Classification of AB O3 perovskite solids: a machine learning study
Abstract
Here we explored the use of machine learning methods for classifying whether a particular ABO3chemistry forms a perovskite or non-perovskite structured solid. Starting with three sets of feature pairs (the tolerance and octahedral factors, the A and B ionic radii relative to the radius of O, and the bond valence distances between the A and B ions from the O atoms), we used machine learning to create a hyper-dimensional partial dependency structure plot using all three feature pairs or any two of them. Doing so increased the accuracy of our predictions by 2–3 percentage points over using any one pair. We also included the Mendeleev numbers of the A and B atoms to this set of feature pairs. Moreover, doing this and using the capabilities of our machine learning algorithm, the gradient tree boosting classifier, enabled us to generate a new type of structure plot that has the simplicity of one based on using just the Mendeleev numbers, but with the added advantages of having a higher accuracy and providing a measure of likelihood of the predicted structure.
- Authors:
-
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1257974
- Report Number(s):
- LA-UR-15-22854
Journal ID: ISSN 2052-5206; ACSBDA; PII: S2052520615013979
- Grant/Contract Number:
- AC52-06NA25396
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Acta Crystallographica. Section B, Structural Science, Crystal Engineering and Materials (Online)
- Additional Journal Information:
- Journal Name: Acta Crystallographica. Section B, Structural Science, Crystal Engineering and Materials (Online); Journal Volume: 71; Journal Issue: 5; Journal ID: ISSN 2052-5206
- Publisher:
- International Union of Crystallography
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE
Citation Formats
Pilania, G., Balachandran, P. V., Gubernatis, J. E., and Lookman, T. Classification of AB O3 perovskite solids: a machine learning study. United States: N. p., 2015.
Web. doi:10.1107/S2052520615013979.
Pilania, G., Balachandran, P. V., Gubernatis, J. E., & Lookman, T. Classification of AB O3 perovskite solids: a machine learning study. United States. https://doi.org/10.1107/S2052520615013979
Pilania, G., Balachandran, P. V., Gubernatis, J. E., and Lookman, T. Thu .
"Classification of AB O3 perovskite solids: a machine learning study". United States. https://doi.org/10.1107/S2052520615013979. https://www.osti.gov/servlets/purl/1257974.
@article{osti_1257974,
title = {Classification of AB O3 perovskite solids: a machine learning study},
author = {Pilania, G. and Balachandran, P. V. and Gubernatis, J. E. and Lookman, T.},
abstractNote = {Here we explored the use of machine learning methods for classifying whether a particular ABO3chemistry forms a perovskite or non-perovskite structured solid. Starting with three sets of feature pairs (the tolerance and octahedral factors, the A and B ionic radii relative to the radius of O, and the bond valence distances between the A and B ions from the O atoms), we used machine learning to create a hyper-dimensional partial dependency structure plot using all three feature pairs or any two of them. Doing so increased the accuracy of our predictions by 2–3 percentage points over using any one pair. We also included the Mendeleev numbers of the A and B atoms to this set of feature pairs. Moreover, doing this and using the capabilities of our machine learning algorithm, the gradient tree boosting classifier, enabled us to generate a new type of structure plot that has the simplicity of one based on using just the Mendeleev numbers, but with the added advantages of having a higher accuracy and providing a measure of likelihood of the predicted structure.},
doi = {10.1107/S2052520615013979},
journal = {Acta Crystallographica. Section B, Structural Science, Crystal Engineering and Materials (Online)},
number = 5,
volume = 71,
place = {United States},
year = {Thu Jul 23 00:00:00 EDT 2015},
month = {Thu Jul 23 00:00:00 EDT 2015}
}
Web of Science
Figures / Tables:
Works referenced in this record:
Formability of ABO3 perovskites
journal, June 2004
- Li, Chonghe; Soh, Kitty Chi Kwan; Wu, Ping
- Journal of Alloys and Compounds, Vol. 372, Issue 1-2
Prediction of the crystal structures of perovskites using the software program SPuDS
journal, November 2001
- Lufaso, Michael W.; Woodward, Patrick M.
- Acta Crystallographica Section B Structural Science, Vol. 57, Issue 6
Structure classification and melting temperature prediction in octet AB solids via machine learning
journal, June 2015
- Pilania, G.; Gubernatis, J. E.; Lookman, T.
- Physical Review B, Vol. 91, Issue 21
Quantum-Defect Electronegativity Scale for Nontransition Elements
journal, October 1974
- John, Judith; Bloch, Aaron N.
- Physical Review Letters, Vol. 33, Issue 18
Determination of the Bonding and Valence Distribution in Inorganic Solids by the Maximum Entropy Method
journal, June 1998
- Rao, G. H.; Brown, I. D.
