Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides

Mannodi-Kanakkithodi, Arun; Toriyama, Michael Y.; Sen, Fatih G.; Davis, Michael J.; Klie, Robert F.; Chan, Maria K. Y.

doi:10.1038/s41524-020-0296-7

Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides

Journal Article · Thu Apr 23 00:00:00 EDT 2020 · npj Computational Materials

DOI:https://doi.org/10.1038/s41524-020-0296-7· OSTI ID:1632326

^[1]; Toriyama, Michael Y. ^[1]; Sen, Fatih G. ^[1]; Davis, Michael J. ^[2]; Klie, Robert F. ^[3]; Chan, Maria K. Y. ^[1]

Argonne National Lab. (ANL), Argonne, IL (United States). Center for Nanoscale Materials
Argonne National Lab. (ANL), Argonne, IL (United States)
Univ. of Illinois, Chicago, IL (United States)

The ability to predict the likelihood of impurity incorporation and their electronic energy levels in semiconductors is crucial for controlling its conductivity, and thus the semiconductor's performance in solar cells, photodiodes, and optoelectronics. The difficulty and expense of experimental and computational determination of impurity levels makes a data-driven machine learning approach appropriate. In this work, we show that a density functional theory-generated dataset of impurities in Cd-based chalcogenides CdTe, CdSe, and CdS can lead to accurate and generalizable predictive models of defect properties. By converting any semiconductor + impurity system into a set of numerical descriptors, regression models are developed for the impurity formation enthalpy and charge transition levels. These regression models can subsequently predict impurity properties in mixed anion CdX compounds (where X is a combination of Te, Se and S) fairly accurately, proving that although trained only on the end points, they are applicable to intermediate compositions. We make machine-learned predictions of the Fermi-level-dependent formation energies of hundreds of possible impurities in 5 chalcogenide compounds, and we suggest a list of impurities which can shift the equilibrium Fermi level in the semiconductor as determined by the dominant intrinsic defects. Machine learning predictions for the dominating impurities compare well with DFT predictions, revealing the power of machine-learned models in the quick screening of impurities likely to affect the optoelectronic behavior of semiconductors.

View Accepted Manuscript (DOE)

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office; USDOE Office of Science (SC), Basic Energy Sciences (BES). Chemical Sciences, Geosciences & Biosciences Division; USDOE Office of Science (SC), Workforce Development for Teachers and Scientists (WDTS)

Grant/Contract Number:: AC02-05CH11231; AC02-06CH11357

OSTI ID:: 1632326

Journal Information:: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 6; ISSN 2057-3960

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

References (71)

