Electronic structure prediction of medium and high entropy alloys across composition space
Source abstract
Abstract
Abstract We propose machine learning (ML) models to predict the electron density — the fundamental unknown of a material’s ground state — across the composition space of concentrated alloys. From this, other physical properties can be inferred, enabling accelerated exploration. A significant challenge is that the number of descriptors and sampled compositions required for accurate prediction grows rapidly with species. To address this, we employ Bayesian Active Learning (AL), which minimizes training data requirements by leveraging uncertainty quantification capabilities of Bayesian Neural Networks. Compared to the strategic tessellation of the composition space, Bayesian-AL reduces the number of training data points by a factor of 2.5 for ternary (SiGeSn) and 1.7 for quaternary (CrFeCoNi) systems. We also introduce easy-to-optimize, body-attached-frame descriptors, which respect physical symmetries while keeping descriptor-vector size nearly constant as alloy complexity increases. Our ML models demonstrate high accuracy and generalizability in predicting both electron density and energy across composition space.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · High Entropy Alloys Studies · Additive Manufacturing Materials and Processes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. Hohenberg, P. & Kohn, W. Inhomogeneous electron gas. Phys. Rev. 136, B864 (1964).10.1103/PhysRev.136.B864 ↗
2. Kohn, W. & Sham, L. J. Self-consistent equations including exchange and correlation effects. Phys. Rev. 140, A1133 (1965).10.1103/PhysRev.140.A1133 ↗
3. Martin, R. M. Electronic Structure: Basic Theory and Practical Methods (Cambridge University Press, 2004), first edn.10.1017/CBO9780511805769 ↗
4. Hafner, J., Wolverton, C. & Ceder, G. Toward computational materials design: the impact of density functional theory on materials research. MRS Bull 31, 659–668 (2006).10.1557/mrs2006.174 ↗
5. Saal, J. E., Kirklin, S., Aykol, M., Meredig, B. & Wolverton, C. Materials design and discovery with high-throughput density functional theory: the open quantum materials database (oqmd). Jom 65, 1501–1509 (2013).10.1007/s11837-013-0755-4 ↗
6. Emery, A. A. & Wolverton, C. High-throughput DFT calculations of formation energy, stability and oxygen vacancy formation energy of ABO3 perovskites. Sci. Data 4, 1–10 (2017).10.1038/sdata.2017.153 ↗
7. Choudhary, K. et al. High-throughput density functional perturbation theory and machine learning predictions of infrared, piezoelectric, and dielectric responses. npj Comput. Mater. 6, 64 (2020).10.1038/s41524-020-0337-2 ↗
8. Jain, A. et al. Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL Mater. 1, 011002 (2013).10.1063/1.4812323 ↗
9. Jain, A. et al. The materials project: Accelerating materials design through theory-driven data and tools. Handb. Mater. Model.: Methods: Theory Model. 1751–1784 (2020).10.1007/978-3-319-44677-6_60 ↗
10. Gavini, V. et al. Roadmap on electronic structure codes in the exascale era. Model. Simul. Mater. Sci. Eng. 31, 063301 (2023).10.1088/1361-651X/acdf06 ↗
11. Goedecker, S. Linear scaling electronic structure methods. Rev. Mod. Phys. 71, 1085 (1999).10.1103/RevModPhys.71.1085 ↗
12. Banerjee, A. S., Lin, L., Hu, W., Yang, C. & Pask, J. E. Chebyshev polynomial filtered subspace iteration in the discontinuous Galerkin method for large-scale electronic structure calculations. J. Chem. Phys. 145, 154101 (2016).10.1063/1.4964861 ↗
13. Banerjee, A. S., Lin, L., Suryanarayana, P., Yang, C. & Pask, J. E. Two-level Chebyshev filter based complementary subspace method: pushing the envelope of large-scale electronic structure calculations. J. Chem. Theory Comput. 14, 2930–2946 (2018).10.1021/acs.jctc.7b01243 ↗
14. Motamarri, P. & Gavini, V. Subquadratic-scaling subspace projection method for large-scale Kohn-Sham density functional theory calculations using spectral finite-element discretization. Phys. Rev. B 90, 115127 (2014).10.1103/PhysRevB.90.115127 ↗
15. Lin, L., García, A., Huhs, G. & Yang, C. SIESTA-PEXSI: Massively parallel method for efficient and accurate ab initio materials simulation without matrix diagonalization. J. Phys.: Condens. Matter 26, 305503 (2014).
