Machine learning for exploring small polaron configurational space
Source abstract
Abstract
Abstract Polaron defects are ubiquitous in materials and play an important role in many processes involving carrier mobility, charge transfer and surface reactivity. Determining small polarons’ spatial distributions is essential to understand materials properties and functionalities. However, the required exploration of the configurational space is computationally demanding when using first principles methods. Here, we propose a machine-learning (ML) accelerated search that determines the ground state polaronic configuration. The ML model is trained on databases of polaron configurations generated by density functional theory (DFT) via molecular dynamics or random sampling. To establish a mapping between configurations and their stability, we designed descriptors modelling the interactions among polarons and charged point defects. We used the DFT+ML protocol to explore the polaron configurational space for two surface-systems, reduced rutile TiO2(110) and Nb-doped SrTiO3(001). The ML-aided search proposes additional polaronic configurations and can be utilized to determine optimal polaron distributions at any charge concentration.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Electronic and Structural Properties of Oxides · X-ray Diffraction in Crystallography
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (66)
Show source-provided references
1. Franchini, C., Reticcioli, M., Setvin, M. & Diebold, U. Polarons in materials. Nat. Rev. Mater. 560–586 (2021).10.1038/s41578-021-00289-w ↗
2. Alexandrov, A. S. & Devreese, J. T. Advances in Polaron Physics (Springer, 2010).10.1007/978-3-642-01896-1 ↗
3. Landau, L. D. Über die Bewegung der Elektronen im Kristallgitter. Phys. Z. Sowjet. 664, 644–645 (1933).
4. Fröhlich, H., Pelzer, H. & Zienau, S. Properties of slow electrons in polar materials. Philos. Mag. 41, 221 (1950).10.1080/14786445008521794 ↗
5. Coropceanu, V. et al. Charge transport in organic semiconductors. Chemical Reviews 107, 926–952 (2007).10.1021/cr050140x ↗
6. Moser, S. et al. Tunable polaronic conduction in anatase TiO2. Phys. Rev. Lett. 110, 196403 (2013).10.1103/PhysRevLett.110.196403 ↗
7. Fratini, S. & Ciuchi, S. Dynamical mean-field theory of transport of small polarons. Phys. Rev. Lett. 91, 256403 (2003).10.1103/PhysRevLett.91.256403 ↗
8. Deskins, N. A. & Dupuis, M. Intrinsic Hole Migration Rates in TiO2 from Density Functional Theory. J. Phys. Chem. C 113, 346–358 (2009).10.1021/jp802903c ↗
9. Zhang, D., Han, Z.-K., Murgida, G. E., Ganduglia-Pirovano, M. V. & Gao, Y. Oxygen-vacancy dynamics and entanglement with polaron hopping at the reduced CeO2(111) surface. Phys. Rev. Lett. 122, 096101 (2019).10.1103/PhysRevLett.122.096101 ↗
10. Mishchenko, A. S., Nagaosa, N., De Filippis, G., de Candia, A. & Cataudella, V. Mobility of holstein polaron at finite temperature: An unbiased approach. Phys. Rev. Lett. 114, 146401 (2015).10.1103/PhysRevLett.114.146401 ↗
11. Mishchenko, A. S. et al. Polaron mobility in the “beyond quasiparticles” regime. Phys. Rev. Lett. 123, 076601 (2019).10.1103/PhysRevLett.123.076601 ↗
12. Papageorgiou, A. C. et al. Electron traps and their effect on the surface chemistry of TiO2(110). Proc. Natl. Acad. Sci. 107, 2391–2396 (2010).10.1073/pnas.0911349107 ↗
13. Reticcioli, M. et al. Interplay between adsorbates and polarons: CO on rutile TiO2(110). Phys. Rev. Lett. 122, 016805 (2019).10.1103/PhysRevLett.122.016805 ↗