Introduction to the LASSO: A Convex Optimization Approach for High-dimensional Problems Gauraha, Niharika Resonance, Vol. 23, Issue 4 https://doi.org/10.1007/s12045-018-0635-x	journal	April 2018
Kinetic Simulations of Cu Doping in Chlorinated CdSeTe PV Absorbers Sankin, Igor; Krasikov, Dmitry physica status solidi (a), Vol. 216, Issue 15 https://doi.org/10.1002/pssa.201800887	journal	February 2019
Understanding kernel ridge regression: Common behaviors from simple functions to density functionals Vu, Kevin; Snyder, John C.; Li, Li International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24939	journal	May 2015
The Nature of Statistical Learning Theory Vapnik, Vladimir N. https://doi.org/10.1007/978-1-4757-2440-0	book	January 1995
The Nature of Statistical Learning Theory Vapnik, Vladimir N. Springer New York, NY https://doi.org/10.1007/978-1-4757-3264-1	book	January 2000
Properties of the oxygen vacancy in ZnO Hofmann, D. M.; Pfisterer, D.; Sann, J. Applied Physics A, Vol. 88, Issue 1 https://doi.org/10.1007/s00339-007-3956-2	journal	April 2007
Application of Lithium Chloride Dopant in Fabrication of CdTe Solar Cells Xu, Hang; Zeng, Guanggen; Feng, Lianghuan Journal of Electronic Materials, Vol. 46, Issue 2 https://doi.org/10.1007/s11664-016-5127-8	journal	November 2016
Characterization of deep levels in CdTe by photo-EPR and related techniques Jantsch, W.; Hendorfer, G. Journal of Crystal Growth, Vol. 101, Issue 1-4 https://doi.org/10.1016/0022-0248(90)91004-A	journal	April 1990
CdTe solar cells with efficiencies over 15% Ferekides, C.; Britt, J. Solar Energy Materials and Solar Cells, Vol. 35 https://doi.org/10.1016/0927-0248(94)90148-1	journal	September 1994
Scoping the polymer genome: A roadmap for rational polymer dielectrics design and beyond Mannodi-Kanakkithodi, Arun; Chandrasekaran, Anand; Kim, Chiho Materials Today, Vol. 21, Issue 7 https://doi.org/10.1016/j.mattod.2017.11.021	journal	September 2018
High-efficiency polycrystalline CdTe thin-film solar cells Wu, Xuanzhi Solar Energy, Vol. 77, Issue 6 https://doi.org/10.1016/j.solener.2004.06.006	journal	December 2004
Co-sublimation of CdSexTe1−x layers for CdTe solar cells Swanson, Drew E.; Sites, James R.; Sampath, Walajabad S. Solar Energy Materials and Solar Cells, Vol. 159 https://doi.org/10.1016/j.solmat.2016.09.025	journal	January 2017
Photoreflectance studies of optical transitions in GaNPAs intermediate band solar cell absorbers Zelazna, K.; Kudrawiec, R.; Luce, A. Solar Energy Materials and Solar Cells, Vol. 188 https://doi.org/10.1016/j.solmat.2018.08.024	journal	December 2018
Phosphorus implanted cadmium telluride solar cells Kraft, C.; Brömel, A.; Schönherr, S. Thin Solid Films, Vol. 519, Issue 21 https://doi.org/10.1016/j.tsf.2011.01.389	journal	August 2011
First-principles-based analysis of the influence of Cu on CdTe electronic properties Krasikov, D.; Knizhnik, A.; Potapkin, B. Thin Solid Films, Vol. 535 https://doi.org/10.1016/j.tsf.2012.10.027	journal	May 2013
From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown Kim, Chiho; Pilania, Ghanshyam; Ramprasad, Ramamurthy Chemistry of Materials, Vol. 28, Issue 5 https://doi.org/10.1021/acs.chemmater.5b04109	journal	February 2016
High-Throughput Machine-Learning-Driven Synthesis of Full-Heusler Compounds Oliynyk, Anton O.; Antono, Erin; Sparks, Taylor D. Chemistry of Materials, Vol. 28, Issue 20 https://doi.org/10.1021/acs.chemmater.6b02724	journal	October 2016
Searching for “Defect-Tolerant” Photovoltaic Materials: Combined Theoretical and Experimental Screening Brandt, Riley E.; Poindexter, Jeremy R.; Gorai, Prashun Chemistry of Materials, Vol. 29, Issue 11 https://doi.org/10.1021/acs.chemmater.6b05496	journal	May 2017
Comprehensive Computational Study of Partial Lead Substitution in Methylammonium Lead Bromide Mannodi-Kanakkithodi, Arun; Park, Ji-Sang; Jeon, Nari Chemistry of Materials, Vol. 31, Issue 10 https://doi.org/10.1021/acs.chemmater.8b04017	journal	March 2019