16. Dogan, M., Liou, K.-H. & Chelikowsky, J. R. Real-space solution to the electronic structure problem for nearly a million electrons. J. Chem. Phys. 158, 244114 (2023).10.1063/5.0150864 ↗
17. Gavini, V., Bhattacharya, K. & Ortiz, M. Vacancy clustering and prismatic dislocation loop formation in aluminum. Phys. Rev. B 76, 180101 (2007).10.1103/PhysRevB.76.180101 ↗
18. Carr, S., Fang, S. & Kaxiras, E. Electronic-structure methods for twisted moiré layers. Nat. Rev. Mater. 5, 748–763 (2020).10.1038/s41578-020-0214-0 ↗
19. Jaros, M. Electronic properties of semiconductor alloy systems. Rep. Prog. Phys. 48, 1091 (1985).10.1088/0034-4885/48/8/001 ↗
20. Wei, S.-H., Ferreira, L., Bernard, J. E. & Zunger, A. Electronic properties of random alloys: Special quasirandom structures. Phys. Rev. B 42, 9622 (1990).10.1103/PhysRevB.42.9622 ↗
21. George, E. P., Raabe, D. & Ritchie, R. O. High-entropy alloys. Nat. Rev. Mater. 4, 515–534 (2019).10.1038/s41578-019-0121-4 ↗
22. Wang, S. et al. Comparison of two calculation models for high entropy alloys: Virtual crystal approximation and special quasi-random structure. Mater. Lett. 282, 128754 (2021).10.1016/j.matlet.2020.128754 ↗
23. Tian, F., Varga, L. K., Shen, J. & Vitos, L. Calculating elastic constants in high-entropy alloys using the coherent potential approximation: Current issues and errors. Comput. Mater. Sci. 111, 350–358 (2016).10.1016/j.commatsci.2015.09.058 ↗
24. Karabin, M. et al. Ab initio approaches to high-entropy alloys: a comparison of cpa, SQS, and supercell methods. J. Mater. Sci. 57, 10677–10690 (2022).10.1007/s10853-022-07186-9 ↗
25. Gao, M. C., Niu, C., Jiang, C. & Irving, D. L. Applications of special quasi-random structures to high-entropy alloys. High-entropy Alloys: Fundam. Appl. 333–368 (2016).10.1007/978-3-319-27013-5_10 ↗
26. Lewis, A. M., Grisafi, A., Ceriotti, M. & Rossi, M. Learning electron densities in the condensed phase. J. Chem. Theory Comput. 17, 7203–7214 (2021).10.1021/acs.jctc.1c00576 ↗
27. Jørgensen, P. B. & Bhowmik, A. Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids. npj Comput. Mater. 8, 183 (2022).10.1038/s41524-022-00863-y ↗
28. Zepeda-Núñez, L. et al. Deep density: circumventing the Kohn-Sham equations via symmetry preserving neural networks. J. Comput. Phys. 443, 110523 (2021).10.1016/j.jcp.2021.110523 ↗
29. Chandrasekaran, A. et al. Solving the electronic structure problem with machine learning. npj Comput. Mater. 5, 22 (2019).10.1038/s41524-019-0162-7 ↗
30. Fiedler, L. et al. Predicting electronic structures at any length scale with machine learning. npj Comput. Mater. 9, 115 (2023).10.1038/s41524-023-01070-z ↗
31. Brockherde, F. et al. Bypassing the kohn-sham equations with machine learning. Nat. Commun. 8, 872 (2017).10.1038/s41467-017-00839-3 ↗
32. del Rio, B. G., Phan, B. & Ramprasad, R. A deep learning framework to emulate density functional theory. npj Comput. Mater. 9, 158 (2023).10.1038/s41524-023-01115-3 ↗
33. Tang, Z. et al. Improving density matrix electronic structure method by deep learning. arXiv preprint arXiv:2406.17561 (2024).