14. Reticcioli, M. et al. Polaron-driven surface reconstructions. Phys. Rev. X 7, 031053 (2017).
15. Rousseau, R., Glezakou, V.-A. & Selloni, A. Theoretical insights into the surface physics and chemistry of redox-active oxides. Nat. Rev. Mater. https://doi.org/10.1038/s41578-020-0198-9 (2020).10.1038/s41578-020-0198-9 ↗
16. Sokolović, I. et al. Resolving the adsorption of molecular O2 on the rutile TiO2(110) surface by noncontact atomic force microscopy. Proc. Natl. Acad. Sci. 117, 14827–14837 (2020).10.1073/pnas.1922452117 ↗
17. Mechelen, J. L. M. et al. Electron-phonon interaction and charge carrier mass enhancement in SrTiO3. Phys. Rev. Lett. 100, 226403 (2008).10.1103/PhysRevLett.100.226403 ↗
18. Yoon, S. et al. Raman and optical spectroscopic studies of small-to-large polaron crossover in the perovskite manganese oxides. Phys. Rev. B 58, 2795–2801 (1998).10.1103/PhysRevB.58.2795 ↗
19. Klimin, S., Tempere, J., Devreese, J. T., Franchini, C. & Kresse, G. Optical response of an interacting polaron gas in strongly polar crystals. Appl. Sci. 10, 2059 (2020).10.3390/app10062059 ↗
20. Srimath Kandada, A. R. & Silva, C. Exciton polarons in two-dimensional hybrid metal-halide perovskites. Journal Phys. Chem. Lett. 11, 3173–3184 (2020).10.1021/acs.jpclett.9b02342 ↗
21. Reticcioli, M., Setvin, M., Schmid, M., Diebold, U. & Franchini, C. Formation and dynamics of small polarons on the rutile TiO2(110) surface. Phys. Rev. B 98, 045306 (2018).10.1103/PhysRevB.98.045306 ↗
22. Reticcioli, M., Diebold, U., Kresse, G. & Franchini, C. Small Polarons in Transition Metal Oxides, 1–39 (Springer International Publishing, Cham, 2019).10.1007/978-3-319-50257-1_52-1 ↗
23. Shluger, A. L. & Stoneham, A. M. Small polarons in real crystals: concepts and problems. J. Phys.: Condensed Matt. 5, 3049–3086 (1993).
24. Sio, W. H., Verdi, C., Poncé, S. & Giustino, F. Polarons from first principles, without supercells. Phys. Rev. Lett. 122, 246403 (2019).10.1103/PhysRevLett.122.246403 ↗
25. Sio, W. H., Verdi, C., Poncé, S. & Giustino, F. Ab initio theory of polarons: Formalism and applications. Phys. Rev. B 99, 235139 (2019).10.1103/PhysRevB.99.235139 ↗
26. Goyal, A., Gorai, P., Peng, H., Lany, S. & Stevanović, V. A computational framework for automation of point defect calculations. Computational Mater. Sci. 130, 1–9 (2017).10.1016/j.commatsci.2016.12.040 ↗
27. Makov, G. & Payne, M. C. Periodic boundary conditions in ab initio calculations. Phys. Rev. B 51, 4014–4022 (1995).10.1103/PhysRevB.51.4014 ↗
28. Freysoldt, C., Neugebauer, J. & Van de Walle, C. G. Fully ab initio finite-size corrections for charged-defect supercell calculations. Phys. Rev. Lett. 102, 016402 (2009).10.1103/PhysRevLett.102.016402 ↗
29. Kowalski, P. M., Camellone, M. F., Nair, N. N., Meyer, B. & Marx, D. Charge localization dynamics induced by oxygen vacancies on the TiO2(110) surface. Phys. Rev. Lett. 105, 146405 (2010).10.1103/PhysRevLett.105.146405 ↗
30. Allen, J. P. & Watson, G. W. Occupation matrix control of d- and f-electron localisations using DFT+U. Phys. Chem. Chem. Phys. 16, 21016–21031 (2014).10.1039/C4CP01083C ↗
