journal article·2023-07

Bandgap energy prediction of senary zincblende III–V semiconductor compounds using machine learning

Mohammed Alsalman, Saad M. Alqahtani, Fahhad H. Alharbi

Publisher page

Abstract

Two complimentary machine learning (ML) models are developed to estimate the bandgap energy ( E g ) of senary zincblende (ZB) III–V semiconductor compounds Al x 1 Ga x 2 In x 3 P y 1 As y 2 Sb y 3 from molar fractions. The models work – as well – for any compound with smaller number of constituent elements from binaries to quinaries. Some of these compounds exhibit transition between a direct and an indirect E g as a function of composition. This is due to the fact that the bandgap for this class of materials is either the direct gap at Γ point ( E g Γ ) or the indirect one between the maximum valance band at Γ point and the minimum conduction band around X point ( E g X ). Hence, to capture precisely the E g and its state, the ML models estimate separately the E g Γ and E g X where the lowest energy gap is the effective E g . For model training, 18 ternary ZB III–V semiconductor compounds are used, which contain all possible ternary configurations of III-type cations (Al, Ga, In) and V-type anions (P, As, Sb). The achieved testing accuracy using cubic regression with ridge regularization – in terms of root mean square error (RMSE) – are 7.583 and 0.021 meV for E g Γ and E g X , respectively. These correspond to R 2 of 0.99995 and 1.00000 (8 nines), respectively. To validate the models, they are benchmarked against experimental measurements of four different quaternary ZB III–V semiconductor compounds. The agreement is very noticeable demonstrating the validity and the excellent accuracy of the developed models.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Materials Science · Semiconductor materials and interfaces · Nuclear Materials and Properties

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

References (45)

Show source-provided references
1. Efficient band gap prediction for solids10.1103/PhysRevLett.105.196403 ↗
2. Resolution of the band gap prediction problem for materials design10.1021/acs.jpclett.5b02870 ↗
3. Solar cell materials by design: Hybrid pyroxene corner-sharing VO4 tetrahedral chains10.1002/cssc.201700121 ↗
4. Status and challenges of density functional theory10.1016/j.trechm.2020.02.005 ↗
5. Localization and delocalization errors in density functional theory and implications for band-gap prediction10.1103/PhysRevLett.100.146401 ↗
6. Fractional charge perspective on the band gap in density-functional theory10.1103/PhysRevB.77.115123 ↗
7. Improving band gap prediction in density functional theory from molecules to solids10.1103/PhysRevLett.107.026403 ↗
8. Reproducibility in G0W0 calculations for solids10.1016/j.cpc.2020.107242 ↗
9. Automation methodologies and large-scale validation for GW: Towards high-throughput GW calculations10.1103/PhysRevB.96.155207 ↗
10. Importance of the kinetic energy density for band gap calculations in solids with density functional theory10.1021/acs.jpca.7b02882 ↗
11. Atomistic simulation of realistically sized nanodevices using NEMO 3-D—Part I: Models and benchmarks10.1109/TED.2007.902879 ↗
12. Atomistic simulation of realistically sized nanodevices using NEMO 3-D—Part II: Applications10.1109/TED.2007.904877 ↗
13. NEMO5: A parallel multiscale nanoelectronics modeling tool10.1109/TNANO.2011.2166164 ↗
14. Si tight-binding parameters from genetic algorithm fitting10.1006/spmi.1999.0797 ↗
15. A semi-empirical tight-binding theory of the electronic structure of semiconductors10.1016/0022-3697(83)90064-1 ↗
16. Sp3s* Tight-binding parameters for transport simulations in compound semiconductors10.1006/spmi.2000.0862 ↗
17. Commentary: The materials project: A materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
18. AFLOW: An automatic framework for high-throughput materials discovery10.1016/j.commatsci.2012.02.005 ↗
19. MaterialsAtlas. org: a materials informatics web app platform for materials discovery and survey of state-of-the-art10.1038/s41524-022-00750-6 ↗
20. Development of materials informatics platform10.2494/photopolymer.34.41 ↗
21. Resampling techniques for materials informatics: Limitations in crystal point groups classification10.1021/acs.jcim.2c00666 ↗
22. Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science10.1063/1.4946894 ↗
23. Machine learning in materials science: From explainable predictions to autonomous design10.1016/j.commatsci.2021.110360 ↗
24. Extending Shannon’s ionic radii database using machine learning
25. Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques10.1103/PhysRevB.93.115104 ↗
26. Machine learning the hubbard u parameter in DFT+U using Bayesian optimization10.1038/s41524-020-00446-9 ↗
27. Predicting the band gaps of inorganic solids by machine learning10.1021/acs.jpclett.8b00124 ↗
28. Adachi · 2009
29. Electron effective mass and band-gap dependence on alloy composition of AlyGaxIn1−y−xAs, lattice matched to InP10.1063/1.107005 ↗
30. Photoreflectance characterization of InAlGaAs molecular beam epitaxy layers and quantum wells10.1016/0040-6090(91)90214-I ↗
31. Electroreflectance study of (AlxGa1-x)0.5In0.5P alloys10.1143/JJAP.35.537 ↗
32. Electroreflectance study of AlxGa1−xInyP alloy10.1016/0038-1098(89)90462-6 ↗
33. Metalorganic vapour phase epitaxy growth of InPAsSb alloys lattice matched to inas10.1016/0022-0248(94)90050-7 ↗
34. Composition dependence of the band gaps of In1−xGaxAs1−yPy quaternary solids lattice matched on InP substrates10.1063/1.324562 ↗
35. Electroreflectance investigation of In1−xGaxAsyp1−y lattice-matched to InP10.1016/0038-1098(80)90924-2 ↗
36. Energy band structure of In1−xGaxAsyp1−y lattice matched to InP by means of the line profile analysis of the electroreflectance spectra10.1002/pssb.2221300227 ↗
37. Van Rossum · 2009
38. Jupyter notebooks – a publishing format for reproducible computational workflows
39. Raybaut · 2009
40. 2020
41. Scikit-learn: Machine learning in Python
42. Array programming with NumPy10.1038/s41586-020-2649-2 ↗
43. Data structures for statistical computing in python10.25080/Majora-92bf1922-00a ↗
44. Structural and spectral features of MOCVD AlxGayIn1−x−yAszP1−z/GaAs (100) alloys10.1134/S106378261206019X ↗
45. Interpolating semiconductor alloy parameters: Application to quaternary III–V band gaps10.1063/1.1613371 ↗