34. Shao, X., Paetow, L., Tuckerman, M. E. & Pavanello, M. Machine learning electronic structure methods based on the one-electron reduced density matrix. Nat. Commun. 14, 6281 (2023).10.1038/s41467-023-41953-9 ↗
35. Hazra, S., Patil, U. & Sanvito, S. Predicting the one-particle density matrix with machine learning. J. Chem. Theory Comput. (2024).10.1021/acs.jctc.4c00042 ↗
36. Sager-Smith, L. M. & Mazziotti, D. A. Reducing the quantum many-electron problem to two electrons with machine learning. J. Am. Chem. Soc. 144, 18959–18966 (2022).10.1021/jacs.2c07112 ↗
37. Teh, Y. S., Ghosh, S. & Bhattacharya, K. Machine-learned prediction of the electronic fields in a crystal. Mech. Mater. 163, 104070 (2021).10.1016/j.mechmat.2021.104070 ↗
38. Pathrudkar, S., Yu, H. M., Ghosh, S. & Banerjee, A. S. Machine learning based prediction of the electronic structure of quasi-one-dimensional materials under strain. Phys. Rev. B 105, 195141 (2022).10.1103/PhysRevB.105.195141 ↗
39. Arora, G., Manzoor, A. & Aidhy, D. S. Charge-density based evaluation and prediction of stacking fault energies in Ni alloys from DFT and machine learning. J. Appl. Phys. 132, 101620 (2022).10.1063/5.0122675 ↗
40. Banerjee, A. S. Ab initio framework for systems with helical symmetry: theory, numerical implementation and applications to torsional deformations in nanostructures. J. Mech. Phys. Solids 154, 104515 (2021).10.1016/j.jmps.2021.104515 ↗
41. Yu, H. M. & Banerjee, A. S. Density functional theory method for twisted geometries with application to torsional deformations in group-iv nanotubes. J. Comput. Phys. 456, 111023 (2022).10.1016/j.jcp.2022.111023 ↗
42. Ghosh, S., Banerjee, A. S. & Suryanarayana, P. Symmetry-adapted real-space density functional theory for cylindrical geometries: Application to large group-IV nanotubes. Phys. Rev. B 100, 125143 (2019).10.1103/PhysRevB.100.125143 ↗
43. Grisafi, A. et al. Transferable machine-learning model of the electron density. ACS Cent. Sci. 5, 57–64 (2018).10.1021/acscentsci.8b00551 ↗
44. Fabrizio, A., Grisafi, A., Meyer, B., Ceriotti, M. & Corminboeuf, C. Electron density learning of non-covalent systems. Chem. Sci. 10, 9424–9432 (2019).10.1039/C9SC02696G ↗
45. Fu, X. et al. A recipe for charge density prediction. Adv. Neural Inf. Process. Syst. 37, 9727–9752 (2024).
46. Qiao, Z. et al. Informing geometric deep learning with electronic interactions to accelerate quantum chemistry. Proc. Natl Acad. Sci. 119, e2205221119 (2022).10.1073/pnas.2205221119 ↗
47. Pathrudkar, S., Thiagarajan, P., Agarwal, S., Banerjee, A. S. & Ghosh, S. Electronic structure prediction of multi-million atom systems through uncertainty quantification enabled transfer learning. npj Comput. Mater. 10, 175 (2024).10.1038/s41524-024-01305-7 ↗
48. Gong, S. et al. Predicting charge density distribution of materials using a local-environment-based graph convolutional network. Phys. Rev. B 100, 184103 (2019).10.1103/PhysRevB.100.184103 ↗
49. Pope, P. & Jacobs, D. Towards combinatorial generalization for catalysts: a Kohn-Sham charge-density approach. Adv. Neural Inf. Process. Syst. 36, 60585–60598 (2024).