31. Pham, T. D. & Deskins, N. A. Efficient method for modeling polarons using electronic structure methods. J. Chem. Theory Comput. 16, 5264–5278 (2020).10.1021/acs.jctc.0c00374 ↗
32. Schmidt, J., Marques, M. R. G., Botti, S. & Marques, M. A. L. Recent advances and applications of machine learning in solid-state materials science. npj Comput. Mater. 5, 1–36 (2019).10.1038/s41524-019-0221-0 ↗
33. von Lilienfeld, O. A. & Burke, K. Retrospective on a decade of machine learning for chemical discovery. Nat. Commun. 11, 4895 (2020).10.1038/s41467-020-18556-9 ↗
34. Ramprasad, R., Batra, R., Pilania, G., Mannodi-Kanakkithodi, A. & Kim, C. Machine learning in materials informatics: recent applications and prospects. npj Comput. Mater. 3, 1–13 (2017).10.1038/s41524-017-0056-5 ↗
35. Behler, J., Lorenz, S. & Reuter, K. Representing molecule-surface interactions with symmetry-adapted neural networks. J. Chem. Phys. 127, 014705 (2007).10.1063/1.2746232 ↗
36. Jinnouchi, R., Karsai, F. & Kresse, G. On-the-fly machine learning force field generation: Application to melting points. Physical Rev. B 100, 014105 (2019).10.1103/PhysRevB.100.014105 ↗
37. Bartók, A. P., Payne, M. C., Kondor, R. & Csányi, G. Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons. Physical Rev. Lett. 104, 136403 (2010).10.1103/PhysRevLett.104.136403 ↗
38. Ko, T. W., Finkler, J. A., Goedecker, S. & Behler, J. A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer. Nat. Commun. 12, 398 (2021).10.1038/s41467-020-20427-2 ↗
39. Unke, O. T. et al. SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects. Nat. Commun. 12, 7273 (2021).10.1038/s41467-021-27504-0 ↗
40. Eckhoff, M., Lausch, K. N., Blöchl, P. E. & Behler, J. Predicting oxidation and spin states by high-dimensional neural networks: Applications to lithium manganese oxide spinels. The Journal of Chemical Physics 153, 164107 (2020).10.1063/5.0021452 ↗
41. Bishop, C. M. Pattern Recognition and Machine Learning. Information Science and Statistics (Springer-Verlag, New York, 2006).
42. Schütt, K. T. et al. (eds.) Machine Learning Meets Quantum Physics. Lecture Notes in Physics (Springer International Publishing, 2020).10.1007/978-3-030-40245-7 ↗
43. Diebold, U. The surface science of titanium dioxide. Surface Science Reports 48, 53–229 (2003).10.1016/S0167-5729(02)00100-0 ↗
44. Setvin, M. et al. Direct view at excess electrons in TiO2 rutile and anatase. Phys. Rev. Lett. 113, 086402 (2014).10.1103/PhysRevLett.113.086402 ↗
45. Deskins, N. A. & Dupuis, M. Electron transport via polaron hopping in bulk TiO2: A density functional theory characterization. Phys. Rev. B 75, 195212 (2007).10.1103/PhysRevB.75.195212 ↗
46. Moses, P. G., Janotti, A., Franchini, C., Kresse, G. & Van De Walle, C. G. Donor defects and small polarons on the TiO2(110) surface. J. Appl. Phys. 119, 181503 (2016).10.1063/1.4948239 ↗
47. Klyukin, K. & Alexandrov, V. Effect of intrinsic point defects on ferroelectric polarization behavior of SrTiO3. Phys. Rev. B 95, 035301 (2017).10.1103/PhysRevB.95.035301 ↗
