journal article·2022-07Open access

A machine learning approach to predict thermal expansion of complex oxides

Jian Peng, N.S. Harsha Gunda, Craig A. Bridges, Sangkeun Lee, J. Allen Haynes, Dongwon Shin

Abstract

Abstract Although it is of scientific and practical importance, the state-of-the-art of predicting the thermal expansion of oxides over broad temperature and composition ranges by physics-based atomistic simulations is currently limited to qualitative agreements. We present an emerging machine learning (ML) approach to accurately predict the thermal expansion of cubic oxides with a dataset consisting of experimentally measured lattice parameters while using the metal cation polyhedron and temperature as descriptors. High-fidelity ML models that can accurately predict temperature- and composition-dependent lattice parameters of cubic oxides with isotropic thermal expansions have been successfully trained. The ML-predicted thermal expansions of oxides not included in the training dataset have shown good agreement with available experiments. The limitations of the current approach and challenges to go beyond cubic oxides with isotropic thermal expansion are also briefly discussed.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Catalysis and Oxidation Reactions · Electronic and Structural Properties of Oxides · Machine Learning in Materials Science

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (75)

Show source-provided references
1. Materials design for the next generation thermal barrier coatings10.1146/annurev.matsci.33.011403.113718 ↗
2. Emerging materials and processes for thermal barrier systems10.1016/j.cossms.2004.03.009 ↗
3. Transport properties of solid oxide electrolyte ceramics: a brief review10.1016/j.ssi.2004.06.015 ↗
4. Thermal expansion of SOFC materials10.1007/BF02375916 ↗
5. Comparison of approximations in density functional theory calculations: Energetics and structure of binary oxides10.1103/PhysRevB.96.094102 ↗
6. First-principles investigation of LaGaO3 and LaInO3 lanthanum perovskite oxides10.1080/14786435.2016.1189100 ↗
7. Phonons and related crystal properties from density-functional perturbation theory10.1103/RevModPhys.73.515 ↗
8. First-principles study of structural, elastic, electronic, and thermal properties of SrTiO3 perovskite cubic10.1016/j.physleta.2008.12.017 ↗
9. High-throughput prediction of finite-temperature properties using the quasi-harmonic approximation10.1016/j.commatsci.2016.07.043 ↗
10. Anisotropic thermal expansion of layered MoO3 crystals10.1103/PhysRevB.69.064111 ↗
11. Special quasirandom structures10.1103/PhysRevLett.65.353 ↗
12. Crystal structure and stability of complex precipitate phases in Al–Cu–Mg–(Si) and Al–Zn–Mg alloys10.1016/S1359-6454(01)00229-4 ↗
13. Thermodynamic properties of binary hcp solution phases from special quasirandom structures10.1103/PhysRevB.74.024204 ↗
14. Hubbard-corrected DFT energy functionals: The LDA+U description of correlated systems10.1002/qua.24521 ↗
15. First-principles LDA+ U and GGA+ U study of cerium oxides: dependence on the effective U parameter10.1103/PhysRevB.75.035115 ↗
16. Choice of U for DFT+ U calculations for titanium oxides10.1021/jp111350u ↗
17. The Li intercalation potential of LiMPO4 and LiMSiO4 olivines with M=Fe, Mn Co10.1016/j.elecom.2004.09.007 ↗
18. Cuffini S, Guevara J, Mascarenhas Y, editors. Structural analysis of polycrystalline CaRuO3 and SrRuO3 ceramics from room temperature up to 1273 K. Mater. Sci. Forum. 1996; 228-231: 789-794.10.4028/www.scientific.net/MSF.228-231.789 ↗
19. Crystal structure and temperature dependent structural phase transitions in (Ba1-xSrx)PbO3 (x=0, 0.2, 0.6) perovskite ceramics10.1016/j.ceramint.2018.07.041 ↗
20. X-ray study and electrical properties of system BaxSr(1–x)MoO310.1016/0022-1902(60)80262-X ↗
21. Role of intrinsic disorder in the structural phase transition of magnetoelectric EuTiO310.1103/PhysRevB.85.184107 ↗
22. Structural phase transitions in EuNbO3 perovskite10.1016/j.jssc.2016.04.032 ↗
23. Structural properties of barium stannate10.1016/j.jssc.2018.01.019 ↗
24. Variable-temperature single-crystal X-ray diffraction study of tetragonal and cubic perovskite-type barium titanate phases10.1107/S2052520615022544 ↗
25. Structural phase transitions in BaCeO310.1016/0167-2738(94)90199-6 ↗
26. Fu W, Visser D, Knight K, IJdo D. Temperature-induced phase transitions in BaTbO3. J. Solid State Chem. 2004;177(4-5):1667-1671.10.1016/j.jssc.2003.12.022 ↗
27. Machine Learning Assisted Synthesis of Metal-Organic Nanocapsules10.1021/jacs.9b11569 ↗
28. High-throughput machine-learning-driven synthesis of full-Heusler compounds10.1021/acs.chemmater.6b02724 ↗
29. Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties10.1063/1.4952607 ↗
30. Universal fragment descriptors for predicting properties of inorganic crystals10.1038/ncomms15679 ↗
31. Machine-Learning-Assisted Synthesis of Polar Racemates10.1021/jacs.0c01239 ↗