50. Zhang, J. et al. Design high-entropy electrocatalyst via interpretable deep graph attention learning. Joule 7, 1832–1851 (2023).10.1016/j.joule.2023.06.003 ↗
51. Zhang, J. et al. Rational design of high-entropy ceramics based on machine learning–a critical review. Curr. Opin. Solid State Mater. Sci. 27, 101057 (2023).10.1016/j.cossms.2023.101057 ↗
52. Li, C., Sharir, O., Yuan, S. & Chan, G. K.-L. Image super-resolution inspired electron density prediction. Nat. Commun. 16, 4811 (2025).10.1038/s41467-025-60095-8 ↗
53. Koker, T., Quigley, K., Taw, E., Tibbetts, K. & Li, L. Higher-order equivariant neural networks for charge density prediction in materials. npj Comput. Mater. 10, 161 (2024).10.1038/s41524-024-01343-1 ↗
54. Okabe, R. et al. Virtual node graph neural network for full phonon prediction. Nat. Comput. Sci. 4, 522–531 (2024).10.1038/s43588-024-00661-0 ↗
55. Fung, V., Zhang, J., Juarez, E. & Sumpter, B. G. Benchmarking graph neural networks for materials chemistry. npj Comput. Mater. 7, 84 (2021).10.1038/s41524-021-00554-0 ↗
56. Jiang, D. et al. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J. Cheminform. 13, 12 (2021).10.1186/s13321-020-00479-8 ↗
57. Pasini, M. et al. Fast and stable deep-learning predictions of material properties for solid solution alloys. J. Phys.: Condens. Matter 33, 084005 (2020).
58. Medasani, B. et al. Predicting defect behavior in B2 intermetallics by merging ab initio modeling and machine learning. npj Comput. Mater. 2, 1 (2016).10.1038/s41524-016-0001-z ↗
59. Deshmukh, G. et al. Active learning of ternary alloy structures and energies. npj Comput. Mater. 10, 116 (2024).10.1038/s41524-024-01256-z ↗
60. Freitas, R., Cao, Y. & Sheriff, K. Chemical-motif characterization of short-range order with e(3)-equivariant graph neural networks. npj Comput. Mater. 10, 215 (2024).10.1038/s41524-024-01393-5 ↗
61. Chen, Z., Shang, Y., Liu, X. & Yang, Y. Accelerated discovery of eutectic compositionally complex alloys by generative machine learning. npj Comput. Mater. 10, 204 (2024).10.1038/s41524-024-01385-5 ↗
62. Vazquez, G., Chakravarty, S., Gurrola, R. & Arróyave, R. A deep neural network regressor for phase constitution estimation in the high entropy alloy system Al-Co-Cr-Fe-Mn-Nb-Ni. npj Comput. Mater. 9, 68 (2023).10.1038/s41524-023-01021-8 ↗
63. Giles, S. A., Sengupta, D., Broderick, S. R. & Rajan, K. Machine-learning-based intelligent framework for discovering refractory high-entropy alloys with improved high-temperature yield strength. npj Comput. Mater. 8, 235 (2022).10.1038/s41524-022-00926-0 ↗
64. Zhang, J., Cai, C., Kim, G., Wang, Y. & Chen, W. Composition design of high-entropy alloys with deep sets learning. npj Comput. Mater. 8, 89 (2022).10.1038/s41524-022-00779-7 ↗
65. Gao, M. C. et al. High-entropy functional materials. J. Mater. Res. 33, 3138–3155 (2018).10.1557/jmr.2018.323 ↗
66. Kumari, P., Gupta, A. K., Mishra, R. K., Ahmad, M. & Shahi, R. R. A comprehensive review: recent progress on magnetic high entropy alloys and oxides. J. Magn. Magn. Mater. 554, 169142 (2022).10.1016/j.jmmm.2022.169142 ↗
