MODELING AND PREDICTION OF THE ELECTRICAL CONDUCTIVITY OF SEMICONDUCTOR NANOTUBES USING ARTIFICIAL NEURAL NETWORKS
H.B. Ibrahimov1, K.V. Tanriverdili2
   download pdf   

ABSTRACT

In this study, the dependence of the electrical conductivity of semiconductor nanotubes (SNTs) on key parameters-temperature, doping level, and diameter-was modeled and predicted using an artificial neural network (ANN) approach. A semi-empirical model was used to generate 2,000 synthetic data samples, and based on these, an ANN was implemented in the TensorFlow/Keras framework. The results indicate that as temperature increases, enhanced phonon scattering leads to a decrease in conductivity, whereas increases in doping concentration and nanotube diameter result in higher conductivity due to an increased number of charge carriers and reduced surface scattering.

Keywords: semiconductor, nanotube, neural network, machine learning
DOI:10.70784/azip.1.2025257

Received: 17.06.2025
Internet publishing: 20.06.2025    AJP Fizika E 2025 02 en p.57-59

AUTHORS & AFFILIATIONS

1. Institute of Physics Ministry of Science and Education of Azerbaijan, H. Cavid Avenue 131, 1073
2. Azerbaijan Technical University, Baku, H. Javid ave., 25
E-mail:

Graphics and Images

      

      Fig.1

 [1]   Z.L. Wang. 2004. Zinc Oxide Nanostructures: Growth, Properties and Applications. Journal of Physics: Condensed Matter, 16(25), R829–R858. DOI: 10.1088/0953-8984/16/25/R01
[2]   J. Smith, et al. 2019. Electrical conductivity of doped carbon nanotubes: Experimental and theoretical study. Physical Review B, 99(15), 155432. DOI: 10.1103/PhysRevB.99.155432
[3]   Y. Zhang, et al. 2022. Machine learning approaches for nanomaterials characterization. Nature Nanotechnology, 17(3), 245–258. DOI: 10.1038/s41565-021-01030-2
[4]   H. Kim, et al. (2020). Application of neural networks to predict electrical conductivity of nanostructures. Nano Letters, 20(4), 2212–2218. DOI: 10.1021/acs.nanolett.9b05147
[5]   X. Liu, Y. Zhang, Z. Wang. 2023. Machine learning-assisted prediction of electrical conductivity in semiconductor nanowires. Nano Energy, 98, 107325. https://doi.org/10.1016/j.nanoen.2022.107325
[6]   L. Wang, X. Li. 2020. Predictive modeling of semiconductor nanotubes using deep learning. Journal of Applied Physics, 128(10), 104301. DOI: 10.1063/5.0021234
[7]   C. Zhang, S. Bengio, M. Hardt, B. Recht, O. Vinyals. 2021. Understanding Deep Learning Requires Rethinking Generalization. Communications of the ACM, 64(3), 107–115. DOI: 10.1145/3446776
[8]   M. Raghu, B. Poole, J. Kleinberg, S. Ganguli, & J. Sohl-Dickstein. 2017. On the Expressive Power of Deep Neural Networks. International Conference on Machine Learning (ICML), 70, 2847–2854.DOI: 10.5555/3305381.3305518
[9]   J. Smith, L. Zhao. 2022. Data-driven modeling of semiconductor properties using deep neural networks. Computational Materials Science, 205, 110450. DOI: 10.1016/j.commatsci.2022.110450
[10]  C. Unsalan, B. Hoke, E. Atmaca. 2024. Embedded Machine Learning with Microcontrollers. Springer. https://doi.org/10.1007/978-3-031-70912-8
[11]  Z. Zhang. 2024. Research on mechanical parts precision evaluation based on machine learning. In SPIE Conference on Intelligent Mechanical and Human–Machine Systems. DOI: 10.1117/12.3050333
[12]  D. Mane, P. Barapate, & P. Khinde. 2024. Early Lung Cancer Detection Using CNN. 2023 4th International Conference on Communication and Signal Processing (ICCSP), IEEE. p.1-6 DOI: 10.1109/ICCSP58952.2024.10627340
[13]  X. Li, L. Shi. 2024. Open problems in transport physics of ultrahigh-thermal conductivity materials. Journal of Materials Research. DOI: 10.1557/s43578-024-01441-2
[14]  Y. Xu, H. Li. 2021. Prediction of nanomaterial conductivity using artificial neural networks. Materials Today Communications, 27, 102226. DOI: 10.1016/j.mtcomm.2021.102226
[15]  Z. Zhang, et al. 202). ML-based modeling for nano-device electronic properties. Journal of Applied Physics, 134(3), 034501. DOI: 10.1063/5.0133456