Distinguishing Intrinsic Descriptors of Grain Boundary Segregation Between Metallic and Non-Metallic Solutes in BCC Fe via Machine Learning

Abstract

Elemental segregation at grain boundaries (GBs) is widely recognized to influence the mechanical properties of structural materials. However, the intrinsic descriptors governing GB segregation have not been systematically clarified. Herein, first-principles calculations combined with interpretable machine learning analysis are used to identify the key factors governing elemental segregation at GBs in BCC Fe. A GB segregation database is constructed for 39 solutes commonly present in steels, including 33 metallic and 6 nonmetallic solutes. An interpretable machine learning framework is then developed to rank the intrinsic descriptors that govern segregation behavior. The results indicate that GB segregation of metallic solutes is primarily controlled by geometric features (Voronoi volume), whereas nonmetallic is more strongly governed by electronic features (Chemical bonding). Moreover, an overall contrasting trend is observed in the correlation between Voronoi volume and segregation energy for metallic and nonmetallic solutes. This study provides a new insight into GB engineering and the design of high-performance steels.

Keywords

feature engineering / first-principles calculations / grain boundary segregation / machine learning

References

[1] Y. Mishin, M. Asta, and J. Li, “Atomistic Modeling of Interfaces and Their Impact on Microstructure and Properties,” Acta Materialia 58, no. 4 (2010): 1117–1151, https://doi.org/10.1016/j.actamat.2009.10.049.

[2] L. Wang, Y. Zhang, Z. Zeng, et al., “Tracking the Sliding of Grain Boundaries at the Atomic Scale,” Science 375, no. 6586 (2022): 1261–1265, https://doi.org/10.1126/science.abm2612.

[3] J. Wei, B. Feng, E. Tochigi, N. Shibata, and Y. Ikuhara, “Direct Imaging of the Disconnection Climb Mediated Point Defects Absorption by a Grain Boundary,” Nature Communications 13, no. 1 (2022): 1455, https://doi.org/10.1038/s41467-022-29162-2.

[4] X.-G. Lu, Y. He, and W. Zheng, “Design of Advanced Steels by Integrated Computational Materials Engineering,” Materials Genome Engineering Advances 2, no. 2 (2024): e36, https://doi.org/10.1002/mgea.36.

[5] R. Gautier, F. Mompiou, O. Renk, et al., “Quantifying Grain Boundary Deformation Mechanisms in Small-Grained Metals,” Nature 648, no. 8093 (2025): 327–332, https://doi.org/10.1038/s41586-025-09800-7.

[6] M. Herbig, D. Raabe, Y. J. Li, P. Choi, S. Zaefferer, and S. Goto, “Atomic-Scale Quantification of Grain Boundary Segregation in Nanocrystalline Material,” Physical Review Letters 112, no. 12 (2014): 126103, https://doi.org/10.1103/PhysRevLett.112.126103.

[7] A. Ahmadian, D. Scheiber, X. Zhou, et al., “Aluminum Depletion Induced by Co-Segregation of Carbon and Boron in a bcc-Iron Grain Boundary,” Nature Communications 12, no. 1 (2021): 6008, https://doi.org/10.1038/s41467-021-26197-9.

[8] Y. Ma, B. Sun, A. Schökel, et al., “Phase Boundary Segregation-Induced Strengthening and Discontinuous Yielding in Ultrafine-Grained Duplex Medium-Mn Steels,” Acta Materialia 200 (2020): 389–403, https://doi.org/10.1016/j.actamat.2020.09.007.

[9] Z. Yang, J. Wang, C. Zhang, et al., “First-Principle Screening of Corrosion Resistant Solutes (Al, Zn, Y, Ce, and Mn) in Mg Alloys for Integrated Computational Materials Engineering Guided Stainless Mg Design,” Materials Genome Engineering Advances 2, no. 1 (2024): e22, https://doi.org/10.1002/mgea.22.

[10] X. Zhang, D. Zhu, C. Zhang, et al., “A Review of Crystal Defect-Induced Element Segregation in Multi-Component Alloy Steels,” Progress in Natural Science: Materials International 34, no. 5 (2024): 840–858, https://doi.org/10.1016/j.pnsc.2024.07.016.

