2025).
  17. [8] L. Šmejkal, A. H. MacDonald, J. Sinova, S. Nakatsuji, and T. Jungwirth, “Anomalous Hall antiferro-
  18. magnets,” Nat. Rev. Mater. 7, 482–496 (2022).
  19. [9] R. González-Hernández et al., “Efficient electrical spin splitter based on nonrelativistic collinear anti-
  20. ferromagnetism,” Phys. Rev. Lett. 126, 127701 (2021).
  21. [10] V. Baltz, A. Manchon, M. Tsoi, T. Moriyama, T. Ono, and Y. Tserkovnyak, “Antiferromagnetic spin-
  22. tronics,” Rev. Mod. Phys. 90, 015005 (2018).
  23. [11] T. Jungwirth, X. Marti, P. Wadley, and J. Wunderlich, “Antiferromagnetic spintronics,” Nat. Nanotech-
  24. nol. 11, 231–241 (2016).
  25. [12] Z. Feng et al., “An anomalous Hall effect in altermagnetic ruthenium dioxide,” Nat. Electron. 5, 735–
  26. 743 (2022).
  27. [13] M. Zeng et al., “Observation of spin splitting in room-temperature metallic antiferromagnet CrSb,”
  28. Adv. Sci. 11, 2406529 (2024).
  29. [14] J. Ding et al., “Large band-splitting in g-wave type altermagnet CrSb,” Phys. Rev. Lett. 133, 206401
  30. (2024).
  31. [15] S. Reimers, L. Odenbreit, L. Šmejkal et al., “Direct observation of altermagnetic band splitting in CrSb
  32. thin films,” Nat. Commun. 15, 2116 (2024).
  33. [16] G. Yang et al., “Three-dimensional mapping of the altermagnetic spin splitting in CrSb,” Nat. Commun.
  34. 16, 1442 (2025).
  35. [17] J. Krempaský et al., “Altermagnetic lifting of Kramers spin degeneracy,” Nature 626, 517–522 (2024).
  36. [18] S. Lee et al., “Broken Kramers degeneracy in altermagnetic MnTe,” Phys. Rev. Lett. 132, 036702
  37. (2024).
  38. [19] A. Bentien, S. Johnsen, G. K. H. Madsen, B. B. Iversen, and F. Steglich, “Colossal Seebeck coefficient
  39. in strongly correlated semiconductor FeSb2,” Europhys. Lett. 80, 17008 (2007).
  40. [20] M. Battiato, J. M. Tomczak, Z. Zhong, and K. Held, “Unified picture for the colossal thermopower
  41. compound FeSb2,” Phys. Rev. Lett. 114, 236603 (2015).
  42. [21] H. Takahashi et al., “Colossal Seebeck effect enhanced by quasi-ballistic phonons dragging massive
  43. electrons in FeSb2,” Nat. Commun. 7, 12732 (2016).
  44. [22] I. I. Mazin, K. Koepernik, M. D. Johannes, R. González-Hernández, and L. Šmejkal, “Prediction of
  45. unconventional magnetism in doped FeSb2,” Proc. Natl. Acad. Sci. U.S.A. 118, e2108924118 (2021).
  46. [23] A. Jain et al., “Commentary: The Materials Project: A materials genome approach to accelerating
  47. materials innovation,” APL Mater. 1, 011002 (2013).
  48. [24] S. P. Ong et al., “Python Materials Genomics (pymatgen): A robust, open-source python library for
  49. materials analysis,” Comput. Mater. Sci. 68, 314–319 (2013).
  50. [25] L. Ward et al., “Matminer: An open source toolkit for materials data mining,” Comput. Mater. Sci.
  51. 152, 60–69 (2018).
  52. [26] L. Ward, A. Agrawal, A. Choudhary, and C. Wolverton, “A general-purpose machine learning frame-
  53. work for predicting properties of inorganic materials,” npj Comput. Mater. 2, 16028 (2016).
  54. [27] K. T. Butler, D. W. Davies, H. Cartwright, O. Isayev, and A. Walsh, “Machine learning for molecular
  55. and materials science,” Nature 559, 547–555 (2018).
  56. [28] L. Breiman, “Random forests,” Mach. Learn. 45, 5–32 (2001).
  57. [29] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res. 12, 2825–2830
  58. (2011).
  59. [30] G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Advances in Neural