67. Dai, F.-Z., Wen, B., Sun, Y., Xiang, H. & Zhou, Y. Theoretical prediction on thermal and mechanical properties of high entropy (zr0. 2hf0. 2ti0. 2nb0. 2ta0. 2) c by deep learning potential. J. Mater. Sci. Technol. 43, 168–174 (2020).10.1016/j.jmst.2020.01.005 ↗
68. Deringer, V. L., Caro, M. A. & Csányi, G. Machine learning interatomic potentials as emerging tools for materials science. Adv. Mater. 31, 1902765 (2019).10.1002/adma.201902765 ↗
69. Körmann, F., Kostiuchenko, T., Shapeev, A. & Neugebauer, J. B2 ordering in body-centered-cubic alnbtiv refractory high-entropy alloys. Phys. Rev. Mater. 5, 053803 (2021).10.1103/PhysRevMaterials.5.053803 ↗
70. Byggmästar, J., Nordlund, K. & Djurabekova, F. Modeling refractory high-entropy alloys with efficient machine-learned interatomic potentials: Defects and segregation. Phys. Rev. B 104, 104101 (2021).10.1103/PhysRevB.104.104101 ↗
71. Pandey, A., Gigax, J. & Pokharel, R. Machine learning interatomic potential for high-throughput screening of high-entropy alloys. JOM 74, 2908–2920 (2022).10.1007/s11837-022-05306-z ↗
72. You, Y. et al. Principal component analysis enables the design of deep learning potential precisely capturing the LZO phase transitions. npj Comput. Mater. 10, 57 (2024).10.1038/s41524-024-01240-7 ↗
73. Li, T., Chen, S. & Jin, X. Coexistence of two types of short-range order in si-ge-sn medium-entropy alloys. Commun. Mater. 3, 66 (2022).10.1038/s43246-022-00289-5 ↗
74. Cao, B., Chen, S., Jin, X., Liu, J. & Li, T. Short-range order in GeSn alloy. ACS Appl. Mater. Interfaces 12, 57245–57253 (2020).10.1021/acsami.0c18483 ↗
75. Wirths, S., Buca, D. & Mantl, S. Si-ge-sn alloys: From growth to applications. Prog. Cryst. Growth Char. Mater. 62, 1–39 (2016).10.1016/j.pcrysgrow.2015.11.001 ↗
76. Zhuang, H. L., Wang, D., Liu, L. & Huang, W. Semiconducting sigesn high-entropy alloy: A density functional theory study. J. Appl. Phys. 126, 225703 (2019).10.1063/1.5135324 ↗
77. Olesinski, R. W. & Abbaschian, G. The Ge-Si (germanium-silicon) system. Bull. Alloy Phase Diagr 5, 180–183 (1984).10.1007/BF02868957 ↗
78. Grützmacher, D., Concepción, O., Zhao, Q.-T. & Buca, D. Si-ge-sn alloys grown by chemical vapour deposition: a versatile material for photonics, electronics, and thermoelectrics. Appl. Phys. A 129, 235 (2023).10.1007/s00339-023-06478-4 ↗
79. Wang, D., Liu, L., Huang, W. & Zhuang, H. L. Semiconducting sigesn high-entropy alloy: A density functional theory study. J. Appl. Phys. 126 (2019).10.1063/1.5135324 ↗
80. Wang, D., Liu, L., Chen, M. & Zhuang, H. Electrical and thermal transport properties of medium-entropy siygeysnx alloys. Acta Mater 199, 443–452 (2020).10.1016/j.actamat.2020.08.053 ↗
81. Cantor, B. Multicomponent high-entropy cantor alloys. Prog. Mater. Sci. 120, 100754 (2021).10.1016/j.pmatsci.2020.100754 ↗
82. He, M.-R. et al. Enhanced damage resistance and novel defect structure of crfeconi under in situ electron irradiation. Scripta Mater. 125, 5–9 (2016).10.1016/j.scriptamat.2016.07.023 ↗
83. Lei, X. & Medford, A. J. A universal framework for featurization of atomistic systems. J. Phys. Chem. Lett. 13, 7911–7919 (2022).10.1021/acs.jpclett.2c02100 ↗
