Machine Learning Prediction of Optical Absorption in GaAs 2D Nanostructure under Hydrostatic Pressure

Abstract:

This work focuses on the modeling and prediction of the optical absorption coefficient in GaAs 2D nanostructure subjected to hydrostatic pressure. The database is generated from numerical calculations describing the optical absorption of exciton confined in GaAs 2D nanostructure. The obtained data are exploited to develop predictive models based on machine learning such as Decision Tree and Gradient Boosting techniques, in order to establish an accurate relationship between the incident photon energies and the optical absorption coefficient. The quality of the proposed approaches is examined using standard statistical metrics, considering the mean absolute, squared errors, and root mean squared error, as well as the coefficient of determination. The obtained results demonstrate an excellent agreement between the predicted and numerical values, with very low errors and strong generalization capability. these approaches therefore represent an efficient alternative to conventional numerical methods for the rapid prediction of the optical properties of discoidal quantum dots and offers promising perspectives for the optimization of optoelectronic devices.

• Periodical: Materials Science Forum (Volume 1199)
• Pages: 3-14
• DOI: https://doi.org/10.4028/p-TvR5GH
• Online since: August 2026
• Authors: I. Lamrini*, M. Hbibi, S. Chouef, M. El Hadi, R. Boussetta, O. Mommadi, A. El Moussaouy, K. Laabidi, C.A. Duque
• Keywords: Decision Tree, Discoidal Quantum Dots, Gradient Boosting, Hydrostatic Pressure, Machine Learning Prediction, Optical Absorption Coefficient

References

[1] T. F. Kuech, III-V compound semiconductors: Growth and structures. Progress in crystal growth and characterization of materials, 62, 352-370 (2016).

DOI: 10.1016/j.pcrysgrow.2016.04.019

[2] M. Hbibi et al., Optoelectronic properties of GaN and GaAs cylindrical nanostructures: Tuning excitonic Q-LED across the UV, visible, and IR domains. J. Appl. Phys. 138, 054301 (2025).

DOI: 10.1063/5.0275425

[3] M. Hbibi et al., Impact of size on the efficiency of intermediate band solar cells based on toroidal quantum rings. Physica B 417674 (2025).

DOI: 10.1016/j.physb.2025.417674

[4] M. Hbibi, S. Chouef, R. Boussetta, A. El Moussaouy, O. Mommadi, C.A. Duque, Optical absorption and photovoltaic performance in InN/InGaN multilayer quantum dots: Effects of confinement and built-in electric field. Solar Energy 298, 113620 (2025).

DOI: 10.1016/j.solener.2025.113620

[5] J.S. Blakemore, Semiconducting and other major properties of gallium arsenide. J. Appl. Phys. 53, R123-R181 (1982).

DOI: 10.1063/1.331665

[6] F. Rol, Optical study of non-polar GaN/AlN single quantum dots. PhD thesis, Univ. Joseph-Fourier - Grenoble I (2007).

[7] S.J. Cheng, W. Sheng, P. Hawrylak, Theory of excitonic artificial atoms: InGaAs/GaAs quantum dots in strong magnetic fields. Phys. Rev. B 68, 235330 (2003).

DOI: 10.1103/physrevb.68.235330

[8] J. Yoon et al., GaAs photovoltaics and optoelectronics using releasable multilayer epitaxial assemblies. Nature 465, 329-333 (2010).

DOI: 10.1038/nature09054

[9] M. Hbibi et al., Hydrostatic pressure and temperature effects on linear and nonlinear optical properties in 2D ultra-thin quantum dot. Lecture Notes in Electrical Engineering, 945, 251-261 (2023).

DOI: 10.1007/978-981-19-6223-3_28

[10] M. Hbibi et al., Theoretical study of optoelectronic properties of GaAs/AlAs quantum disks: Role of correlated and uncorrelated excitons under pressure and temperature. Appl. Phys. A 132, 106 (2026).

DOI: 10.1007/s00339-026-09290-y

[11] S. Yadav et al., Heterostructures of 2D materials-quantum dots (QDs) for optoelectronic devices: Challenges and opportunities. Emergent Materials 4, 901-922 (2021).

DOI: 10.1007/s42247-021-00222-5

[12] M. Hbibi, O. Mommadi, S. Chouef, R. Boussetta, M. Chnafi, L. Belamkadem, F. Falyouni, Unbound excitonic properties in a multilayered quantum dot under hydrostatic pressure and temperature. Defect Diffus. Forum 428, 105-115 (2023).

DOI: 10.4028/p-uflk2m

[13] R. Boussetta et al., Simultaneous effects of hydrostatic pressure and temperature on the electronic spectrum in the presence of a single off-center donor atom in a hemi-quantum ring. Physica B 665, 415009 (2023).

DOI: 10.1016/j.physb.2023.415009

[14] M. Hbibi et al., Controlled exciton properties in UV light-emitting devices using multilayer cylindrical quantum dots: Improvement through hydrostatic pressure, temperature and strain effects. Optik 324, 172229 (2025).

DOI: 10.1016/j.ijleo.2025.172229

[15] O. Mommadi et al., Excitonic properties in an asymmetric quantum dot nanostructure under combined influence of temperature and lateral hydrostatic pressure. Mater. Today Proc. 13, 1023-1032 (2019).

DOI: 10.1016/j.matpr.2019.04.067

[16] M.D. Frogley, J.L. Sly, D.J. Dunstan, Pressure dependence of the direct band gap in tetrahedral semiconductors. Phys. Rev. B 58, 12579 (1998).

DOI: 10.1103/physrevb.58.12579

[17] C.M. Duque, M.E. Mora-Ramos, C.A. Duque, Simultaneous effects of electron and hole correlation, hydrostatic pressure, and temperature on the third harmonic generation in parabolic GaAs quantum dots. J. Nanopart. Res. 13, 6103 (2011).

DOI: 10.1007/s11051-011-0348-5

[18] T.O. Ayodele, Types of machine learning algorithms. New Adv. Mach. Learn. 3, 5-11 (2010).

[19] A. Ed-Dahmouny et al., Machine learning for optimized nonlinear optical rectification in core/shell nanodiscs under hydrostatic pressure. Ceram. Int. (2026).

DOI: 10.1016/j.ceramint.2026.01.045

[20] N. Zeiri et al., Machine learning-based prediction of nonlinear optical rectification in GaAs/AlGaAs tetrapod core/shell quantum dots under pressure and central hydrogenic impurity effects. Mater. Sci. Semicond. Process. 200, 110010 (2025).

DOI: 10.1016/j.mssp.2025.110010

[21] M. El-Yadri et al., Tunable excitonic transitions in strained GaAs ultra-thin quantum disk. Superlattices Microstruct. 102, 382-390 (2017).

DOI: 10.1016/j.spmi.2016.12.021

[22] N. Aghoutane et al., Optical absorption of excitons in strained quasi 2D GaN quantum dot. Phys. Status Solidi B 256, 1800361 (2019).

DOI: 10.1002/pssb.201800361

[23] C.A. Duque, S.Y. López, M.E. Mora-Ramos, Hydrostatic pressure effects on the X-conduction band mixing and the binding energy of a donor impurity in GaAs–Ga1-xAlxAs quantum wells. Phys. Status Solidi B 244, 1964-1970 (2007).

DOI: 10.1002/pssb.200642377

[24] S. Le Goff, B. Stébé, Influence of longitudinal and lateral confinements on excitons in cylindrical quantum dots of semiconductors. Phys. Rev. B 47, 1383 (1993).

DOI: 10.1103/physrevb.47.1383

[25] O. Mommadi et al., Behavior of optoelectronic properties of exciton–phonon in a multilayered cylindrical quantum well wire dot with two finite confinement potentials. Mater. Sci. Semicond. Process. 168, 107805 (2023).

DOI: 10.1016/j.mssp.2023.107805

[26] M.A. Mkrtchyan et al., Effects of an external magnetic field on the interband and intraband optical properties of an asymmetric biconvex lens shaped quantum dot. Nanomaterials 12, 60 (2022).

DOI: 10.3390/nano12010060

[27] R.G. Toscano Negrette et al. Effect of external fields on the electronic and optical properties in ZnTe/CdSe and CdSe/ZnTe spherical quantum dots. Condensed Matter 8, 66 (2023).

DOI: 10.3390/condmat8030066

[28] A.D. Watpade et al., Comparative analysis of machine learning models for predicting dielectric properties in MoS₂ nanofiller reinforced epoxy composites. Ain Shams Eng. J. 15, 102754 (2024).

DOI: 10.1016/j.asej.2024.102754

[29] A. Cherni et al., Supervised machine learning prediction and investigation of nonlinear optical rectification in Ge/Si₀.₁₅Ge₀.₈₅ asymmetric coupled triangle quantum wells. Results Eng. 27, 106589 (2025).

DOI: 10.1016/j.rineng.2025.106589

[30] A. Ed-Dahmouny et al., Machine learning prediction of electric field dependent absorption coefficient in CdTe/CdS quantum dots. Mater. Today Phys. 101851 (2025).

DOI: 10.1016/j.mtphys.2025.101851