48. Janotti, A., Varley, J. B., Choi, M. & Van de Walle, C. G. Vacancies and small polarons in SrTiO3. Phys. Rev. B 90, 085202 (2014).10.1103/PhysRevB.90.085202 ↗
49. Eglitis, R. I. Ab initio calculations of SrTiO3, BaTiO3, PbTiO3, CaTiO3, SrZrO3, PbZrO3 and BaZrO3 (001), (011) and (111) surfaces as well as F centers, polarons, KTN solid solutions and Nb impurities therein. Int. J. Modern Phys. B 28, 1430009 (2014).10.1142/S0217979214300096 ↗
50. Onishi, H. & Iwasawa, Y. Reconstruction of TiO2(110) surface: STM study with atomic-scale resolution. Surface Sci. 313, L783–L789 (1994).10.1016/0039-6028(94)91146-0 ↗
51. Krüger, P. et al. Defect States at the TiO2(110) Surface probed by resonant photoelectron diffraction. Phys. Rev. Lett. 100, 055501 (2008).10.1103/PhysRevLett.100.055501 ↗
52. Shibuya, T., Yasuoka, K., Mirbt, S. & Sanyal, B. Subsurface polaron concentration as a factor in the chemistry of reduced TiO2 (110) surfaces. J. Phys. Chem. C 121, 11325–11334 (2017).10.1021/acs.jpcc.7b00935 ↗
53. Kresse, G. & Furthmüller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. Mater. Sci. 6, 15–50 (1996).10.1016/0927-0256(96)00008-0 ↗
54. Kresse, G. & Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B 54, 11169–11186 (1996).10.1103/PhysRevB.54.11169 ↗
55. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865–3868 (1996).10.1103/PhysRevLett.77.3865 ↗
56. Hao, X., Wang, Z., Schmid, M., Diebold, U. & Franchini, C. Coexistence of trapped and free excess electrons in SrTiO3. Phys. Rev. B 91, 085204 (2015).10.1103/PhysRevB.91.085204 ↗
57. Hou, Z. & Terakura, K. Defect states induced by oxygen vacancies in cubic SrTiO3: First-principles calculations. J. Phys. Soc. Japan 79, 114704 (2010).10.1143/JPSJ.79.114704 ↗
58. Choi, M., Oba, F., Kumagai, Y. & Tanaka, I. Anti-ferrodistortive-like oxygen-octahedron rotation induced by the oxygen vacancy in cubic SrTiO3. Adv. Mater. 25, 86–90 (2013).10.1002/adma.201203580 ↗
59. Blöchl, P. E. Projector augmented-wave method. Phys. Rev. B 50, 17953–17979 (1994).10.1103/PhysRevB.50.17953 ↗
60. Kresse, G. & Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B 59, 1758–1775 (1999).10.1103/PhysRevB.59.1758 ↗
61. Sokolović, I. et al. Quest for a pristine unreconstructed SrTiO3(001) surface: An atomically resolved study via noncontact atomic force microscopy. Phys. Rev. B 103, L241406 (2021).10.1103/PhysRevB.103.L241406 ↗
62. Sokolović, I., Schmid, M., Diebold, U. & Setvin, M. Incipient ferroelectricity: A route towards bulk-terminated SrTiO3. Phys. Rev. Mater. 3, 034407 (2019).10.1103/PhysRevMaterials.3.034407 ↗
63. Kingma, D. P. & Ba, J. Adam: A Method for Stochastic Optimization. (2014).
64. van der Walt, S., Colbert, S. C. & Varoquaux, G. The NumPy Array: A structure for efficient numerical computation. Comput. Sci. Eng. 13, 22–30 (2011).10.1109/MCSE.2011.37 ↗
65. Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. J. Machine Learning Res. 12, 2825–2830 (2011).
66. Paszke, A. et al. Pytorch: An imperative style, high-performance deep learning library. In Wallach, H. et al. (eds.) Advances in Neural Information Processing Systems 32, 8024–8035 (Curran Associates, Inc., 2019).