84. Timmerman, L. R., Kumar, S., Suryanarayana, P. & Medford, A. J. Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations. J. Chem. Theory Comput. 20, 5788–5795 (2024).10.1021/acs.jctc.4c00474 ↗
85. Nemani, S. K. et al. High-entropy 2d carbide MXenes: Tivnbmoc3 and tivcrmoc3. ACS Nano 15, 12815–12825 (2021).10.1021/acsnano.1c02775 ↗
86. Nemani, S. K., Torkamanzadeh, M., Wyatt, B. C., Presser, V. & Anasori, B. Functional two-dimensional high-entropy materials. Commun. Mater. 4, 16 (2023).10.1038/s43246-023-00341-y ↗
87. Deshpande, A., Ratsch, C., Ciobanu, C. V. & Kodambaka, S. Entropy stabilization of two-dimensional transition metal dichalcogenide alloys: a density functional theory study. J. Appl. Phys. 131, 234302 (2022).10.1063/5.0094335 ↗
88. He, F. et al. Solid solution island of the co-cr-fe-ni high entropy alloy system. Scr. Mater. 131, 42–46 (2017).10.1016/j.scriptamat.2016.12.033 ↗
89. Sen, S. et al. Grain boundary self- and Mn impurity diffusion in equiatomic cocrfeni multi-principal element alloy. Acta Mater 264, 119588 (2024).10.1016/j.actamat.2023.119588 ↗
90. Zhao, L. et al. High throughput synthesis enabled exploration of cocrfeni-based high entropy alloys. J. Mater. Sci. Technol. 110, 269–282 (2022).10.1016/j.jmst.2021.09.031 ↗
91. Zhang, Z. et al. Computational design of non-equiatomic cocrfeni alloys towards optimized mechanical and surface properties. J. Mater. Res. 37, 2738–2748 (2022).10.1557/s43578-022-00695-y ↗
92. Zhong, Y. & Yang, S. Ab initio modeling of fcc Fe-Co-Cr-Ni high entropy alloys with full composition range. J. Phase Equilibr. Diffus. 42, 656–672 (2021).10.1007/s11669-021-00905-w ↗
93. Zhao, Y. & Park, J.-M. Jang, J.-i & Ramamurty, U. Bimodality of incipient plastic strength in face-centered cubic high-entropy alloys. Acta Mater 202, 124–134 (2021).10.1016/j.actamat.2020.10.066 ↗
94. Tuomisto, F. et al. Segregation of ni at early stages of radiation damage in nicofecr solid solution alloys. Acta Mater 196, 44–51 (2020).10.1016/j.actamat.2020.06.024 ↗
95. Robarts, H. C. et al. Extreme fermi surface smearing in a maximally disordered concentrated solid solution. Phys. Rev. Lett. 124, 046402 (2020).10.1103/PhysRevLett.124.046402 ↗
96. Wei, D. et al. Novel co-rich high entropy alloys with superior tensile properties. Mater. Res. Lett. 7, 82–88 (2019).10.1080/21663831.2018.1553803 ↗
97. Bae, J. W. et al. Exceptional phase-transformation strengthening of ferrous medium-entropy alloys at cryogenic temperatures. Acta Mater 161, 388–399 (2018).10.1016/j.actamat.2018.09.057 ↗
98. Niu, C., Zaddach, A., Koch, C. & Irving, D. First principles exploration of near-equiatomic nifecrco high entropy alloys. J. Alloy. Compd. 672, 510–520 (2016).10.1016/j.jallcom.2016.02.108 ↗
99. Middleburgh, S., King, D., Lumpkin, G., Cortie, M. & Edwards, L. Segregation and migration of species in the Cr-Cofen high entropy alloy. J. Alloy. Compd. 599, 179–182 (2014).10.1016/j.jallcom.2014.01.135 ↗
100. Ghosh, S. & Suryanarayana, P. Sparc: Accurate and efficient finite-difference formulation and parallel implementation of density functional theory: Extended systems. Comput. Phys. Commun. 216, 109–125 (2017).10.1016/j.cpc.2017.02.019 ↗