Descriptor-Based Approach for the Prediction of Cation Vacancy Formation Energies and Transition Levels Varley, Joel B.; Samanta, Amit; Lordi, Vincenzo The Journal of Physical Chemistry Letters, Vol. 8, Issue 20 https://doi.org/10.1021/acs.jpclett.7b02333	journal	October 2017
Learning-in-Templates Enables Accelerated Discovery and Synthesis of New Stable Double Perovskites Askerka, Mikhail; Li, Ziliang; Lempen, Mathieu Journal of the American Chemical Society, Vol. 141, Issue 8 https://doi.org/10.1021/jacs.8b13420	journal	January 2019
CdSeS Nanowires: Compositionally Controlled Band Gap and Exciton Dynamics Kim, Jong-Pil; Christians, Jeffrey A.; Choi, Hyunbong The Journal of Physical Chemistry Letters, Vol. 5, Issue 7 https://doi.org/10.1021/jz500280g	journal	March 2014
Accelerated search for materials with targeted properties by adaptive design Xue, Dezhen; Balachandran, Prasanna V.; Hogden, John Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms11241	journal	April 2016
Understanding intermediate-band solar cells Luque, Antonio; Martí, Antonio; Stanley, Colin Nature Photonics, Vol. 6, Issue 3 https://doi.org/10.1038/nphoton.2012.1	journal	February 2012
Machine learning in materials informatics: recent applications and prospects Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam npj Computational Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s41524-017-0056-5	journal	December 2017
Understanding the role of selenium in defect passivation for highly efficient selenium-alloyed cadmium telluride solar cells Fiducia, Thomas A. M.; Mendis, Budhika G.; Li, Kexue Nature Energy, Vol. 4, Issue 6 https://doi.org/10.1038/s41560-019-0389-z	journal	May 2019
Point defect engineering in thin-film solar cells Park, Ji Sang; Kim, Sunghyun; Xie, Zijuan Nature Reviews Materials, Vol. 3, Issue 7 https://doi.org/10.1038/s41578-018-0026-7	journal	June 2018
Self-compensation in arsenic doping of CdTe Ablekim, Tursun; Swain, Santosh K.; Yin, Wan-Jian Scientific Reports, Vol. 7, Issue 1 https://doi.org/10.1038/s41598-017-04719-0	journal	July 2017
GaN intermediate band solar cells with Mn-doped absorption layer Lee, Ming-Lun; Huang, Feng-Wen; Chen, Po-Cheng Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-27005-z	journal	June 2018
Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution Tran, Kevin; Ulissi, Zachary W. Nature Catalysis, Vol. 1, Issue 9 https://doi.org/10.1038/s41929-018-0142-1	journal	September 2018
Machine Learning Strategy for Accelerated Design of Polymer Dielectrics Mannodi-Kanakkithodi, Arun; Pilania, Ghanshyam; Huan, Tran Doan Scientific Reports, Vol. 6, Issue 1 https://doi.org/10.1038/srep20952	journal	February 2016
Deep level trapped defect analysis in CH ₃ NH ₃ PbI ₃ perovskite solar cells by deep level transient spectroscopy Heo, Sung; Seo, Gabseok; Lee, Yonghui Energy & Environmental Science, Vol. 10, Issue 5 https://doi.org/10.1039/C7EE00303J	journal	January 2017
Detailed Balance Limit of Efficiency of p‐n Junction Solar Cells Shockley, William; Queisser, Hans J. Journal of Applied Physics, Vol. 32, Issue 3, p. 510-519 https://doi.org/10.1063/1.1736034	journal	March 1961
Energy band gaps and lattice parameters evaluated with the Heyd-Scuseria-Ernzerhof screened hybrid functional Heyd, Jochen; Peralta, Juan E.; Scuseria, Gustavo E. The Journal of Chemical Physics, Vol. 123, Issue 17 https://doi.org/10.1063/1.2085170	journal	November 2005
Photoluminescence of CdTe doped with arsenic and antimony acceptors Soltani, M.; Certier, M.; Evrard, R. Journal of Applied Physics, Vol. 78, Issue 9 https://doi.org/10.1063/1.359686	journal	November 1995
Cathodoluminescence image of defects and luminescence centers in ZnS/GaAs(100) Mitsui, Tadashi; Yamamoto, Naoki; Tadokoro, Toyoyasu Journal of Applied Physics, Vol. 80, Issue 12 https://doi.org/10.1063/1.363770	journal	December 1996
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy APL Materials, Vol. 1, Issue 1 https://doi.org/10.1063/1.4812323	journal	July 2013
Magnetoresistance in p-type cadmium telluride doped with sodium Ahmad, Faisal R. Applied Physics Letters, Vol. 106, Issue 1 https://doi.org/10.1063/1.4905657	journal	January 2015