- Acta Crystallographica Section B Structural Science, Vol. 54, Issue 3
Structural stability and formability of AB O 3 -type perovskite compounds
journal, November 2007
- Zhang, Huan; Li, Na; Li, Keyan
- Acta Crystallographica Section B Structural Science, Vol. 63, Issue 6
Quantum-defect theory of heats of formation and structural transition energies of liquid and solid simple metal alloys and compounds
journal, March 1978
- Chelikowsky, J. R.; Phillips, J. C.
- Physical Review B, Vol. 17, Issue 6
Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenides
journal, September 1976
- Shannon, R. D.
- Acta Crystallographica Section A, Vol. 32, Issue 5, p. 751-767
On the crystal chemistry of normal valence compounds
journal, December 1959
- Mooser, E.; Pearson, W. B.
- Acta Crystallographica, Vol. 12, Issue 12
Formability of ABO3 cubic perovskites
journal, April 2008
- Feng, L. M.; Jiang, L. Q.; Zhu, M.
- Journal of Physics and Chemistry of Solids, Vol. 69, Issue 4
Lattice constant of cubic perovskites
journal, October 2009
- Verma, A. S.; Jindal, V. K.
- Journal of Alloys and Compounds, Vol. 485, Issue 1-2
Prediction of Formability in Perovskite-Type Oxides~!2008-08-05~!2008-10-08~!2008-12-05~!
journal, December 2008
- Kumar, A.; Verma, A. S.; Bhardwaj, S. R.
- The Open Applied Physics Journal, Vol. 1, Issue 1
Identifying the ‘inorganic gene’ for high-temperature piezoelectric perovskites through statistical learning
journal, February 2011
- Balachandran, Prasanna V.; Broderick, Scott R.; Rajan, Krishna
- Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 467, Issue 2132
Comment on “Prediction of lattice constant in cubic perovskites”
journal, August 2007
- Moreira, Roberto L.; Dias, Anderson
- Journal of Physics and Chemistry of Solids, Vol. 68, Issue 8
Recent Developments in the Methods and Applications of the Bond Valence Model
journal, December 2009
- Brown, Ian David
- Chemical Reviews, Vol. 109, Issue 12
Bond-valence parameters obtained from a systematic analysis of the Inorganic Crystal Structure Database
journal, August 1985
- Brown, I. D.; Altermatt, D.
- Acta Crystallographica Section B Structural Science, Vol. 41, Issue 4
Prediction of lattice constant in cubic perovskites
journal, July 2006
- Jiang, L. Q.; Guo, J. K.; Liu, H. B.
- Journal of Physics and Chemistry of Solids, Vol. 67, Issue 7
Simple descriptor derived from symbolic regression accelerating the discovery of new perovskite catalysts
journal, July 2020
- Weng, Baicheng; Song, Zhilong; Zhu, Rilong
- Nature Communications, Vol. 11, Issue 1
Comment on "Prediction of lattice constant in cubic perovskites"
text, January 2007
- Moreira, Roberto L.; Dias, Anderson
- arXiv
Works referencing / citing this record:
Data-enabled structure–property mappings for lanthanide-activated inorganic scintillators
journal, February 2019
- Pilania, G.; Liu, Xiang-Yang; Wang, Zhehui
- Journal of Materials Science, Vol. 54, Issue 11
Accelerated search for materials with targeted properties by adaptive design
journal, April 2016
- Xue, Dezhen; Balachandran, Prasanna V.; Hogden, John
- Nature Communications, Vol. 7, Issue 1
Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning
journal, April 2018
- Balachandran, Prasanna V.; Kowalski, Benjamin; Sehirlioglu, Alp
- Nature Communications, Vol. 9, Issue 1
Recent advances and applications of machine learning in solid-state materials science
journal, August 2019
- Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana
- npj Computational Materials, Vol. 5, Issue 1
Inverse design in search of materials with target functionalities
journal, March 2018
- Zunger, Alex
- Nature Reviews Chemistry, Vol. 2, Issue 4
Machine learning bandgaps of double perovskites
journal, January 2016
- Pilania, G.; Mannodi-Kanakkithodi, A.; Uberuaga, B. P.
- Scientific Reports, Vol. 6, Issue 1
New tolerance factor to predict the stability of perovskite oxides and halides
journal, February 2019
- Bartel, Christopher J.; Sutton, Christopher; Goldsmith, Bryan R.
- Science Advances, Vol. 5, Issue 2
Finding New Perovskite Halides via Machine Learning
journal, April 2016
- Pilania, Ghanshyam; Balachandran, Prasanna V.; Kim, Chiho
- Frontiers in Materials, Vol. 3
New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides
text, January 2018
- Bartel, Christopher J.; Sutton, Christopher; Goldsmith, Bryan R.
- arXiv
Figures / Tables found in this record: