Exploration of Deep Learning Models for Accelerated Defect Property Predictions and Device Design of Cubic Semiconductor Crystals
Source abstract
Abstract
In this work, we present an exploration of deep learning models for predicting defect properties in cubic phase semiconductors. The nature of impurity energy levels strongly influences the performance of semiconductors in a wide range of applications, such as solar cells, field effect transistors, and qubits for quantum computing. In this work, we employ two types of deep learning models, a crystal defect graph neural network and a chemical environment-encoded artificial neural network, to predict defect properties. The models are trained on a data set of charge-dependent defect formation energies obtained from density functional theory computations and descriptors based on elemental properties, defect local environment, and relevant semiconductor properties. We assess the models’ performance and showcase their capability in optimizing semiconductor devices, particularly when used in tandem with compositionally constrained thermodynamics and technology computer-aided design models.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Electron and X-Ray Spectroscopy Techniques · Electronic and Structural Properties of Oxides
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Molecular Engineering & Sciences Institute, University of Washington, Seattle, Washington 98195, United States
Department of Physics, University of Washington, Seattle, Washington 98195, United States
Department of Electrical and Computer Engineering, University of Washington, Seattle, Washington 98195, United States
Funding
Solar Energy Technologies Office · Division of Materials Research
References (44)
Show source-provided references
1. 10.1063/1.501747510.1063/1.5017475 ↗
2. Xiang, X.; Sommer, D. E.; Gehrke, A.; Dunham, S. T. Coupled process and device modeling of Cu (In, Ga) Se 2 solar cells. 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC), 2021; pp 1707–1711.10.1109/PVSC43889.2021.9519020 ↗
3. 10.1088/0965-0393/17/8/08400210.1088/0965-0393/17/8/084002 ↗
4. 10.1103/PhysRevLett.120.14530110.1103/PhysRevLett.120.145301 ↗
5. 10.1103/PhysRevMaterials.4.06380110.1103/PhysRevMaterials.4.063801 ↗
6. 10.1038/s41524-021-00650-110.1038/s41524-021-00650-1 ↗
7. 10.1021/acs.chemmater.9b0129410.1021/acs.chemmater.9b01294 ↗
8. 10.1063/5.013538210.1063/5.0135382 ↗
9. 10.1038/s43588-023-00495-210.1038/s43588-023-00495-2 ↗
10. 10.1088/0268-1242/31/8/08300210.1088/0268-1242/31/8/083002 ↗
11. 10.1038/s41524-023-00973-110.1038/s41524-023-00973-1 ↗
12. 10.1016/j.patter.2022.10045010.1016/j.patter.2022.100450 ↗
13. 10.1103/RevModPhys.86.25310.1103/RevModPhys.86.253 ↗
14. 10.1103/PhysRevB.87.18411510.1103/PhysRevB.87.184115 ↗
15. Synopsys Inc. Sentaurus Device User Guide Version K-2023.12; Synopsys, Inc.: Mountain View, CA, 2023.
16. 10.1016/j.cpc.2019.10694910.1016/j.cpc.2019.106949 ↗
17. 10.1063/5.008387710.1063/5.0083877 ↗
18. 10.1109/JPHOTOV.2015.243001510.1109/JPHOTOV.2015.2430015 ↗
19. 10.1063/1.10962910.1063/1.109629 ↗
20. Reich, C. Investigations to Improve CdTe-Based Solar Cell Open Circuit Voltage and Efficiency Using a Passivation and Selectivity Theoretical Framework, Ph.D. Thesis, Colorado State University, 2022.
21. 10.1016/j.tsf.2012.10.02710.1016/j.tsf.2012.10.027 ↗
22. 10.1103/PhysRevB.90.24520210.1103/PhysRevB.90.245202 ↗
23. 10.1021/acsenergylett.1c0038010.1021/acsenergylett.1c00380 ↗
24. 10.1038/srep2171210.1038/srep21712 ↗
25. 10.1063/1.494252910.1063/1.4942529 ↗
26. 10.48550/arXiv.2404.0779610.48550/arXiv.2404.07796 ↗
27. 10.1103/PhysRevB.90.07520210.1103/PhysRevB.90.075202 ↗
28. 10.1016/j.cpc.2021.10805610.1016/j.cpc.2021.108056 ↗
29. 10.1063/1.482848410.1063/1.4828484 ↗
30. 10.1103/RevModPhys.61.28910.1103/RevModPhys.61.289 ↗
31. 10.1109/jphotov.2024.336665210.1109/jphotov.2024.3366652 ↗
32. 10.1007/s11664-016-4786-910.1007/s11664-016-4786-9 ↗
33. Palekis, V.; Wang, W.; Elahi, S. T.; Zahangir Alom, M.; Ferekides, C. Thin Film Solar Cells with n-type CdTe Absorber and p-type ZnTe Window Layers. 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC), 2021; pp 1293–1297.10.1109/PVSC43889.2021.9518840 ↗
34. 10.1109/JPHOTOV.2019.290235610.1109/JPHOTOV.2019.2902356 ↗
35. 10.1038/nenergy.2016.6710.1038/nenergy.2016.67 ↗
36. 10.1063/1.36116010.1063/1.361160 ↗
37. 10.1063/5.000488310.1063/5.0004883 ↗
38. 10.1063/1.499901110.1063/1.4999011 ↗
39. 10.1038/s41598-017-04719-010.1038/s41598-017-04719-0 ↗
40. 10.1109/JPHOTOV.2017.273086510.1109/JPHOTOV.2017.2730865 ↗
41. 10.1016/j.nanoen.2020.10483510.1016/j.nanoen.2020.104835 ↗
42. 10.1063/1.33939510.1063/1.339395 ↗
43. 10.1016/j.actamat.2015.09.03510.1016/j.actamat.2015.09.035 ↗
44. Xiang, X.; Gehrke, A.; Dunham, S. Understanding the Dopability of As in Selenium-Alloyed Cadmium Telluride Solar Cells. 2023 IEEE 50th Photovoltaic Specialists Conference (PVSC), 2023; pp 1–3.10.1109/PVSC48320.2023.10359554 ↗