Unipolar self-doping behavior in perovskite CH ₃ NH ₃ PbBr ₃ Shi, Tingting; Yin, Wan-Jian; Hong, Feng Applied Physics Letters, Vol. 106, Issue 10 https://doi.org/10.1063/1.4914544	journal	March 2015
Tutorial: Defects in semiconductors—Combining experiment and theory Alkauskas, Audrius; McCluskey, Matthew D.; Van de Walle, Chris G. Journal of Applied Physics, Vol. 119, Issue 18 https://doi.org/10.1063/1.4948245	journal	May 2016
Laplace current deep level transient spectroscopy measurements of defect states in methylammonium lead bromide single crystals Rosenberg, John W.; Legodi, Matshisa J.; Rakita, Yevgeny Journal of Applied Physics, Vol. 122, Issue 14 https://doi.org/10.1063/1.4995970	journal	October 2017
Structural and electronic properties of CdTe _1-x Se _x films and their application in solar cells Lingg, Martina; Spescha, Annina; Haass, Stefan G. Science and Technology of Advanced Materials, Vol. 19, Issue 1 https://doi.org/10.1080/14686996.2018.1497403	journal	August 2018
High resistivity in undoped CdTe: carrier compensation of Te antisites and Cd vacancies Lindström, A.; Mirbt, S.; Sanyal, B. Journal of Physics D: Applied Physics, Vol. 49, Issue 3 https://doi.org/10.1088/0022-3727/49/3/035101	journal	December 2015
The GW method Aryasetiawan, F.; Gunnarsson, O. Reports on Progress in Physics, Vol. 61, Issue 3 https://doi.org/10.1088/0034-4885/61/3/002	journal	March 1998
Deformation-induced defect levels in ZnSe crystals Fernández, P.; Piqueras, J.; Urbieta, A. Semiconductor Science and Technology, Vol. 14, Issue 5 https://doi.org/10.1088/0268-1242/14/5/010	journal	January 1999
Review on first-principles study of defect properties of CdTe as a solar cell absorber Yang, Ji-Hui; Yin, Wan-Jian; Park, Ji-Sang Semiconductor Science and Technology, Vol. 31, Issue 8 https://doi.org/10.1088/0268-1242/31/8/083002	journal	July 2016
Cathodoluminescence of defects in diamond films and particles grown by hot-filament chemical-vapor deposition Robins, L. H.; Cook, L. P.; Farabaugh, E. N. Physical Review B, Vol. 39, Issue 18 https://doi.org/10.1103/PhysRevB.39.13367	journal	June 1989
Native defects in CdTe Berding, M. A. Physical Review B, Vol. 60, Issue 12 https://doi.org/10.1103/PhysRevB.60.8943	journal	September 1999
Structure stability and carrier localization in Cd X ( X = S , S e , Te ) semiconductors Wei, Su-Huai; Zhang, S. B. Physical Review B, Vol. 62, Issue 11 https://doi.org/10.1103/PhysRevB.62.6944	journal	September 2000
Energy levels of isolated interstitial hydrogen in silicon Herring, Conyers; Johnson, N. M.; Van de Walle, Chris G. Physical Review B, Vol. 64, Issue 12 https://doi.org/10.1103/PhysRevB.64.125209	journal	September 2001
Ab initio electronic structure calculations for metallic intermediate band formation in photovoltaic materials Wahnón, P.; Tablero, C. Physical Review B, Vol. 65, Issue 16 https://doi.org/10.1103/PhysRevB.65.165115	journal	April 2002
Intrinsic stoichiometry and oxygen-induced p -type conductivity of pyrite FeS 2 Sun, Ruoshi; Chan, M. K. Y.; Kang, ShinYoung Physical Review B, Vol. 84, Issue 3 https://doi.org/10.1103/PhysRevB.84.035212	journal	July 2011
Spin-orbit coupling effects on predicting defect properties with hybrid functionals: A case study in CdTe Pan, Jie; Metzger, Wyatt K.; Lany, Stephan Physical Review B, Vol. 98, Issue 5 https://doi.org/10.1103/PhysRevB.98.054108	journal	August 2018
Defect Energy Levels in Density Functional Calculations: Alignment and Band Gap Problem Alkauskas, Audrius; Broqvist, Peter; Pasquarello, Alfredo Physical Review Letters, Vol. 101, Issue 4 https://doi.org/10.1103/PhysRevLett.101.046405	journal	July 2008
Fully Ab Initio Finite-Size Corrections for Charged-Defect Supercell Calculations Freysoldt, Christoph; Neugebauer, Jörg; Van de Walle, Chris G. Physical Review Letters, Vol. 102, Issue 1 https://doi.org/10.1103/PhysRevLett.102.016402	journal	January 2009
Efficient Band Gap Prediction for Solids Chan, M. K. Y.; Ceder, G. Physical Review Letters, Vol. 105, Issue 19 https://doi.org/10.1103/PhysRevLett.105.196403	journal	November 2010