[11] T. D. Doležal, R. Freitas, and J. Li, “Segregation and Ordering of Light Interstitials (B, C, H, and N) in Cr–Ni Alloys: Implications for Grain Boundary Stability in Superalloy Design,” Acta Materialia 296 (2025): 121221, https://doi.org/10.1016/j.actamat.2025.121221.

[12] A. Reiners-Sakic, A. Reichmann, C. Dösinger, L. Romaner, and D. Holec, “Interstitials as a Key Ingredient for P Segregation to Grain Boundaries in Polycrystalline α-Fe,” Scripta Materialia 268 (2025): 116864, https://doi.org/10.1016/j.scriptamat.2025.116864.

[13] J. Wang, R. Janisch, G. K. H. Madsen, and R. Drautz, “First-Principles Study of Carbon Segregation in Bcc Iron Symmetrical Tilt Grain Boundaries,” Acta Materialia 115 (2016): 259–268, https://doi.org/10.1016/j.actamat.2016.04.058.

[14] H. L. Mai, X.-Y. Cui, D. Scheiber, L. Romaner, and S. P. Ringer, “Phosphorus and Transition Metal Co-Segregation in Ferritic Iron Grain Boundaries and Its Effects on Cohesion,” Acta Materialia 250 (2023): 118850, https://doi.org/10.1016/j.actamat.2023.118850.

[15] K. Song, S. Cao, Y. Bao, P. Qian, and Y. Su, “Designing Hydrogen Embrittlement-Resistant Grain Boundary in Steel by Alloying Elements Segregation: First-Principles Calculations,” Applied Surface Science 656 (2024): 159684, https://doi.org/10.1016/j.apsusc.2024.159684.

[16] S. Das, N. Oyeniran, J. Walter, A. Gesch, and C. Hu, “Bayesian Optimization of Grain-Boundary Segregation in High-Entropy Alloys,” npj Computational Materials 11, no. 1 (2025): 371, https://doi.org/10.1038/s41524-025-01850-9.

[17] A. Linda, R. Mukherjee, and S. Bhowmick, “Multiscale Modeling of Abnormal Grain Growth: Role of Solute Segregation and Grain Boundary Character,” Acta Materialia 306 (2025): 121861, https://doi.org/10.1016/j.actamat.2025.121861.

[18] Z. Xie, C. Song, W. Shen, et al., “First-Principles Study on the Effect of Ce on Segregation Behavior of bcc-Fe Grain Boundaries in Low-Carbon Low-Alloy Steel,” Journal of Materials Research and Technology 36 (2025): 10474–10486, https://doi.org/10.1016/j.jmrt.2025.05.237.

[19] X.-Y. Zhou, H.-H. Wu, M. Zhou, L. Wang, T. Lookman, and X. Mao, “Enhanced Hydrogen Embrittlement Resistance of FeCoNiCrMn Multi-Principal Element Alloys via Local Chemical Ordering and Grain Boundary Segregation,” Acta Materialia 296 (2025): 121209, https://doi.org/10.1016/j.actamat.2025.121209.

[20] X. Wu, Y.-W. You, X.-S. Kong, et al., “First-Principles Determination of Grain Boundary Strengthening in Tungsten: Dependence on Grain Boundary Structure and Metallic Radius of Solute,” Acta Materialia 120 (2016): 315–326, https://doi.org/10.1016/j.actamat.2016.08.048.

[21] F. Wang, H.-H. Wu, X. Zhou, et al., “First-Principle Study on the Segregation and Strengthening Behavior of Solute Elements at Grain Boundary in BCC Iron,” Journal of Materials Science & Technology 189 (2024): 247–261, https://doi.org/10.1016/j.jmst.2024.01.005.

[22] C. Dösinger, M. Hodapp, O. Peil, et al., “Efficient Descriptors and Active Learning for Grain Boundary Segregation,” Physical Review Materials 7, no. 11 (2023): 113606, https://doi.org/10.1103/PhysRevMaterials.7.113606.

