AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Materiomics Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research paper | Open Access

Prediction of nature of band gap of perovskite oxides (ABO3) using a machine learning approach

Sudha Priyanga Ga, Manoj N. Matturb,1, N. Nagappanc,1, Smarak Rathc, Tiju Thomasc( )
Department of Physics, Research Institute for Natural Science, and Institute for High Pressure at Hanyang University, Hanyang University, 222 Wangsimniro, Seongdong-Ku, Seoul 04763, Republic of Korea
Department of Metallurgical and Materials Engineering, Indian Institute of Technology Bhubaneswar, Odisha, 752050, India
Department of Metallurgical and Materials Engineering, Indian Institute of Technology Madras, Chennai, 600036, India

Peer review under responsibility of The Chinese Ceramic Society.

1 Authors contributed equally.

Show Author Information

Abstract

A material's electronic properties and technological utility depend on its band gap value and the nature of band gap (i.e. direct or indirect). This nature of band gaps is notoriously difficult to compute from first principles. In fact it is computationally intense to approximate and also rather time consuming. Hence its prediction represents a challenging problem. Machine learning based approach offers a promising and computationally efficient means to address this problem. Here we predict the nature of band gap for perovskite oxides (ABO3) with elemental composition, ionic radius, ionic character and electronegativity. We do this by training machine learning models on computationally generated datasets. Knowing the nature of the band gap of the perovskite oxides (whether direct or indirect) plays a pivotal role in determining whether the perovskite can be used for photovoltaic or photocatalytic applications. A total of 5329 perovskite oxides are considered in this study. Here, we determine the correlation between the nature of band gap and the composition of the perovskite oxide. A Random Forest algorithm is used for predicting the same since it yielded higher accuracy (~91%) compared to the other Machine Learning models. The approach suggested here can be used to predict the nature of bandgap and can also aid in novel materials discovery within the family of perovskites. This is a robust, quick, and low-cost strategy to find novel materials for light harvesting applications in particular. Also we present feature ranking as it pertains to prediction of nature of bandgap and also discuss correlation between the features. We also show feature importance graphs and SHapley Additive exPlanations (SHAP) as is relevant for prediction of nature of band gaps. Using the approach reported, NaPuO3 and VPbO3 are discovered to be good candidates for solar cell materials (direct band gap~1.5 eV). Novel composition predictions for targeted applications are the future and our model is a step ahead in this direction.

Keywords

Machine learningPerovskitesRandom forest algorithmNature of band gapData set

References

[1]

Kim Y, Kim E, Antono E, et al. npj Comput Mater 2020;6: 131. https://doi.org/10.1038/s41524-020-00401-8.
Crossref
[2]

Brunin G, Ricci F, Ha VA, et al. npj Comput Mater 2019;5: 63. https://doi.org/10.1038/s41524-019-0200-5.
Crossref
[3]

Cole Jacqueline M. Acc Chem Res 2020;53(3): 599-610.
[4]

Sorkun MC, Astruc S, Koelman JMVA, et al. npj Comput Mater 2020;6: 106. https://doi.org/10.1038/s41524-020-00375-7.
Crossref
[5]

Lauri Himanen, Amber Geurts, Adam Stuart Foster, Patrick Rinke. Adv Sci 2019;6(21). https://doi.org/10.1002/advs.201900808.1900808.
Crossref
[6]

Mannodi-Kanakkithodi Arun, Maria K, Chan Y. Trends Chem 2021;3(2): 79-82. https://doi.org/10.1016/j.trechm.2020.12.007.
Crossref
[7]

Ludwig A. npj Comput Mater 2019;5: 70. https://doi.org/10.1038/s41524-019-0205-0.
Crossref
[8]

Juan Yongfei, Dai Yongbing, Yang Yang, Zhang Jiao. J Mater Sci Technol 2021;79: 178-90. https://doi.org/10.1016/j.jmst.2020.12.010.
Crossref
[9]