  60. Information Processing Systems 30 (NeurIPS 2017).
  61. [31] J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Stat. 29, 1189–
  62. 1232 (2001).
  63. [32] A. Fisher, C. Rudin, and F. Dominici, “All models are wrong, but many are useful: Learning a vari-
  64. able’s importance by studying an entire class of prediction models simultaneously,” J. Mach. Learn.
  65. Res. 20, 1–81 (2019).
  66. [33] C. Rudin, “Stop explaining black box machine learning models for high stakes decisions and use
  67. interpretable models instead,” Nat. Mach. Intell. 1, 206–215 (2019).
  68. [34] S.-O. Kaba, B. Groleau-Paré, M.-A. Gauthier, A.-M. S. Tremblay, S. Verret, and C. Gauvin-Ndiaye,
  69. “Prediction of large magnetic moment materials with graph neural networks and random forests,” Phys.
  70. Rev. Mater. 7, 044407 (2023).
  71. [35] A. E. Fahmy et al., “Learning magnetic order classification from large-scale materials databases,”
  72. arXiv:2509.05909 (2025).
  73. [36] N. C. Frey, M. K. Horton et al., “High-throughput search for magnetic and topological order in transi-
  74. tion metal oxides,” Sci. Adv. 6, eabd1076 (2020).
  75. [37] A. Verma, J. Jami, and A. Bhattacharya, “Advancing magnetic materials discovery: A structure-
  76. based machine learning approach for magnetic ordering and magnetic moment prediction,”
  77. arXiv:2507.01913 (2025).
  78. [38] T. L. Pham, H. Kino, K. Terakura, T. Miyake, K. Tsuda, I. Takigawa, and H. C. Dam, “Machine
  79. learning reveals orbital interaction in materials,” Sci. Technol. Adv. Mater. 18, 756–765 (2017).
  80. [39] R. Y. Sanspeur and J. R. Kitchin, “Circumventing data imbalance in magnetic ground state data for
  81. magnetic moment predictions,” Mach. Learn.: Sci. Technol. 5, 015023 (2024).
  82. [40] P. Hohenberg and W. Kohn, “Inhomogeneous electron gas,” Phys. Rev. 136, B864–B871 (1964).
  83. [41] W. Kohn and L. J. Sham, “Self-consistent equations including exchange and correlation effects,” Phys.
  84. Rev. 140, A1133–A1138 (1965).
  85. [42] J. P. Perdew, K. Burke, and M. Ernzerhof, “Generalized gradient approximation made simple,” Phys.
  86. Rev. Lett. 77, 3865–3868 (1996).
  87. [43] G. Kresse and J. Furthmüller, “Efficient iterative schemes for ab initio total-energy calculations using
  88. a plane-wave basis set,” Phys. Rev. B 54, 11169–11186 (1996).
  89. [44] T. Xie and J. C. Grossman, “Crystal graph convolutional neural networks for an accurate and inter-
  90. pretable prediction of material properties,” Phys. Rev. Lett. 120, 145301 (2018).
  91. [45] C. Chen, W. Ye, Y. Zuo, C. Zheng, and S. P. Ong, “Graph networks as a universal machine learning
  92. framework for molecules and crystals,” Chem. Mater. 31, 3564–3572 (2019).

Metrics

Article views
39
Downloads
31

Licensing

© 2026 Emon Sarder. This article is published under CC BY-SA 4.0.

How to cite

Sarder, E. (2026). Machine Learning Prediction of Magnetic Moments inTransition-Metal Compounds: A Data-Driven ScreeningFramework for Altermagnetic Candidate Materials. Journal of Magnetism and Its Applications, 6(2).

How to Cite

Machine Learning Prediction of Magnetic Moments inTransition-Metal Compounds: A Data-Driven ScreeningFramework for Altermagnetic Candidate Materials. (2026). Journal of Magnetism and Its Applications, 6(2). https://www.jourmag.org/index.php/jma/article/view/154