[23] X. Geng, F. Wang, H.-H. Wu, et al., “Data-Driven and Artificial Intelligence Accelerated Steel Material Research and Intelligent Manufacturing Technology,” Materials Genome Engineering Advances 1, no. 1 (2023): e10, https://doi.org/10.1002/mgea.10.

[24] S. Han, C. Wang, Y. Zhang, W. Xu, and H. Di, “Employing Deep Learning in Non-Parametric Inverse Visualization of Elastic–Plastic Mechanisms in Dual-Phase Steels,” Materials Genome Engineering Advances 2, no. 1 (2024): e29, https://doi.org/10.1002/mgea.29.

[25] X. Liu, M. Chen, C. Bai, C. Liu, and A. Soon, “Towards Designing Titanium Alloys With High Mechanical Performance via Grain Boundary Segregation Strategy Based on Data-Driven,” Journal of Alloys and Compounds 1038 (2025): 182803, https://doi.org/10.1016/j.jallcom.2025.182803.

[26] J. Wang, Y. Yuan, T. Chen, et al., “Design of Corrosion-Resistant Mg–Zn/Gd–X Alloys: Insights From Theoretical Calculations and Experimental Studies,” Corrosion Science 255 (2025): 113078, https://doi.org/10.1016/j.corsci.2025.113078.

[27] J. Messina, R. Luo, K. Xu, et al., “Machine Learning to Predict Aluminum Segregation to Magnesium Grain Boundaries,” Scripta Materialia 204 (2021): 114150, https://doi.org/10.1016/j.scriptamat.2021.114150.

[28] X. Li, Y. Hu, X. Li, et al., “Prediction of the Energetics of Stable Self-Interstitial Atoms at Tungsten Grain Boundaries via Machine Learning,” Journal of Nuclear Materials 593 (2024): 154992, https://doi.org/10.1016/j.jnucmat.2024.154992.

[29] C. Ravi and C. Wolverton, “First-Principles Study of Crystal Structure and Stability of Al–Mg–Si–(Cu) Precipitates,” Acta Materialia 52, no. 14 (2004): 4213–4227, https://doi.org/10.1016/j.actamat.2004.05.037.

[30] J. P. Perdew, J. A. Chevary, S. H. Vosko, et al., “Atoms, Molecules, Solids, and Surfaces: Applications of the Generalized Gradient Approximation for Exchange and Correlation,” Physical Review B 46, no. 11 (1992): 6671–6687, https://doi.org/10.1103/PhysRevB.46.6671.

[31] M. Ropo, K. Kokko, and L. Vitos, “Assessing the Perdew-Burke-Ernzerhof Exchange-Correlation Density Functional Revised for Metallic Bulk and Surface Systems,” Physical Review B 77, no. 19 (2008): 195445, https://doi.org/10.1103/PhysRevB.77.195445.

[32] S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems 30 (2017), https://doi.org/10.5555/3295222.3295230.

[33] D. Zhu, H.-H. Wu, F. Hou, et al., “A Transfer Learning Strategy for Tensile Strength Prediction in Austenitic Stainless Steel Across Temperatures,” Scripta Materialia 251 (2024): 116210, https://doi.org/10.1016/j.scriptamat.2024.116210.

[34] K. Sahoo, S. Diwase, M. K. Singh, R. Santhanam, and R. M. R , “Materials Informatics Approach to Design New High-Entropy Shape Memory Alloys,” Scripta Materialia 271 (2026): 117013, https://doi.org/10.1016/j.scriptamat.2025.117013.

[35] H. L. Mai, X.-Y. Cui, T. Hickel, J. Neugebauer, and S. P. Ringer, “A High-Throughput Ab Initio Study of Elemental Segregation and Cohesion at Ferritic-Iron Grain Boundaries,” Acta Materialia 297 (2025): 121288, https://doi.org/10.1016/j.actamat.2025.121288.

[36] R. Kohavi and G. H. John, “Wrappers for Feature Subset Selection,” Artificial Intelligence 97, no. 1 (1997): 273–324, https://doi.org/10.1016/S0004-3702(97)00043-X.

Rights & permissions

2026 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.