Schleder Gabriel R, Bruno Focassio, Fazzio Adalberto. Appl Phys Rev 2021;8: 31409.
[10]

Gordon GC. Peterson and jakoah brgoch. J. Phys. Energy 2021;3: 22002.
[11]

Im J, Lee S, Ko TW, et al. Identifying Pb-free perovskites for solar cells by machine learning. npj Comput Mater 2019;5: 37. https://doi.org/10.1038/s41524-019-0177-0.
Crossref
[12]

Zhou J, Huang B, Yan Z, et al. Emerging role of machine learning in lightmatter interaction. Light Sci Appl 2019;8: 84. https://doi.org/10.1038/s41377-019-0192-4.
Crossref
[13]

Borysov Stanislav, Geilhufe R, Balatsky A. PLoS One 2017;12: e0171501. https://doi.org/10.1371/journal.pone.0171501.
Crossref
[14]

Belle CE, Aksakalli V, Russo SP. J Chem Inf 2021;13: 42. https://doi.org/10.1186/s13321-021-00518-y.
Crossref
[15]

Feng Hong-Jian, Wu Kan, Deng Zun-Yi. Cell Rep Phy Sci 2020;1(9): 100179.
[16]

Chibani Siwar, Coudert François-Xavier. Apl Mater 2020;8: 80701.
[17]

Huang Y, Yu C, Chen W, Liu Y, et al. J Mater Chem C 2019;7(11): 3238-45. https://doi.org/10.1039/c8tc05554h.
Crossref
[18]

Ward L, Agrawal A, Choudhary A, et al. npj Comput Mater 2016;2: 16028. https://doi.org/10.1038/npjcompumats.2016.28.
Crossref
[19]
Lambrecht WRL. Rare Earth and Transition Metal Doping of Semiconductor Materials: Synthesis Magnetic properties and room temperature spintronics. Woodhead Publishing; 2016. p. 43-101. https://doi.org/10.1016/B978-0-08-100041-0.00002-0.
[20]

Liu Yue, Zhao Tianlu, Ju Wangwei, Shi Siqi. J Materiomics 2017;3(3): 159-77. https://doi.org/10.1016/j.jmat.2017.08.002.
Crossref
[21]

Chandrasekaran A, Kamal D, Batra R, et al. npj Comput Mater 2019;5: 22. https://doi.org/10.1038/s41524-019-0162-7.
Crossref
[22]

Rosen Andrew S, lyer Shaelyn M, Ray Debmalya, et al. Matter 2021;4(5): 1578-97. https://doi.org/10.1016/j.matt.2021.02.015.
Crossref
[23]

Oba Fumiyasu, Kumagai Yu. Appl Phys Express 2018;11: 60101.
[24]
Anantha Natarajan S, Varadhan R, Ezhilvel ME. Academia. edu, https://www.academia.edu/27697339/Band_Gap_Estimation_Using_Machine_Learning_Techniques.
[25]

Li F, Peng X, Wang Z, et al. Energy Environ. Mater. 2019;2: 280-91. https://doi.org/10.1002/eem2.12049.
Crossref
[26]

Eglitis Roberts, Popov Anatoli. J Saudi Chem Soc 2018;22: 459. https://doi.org/10.1016/j.jscs.2017.05.011.
Crossref
[27]

Liang Yunting, Shao Guosheng. RSC Adv 2019;9: 7551. https://doi.org/10.1039/C9RA00289H.
Crossref
[28]

Varignon J, Bibes M, Zunger A. Nat Commun 2019;10: 1658. https://doi.org/10.1038/s41467-019-09698-6.
Crossref
[29]

Emery A, Wolverton C. Sci Data 2017;4: 170153. https://doi.org/10.1038/sdata.2017.153.
Crossref
[30]

Emery Antoine A, Saal James E, Kirklin Scott, Hegde Vinay I, Wolverton Chris. Chem Mater 2016;28(16): 5621-34. https://doi.org/10.1021/acs.chemmater.6b01182.
Crossref
[31]