32. Coupling physics in machine learning to predict properties of high-temperatures alloys. npj Comput
33. Data analytics approach for melt-pool geometries in metal additive manufacturing10.1080/14686996.2019.1671140 ↗
34. Modern data analytics approach to predict creep of high-temperature alloys10.1016/j.actamat.2019.02.017 ↗
35. A Universal Machine Learning Algorithm for Large-Scale Screening of Materials10.1021/jacs.9b11084 ↗
36. J. Peng, Y. Yamamoto, P. BM, S. Lee, J.A. Haynes, D. Shin. Uncertainty Quantification of Machine Learning Predicted Creep Property of Alumina-Forming Austenitic Alloys. JOM. 2021;73:164–173.10.1007/s11837-020-04423-x ↗
37. Machine learning assisted design of high entropy alloys with desired property10.1016/j.actamat.2019.03.010 ↗
38. A useful fiction: polyhedral modeling of mineral properties
39. Bulk modulus—volume relationship for cation-anion polyhedra10.1029/JB084iB12p06723 ↗
40. Hazen RMF, L. W. Structural Variation with Temperature. In Comparitive crystal chemistry: Wiley; 1982. p. 115–146.
41. High-temperature crystal chemistry of sodium zirconium phosphate (NZP)10.1557/JMR.1987.0329 ↗
42. Heat capacity, relative enthalpy, and calorimetric entropy of silicate minerals; an empirical method of prediction
43. A new method to calculate end-member thermodynamic properties of minerals from their constituent polyhedra II: heat capacity, compressibility and thermal expansion10.1111/j.1525-1314.2005.00603.x ↗
44. Estimating the thermodynamic properties (ΔG of and ΔH of) of silicate minerals at 298 K from the sum of polyhedral contributions
45. Estimating the thermodynamic properties of phosphate minerals at high and low temperature from the sum of constituent units10.3989/egeol.39849.060 ↗
46. A new method to calculate end-member thermodynamic properties of minerals from their constituent polyhedra I: enthalpy, entropy and molar volume10.1111/j.1525-1314.2005.00569.x ↗
47. Estimating the free energy of formation of silicate minerals at high temperatures from the sum of polyhedral contributions
48. Comparative crystal chemistry and the polyhedral approach
49. Au · 1984
50. ASCENDS: Advanced data SCiENce toolkit for Non-Data Scientists10.21105/joss.01656 ↗
51. Advanced data science toolkit for non-data scientists–A user guide10.1016/j.calphad.2019.101733 ↗
52. Bayesian interpolation10.1162/neco.1992.4.3.415 ↗
53. Freedman · 2009
54. An introduction to kernel and nearest-neighbor nonparametric regression10.1080/00031305.1992.10475879 ↗
55. The random subspace method for constructing decision forests10.1109/34.709601 ↗
56. Awad · 2015
57. Towards an accurate description of perovskite ferroelectrics: exchange and correlation effects
58. SrTiO3 and BaTiO3 revisited using the projector augmented wave method: Performance of hybrid and semilocal functionals10.1103/PhysRevB.78.104116 ↗
59. Electronic properties of reduced molybdenum oxides10.1039/C7CP00644F ↗
60. GGA-1/2 self-energy correction for accurate band structure calculations: the case of resistive switching oxides10.1088/2399-6528/aade7e ↗
61. Restoring the density-gradient expansion for exchange in solids and surfaces10.1103/PhysRevLett.100.136406 ↗
62. Hazen · 1982
63. Thermal Expansion of MgCr2O4, MgAl2O4 and MgFe2O4
64. Rationalization of Diversity in Spinel MgFe2O4 Surfaces10.1002/admi.201901218 ↗
65. First-Principles Study of the Geometric and Electronic Structures and Optical Properties of Vacancy Magnesium Ferrite10.1007/s11661-020-05925-8 ↗
66. Kopnin E, Istomin SY, D'yachenko O, Antipov E, Bordet P, Capponi J, et al. Synthesis, structure, and resistivity properties of K1−xBaxNbO3 (0.2≤x≤0.5) and K0.5Sr0.5NbO3. Mater. Res. Bull. 1995;30(11):1379-1386.10.1016/0025-5408(95)00117-4 ↗
67. „BaNb3O6 “ist ein Perowskit BaNbO3, eine Korrektur und ein Beitrag zu BaxNbO3/“BaNb3O6 “is a Perovskite BaNbO3, a Correction and a Contribution to BaxNbO310.1515/znb-1997-0201 ↗
68. Atomistic study of structural, elastic, electronic and thermal properties of perovskites Ba(Ti, Zr, Nb)O310.1016/j.commatsci.2006.10.012 ↗
69. First-principles studies of the atomic, elastic and vibrational properties of BaNbO310.1063/1.4944244 ↗
70. Crystal structure, thermal expansion and electrical conductivity of perovskite oxides BaxSr1−xCo0.8Fe0.2O3−δ (0.3≤x≤ 0.7)10.1016/j.jeurceramsoc.2005.06.047 ↗
71. Oxygen-sorptive properties and defect structure of perovskite-type oxides10.1246/cl.1984.893 ↗
72. Structure and electrical properties of La1−xSrxCo1−yFeyO3. Part 1. The system La0.8Sr0.2Co1−yFeyO310.1016/0167-2738(94)00244-M ↗
73. Thermal expansion and solubility limits of cerium-doped lanthanum zirconates10.1016/j.jallcom.2012.02.077 ↗
74. O’Keeffe M, Hyde B. The role of nonbonded forces in crystals, in Structure and Bonding in Crystals, edited by M. O’Keefe and A. Navrotsky (Academic Press Inc., New York, 1981), Chap. 10, Vol. 1, p. 227.10.1016/B978-0-12-525101-3.50016-4 ↗
75. Thermal expansion in insulating solids from first principles10.1063/1.5125779 ↗