Residual Native Shallow Donor in ZnO Look, D. C.; Hemsky, J. W.; Sizelove, J. R. Physical Review Letters, Vol. 82, Issue 12 https://doi.org/10.1103/PhysRevLett.82.2552	journal	March 1999
Theory of Defect Levels and the “Band Gap Problem” in Silicon Schultz, Peter A. Physical Review Letters, Vol. 96, Issue 24 https://doi.org/10.1103/PhysRevLett.96.246401	journal	June 2006
Production of Photocurrent due to Intermediate-to-Conduction-Band Transitions: A Demonstration of a Key Operating Principle of the Intermediate-Band Solar Cell Martí, A.; Antolín, E.; Stanley, C. R. Physical Review Letters, Vol. 97, Issue 24 https://doi.org/10.1103/PhysRevLett.97.247701	journal	December 2006
Autonomous efficient experiment design for materials discovery with Bayesian model averaging Talapatra, Anjana; Boluki, S.; Duong, T. Physical Review Materials, Vol. 2, Issue 11 https://doi.org/10.1103/PhysRevMaterials.2.113803	journal	November 2018
First-principles calculations for point defects in solids Freysoldt, Christoph; Grabowski, Blazej; Hickel, Tilmann Reviews of Modern Physics, Vol. 86, Issue 1 https://doi.org/10.1103/RevModPhys.86.253	journal	March 2014
Annealing effects on defect levels of CdTe:Cl materials and the uniformity of the electrical properties Ayoub, M.; Hage-Ali, M.; Koebel, J. M. IEEE Transactions on Nuclear Science, Vol. 50, Issue 2 https://doi.org/10.1109/TNS.2003.809981	journal	April 2003
The Nature Of Statistical Learning Theory~ Cherkassky, V. IEEE Transactions on Neural Networks, Vol. 8, Issue 6 https://doi.org/10.1109/tnn.1997.641482	journal	November 1997
Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning Zahrt, Andrew F.; Henle, Jeremy J.; Rose, Brennan T. Science, Vol. 363, Issue 6424 https://doi.org/10.1126/science.aau5631	journal	January 2019
Deep Defect Levels in Plastically Deformed GaAs Suezawa, Masashi; Sumino, Koji Japanese Journal of Applied Physics, Vol. 25, Issue Part 1, No. 4 https://doi.org/10.1143/JJAP.25.533	journal	April 1986
Random forest versus logistic regression: a large-scale benchmark experiment Couronné, Raphael; Probst, Philipp; Boulesteix, Anne-Laure BMC Bioinformatics, Vol. 19, Issue 1 https://doi.org/10.1186/s12859-018-2264-5	journal	July 2018
Predicted Theoretical Efficiency for New Intermediate Band Solar Cells (IBSC) Based on GaAs1-xNx Boumesjed, A.; Mazari, H.; Ameur, K. Journal of New Technology and Materials, Vol. 8, Issue 1 https://doi.org/10.12816/0048938	journal	January 2018
High-Throughput Machine-Learning-Driven Synthesis of Full-Heusler Compounds Oliynyk, Ao; Antono, E.; Sparks, Td Apollo - University of Cambridge Repository https://doi.org/10.17863/cam.9378	text	January 2016
Defect Energy Levels in Density Functional Calculations: Alignment and Band Gap Problem Alkauskas, Audrius; Broqvist, Peter; Pasquarello, Alfredo arXiv https://doi.org/10.48550/arxiv.0807.4647	text	January 2008
Autonomous Efficient Experiment Design for Materials Discovery with Bayesian Model Averaging Talapatra, Anjana; Boluki, Shahin; Duong, Thien arXiv https://doi.org/10.48550/arxiv.1803.05460	text	January 2018
Random forest versus logistic regression: a large-scale benchmark experiment Couronné, Raphael; Probst, Philipp; Boulesteix, Anne-Laure Universitätsbibliothek der Ludwig-Maximilians-Universität München https://doi.org/10.5282/ubm/epub.39955	text	January 2017

Similar Records

Machine learning defect properties in Cd-based chalcogenides

Conference · Wed Feb 05 23:00:00 EST 2020 · OSTI ID:1872402

Accelerated screening of functional atomic impurities in halide perovskites using high-throughput computations and machine learning

Journal Article · Thu Mar 03 19:00:00 EST 2022 · Journal of Materials Science · OSTI ID:1898519

Universal machine learning framework for defect predictions in zinc blende semiconductors

Journal Article · Sun Feb 13 19:00:00 EST 2022 · Patterns · OSTI ID:1846304

Related Subjects

36 MATERIALS SCIENCE

Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides

Citation Formats

References (71)

Similar Records

Related Subjects