Meftahi N, Klymenko M, Christofferson AJ, et al. npj Comput Mater 2020;6: 166. https://doi.org/10.1038/s41524-020-00429-w.
Crossref
[32]
https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
[33]
https://scikit-learn.org/stable/.
[34]

Leevy Joffrey L, Khoshgoftaar Taghi M, Bauder Richard A. Naeem seliya. J Big Data 2018;5: 42. https://doi.org/10.1186/s40537-018-0151-6.
Crossref
[35]
https://materialsproject.org/.
[36]

Pilania G, Balachandran PV, Gubernatis JE, Lookman T. Acta Crystallogr 2015;B71: 507-13.
[37]

Tao Q, Xu P, Li M, et al. npj Comput Mater 2021;7: 23. https://doi.org/10.1038/s41524-021-00495-8.
Crossref
[38]

Emery A, Wolverton C. Sci Data 2017;4: 170153. https://doi.org/10.1038/sdata.2017.153.
Crossref
[39]
Perovskite, comprehensive composite materials. 2000. https://www.sciencedirect.com/topics/chemical-engineering/perovskite.
[40]

Al Mehedi Hasan Md, Nasser Mohammed. Biprodip pal, shamim ahmad. J Intell Learn Syst Appl 2014;6: 45-52. https://doi.org/10.4236/jilsa.2014.61005.
Crossref
[41]
Pal M. Int J Rem Sens 2005;26: 217-22. https://www.tandfonline.com/doi/abs/10.1080/01431160412331269698.
[42]

Hastie T, Tibshirani R, Friedman J. Sprin. Sci. Bus. Media 2009. https://link.springer.com/book/10.1007/978-0-387-84858-7.
[43]
Cohen Shay B. Eytan ruppin and gideon dror. IJCAI; 2005.
[44]

Shockley William, Hans J. Queisser. J Appl Phys 1961;32: 510-9.
[45]

Kohn Walter, Sham Lu Jeu. Phys Rev 1965;140(4A): A1133.
[46]

Kresse Georg, Hafner Jürgen. Phys Rev B 1994;49: 14251. 20.
[47]

Kresse Georg, Furthmüller Jürgen. Comput Mater Sci 1996;6(1): 15-50.
[48]

Perdew John P, Zunger Alex. Phys Rev B 1981;23(10): 5048.
[49]

Blöchl Peter E. Phys Rev B 1994;50(24): 17953.
[50]

Kresse Georg, Joubert Daniel. Phys Rev B 1999;59(3): 1758.
[51]

Perdew John P, Burke Kieron, Ernzerhof Matthias. Phys Rev Lett 1996;77(18): 3865.
[52]

Monkhorst Hendrik J, Pack James D. Phys Rev B 1976;13(12): 5188.
[53]

Nelson Cory, Monahan Nicholas, Zhu X-Y. Energy Environ Sci 2013;6:3508. https://doi.org/10.1039/c3ee42098a.
Crossref
[54]
Emery Antoine. 5329 perovskites. Figshare; 2017. https://doi.org/10.6084/m9.figshare.4833587.v1.Dataset.
[55]
Materials project. https://materialsproject.org/.
Journal of Materiomics
Volume 8 Issue 5,
September 2022
Pages 937-948
DOI: 10.1016/j.jmat.2022.04.006
Cite this article:
G SP, Mattur MN, Nagappan N, et al. Prediction of nature of band gap of perovskite oxides (ABO3) using a machine learning approach. Journal of Materiomics, 2022, 8(5): 937-948. https://doi.org/10.1016/j.jmat.2022.04.006

539

Views

25

Crossref

29

Web of Science

33

Scopus

Altmetrics
Received: 11 March 2022
Revised: 18 April 2022
Accepted: 19 April 2022
Published: 27 April 2022
© 2022 The Chinese Ceramic Society.

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Return