Sign Up Submit Enquiry

Application of machine learning for predicting the millimetre-wave and sub-millimetre-wave characteristics of avalanche transit time sources

Home Application of machine learning for predicting the millimetre-wave and sub-millimetre-wave characteristics of avalanche transit time sources

Related Articles

Contact us

Article Content

Abstract

We explore the application of artificial neural networks (ANNs) for predicting the millimetre-wave (mm-wave) and sub-millimetre-wave (sub-mm-wave) characteristics of double-drift region (DDR) Si IMPATT diodes. The proposed ANN models predict key parameters such as DC, large-signal (L-S) performance, and avalanche noise characteristics across frequencies ranging from 94 to 500 GHz. A dataset derived from self-consistent quantum drift–diffusion (SCQDD) simulations is used to train the ANN models, which accurately capture the influence of structural, doping, and biasing variations. The ANN models showed a significant reduction in computational time, predicting device characteristics in just 4.4–15% of the time required by SCQDD simulations, while maintaining high accuracy. The mean square error (MSE) between ANN predictions and SCQDD simulations for breakdown voltage and power output was observed to be in the order of 10−3 Unit2, indicating excellent predictive performance. The models were validated against experimental data, showing strong agreement in terms of power output, efficiency, and noise characteristics. This work demonstrates that machine learning can effectively replace traditional time-intensive simulations, making it a promising approach for the rapid design and optimization of high-frequency semiconductor devices.

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

  • Electrical and Electronic Engineering
  • Electronic Materials
  • Machine Learning
  • Semiconductors
  • Technoscience
  • Artificial Intelligence

Data availability

No datasets were generated or analysed during the current study.

References

  1. Steiger, Sebastian, et al. “NEMO5: a parallel multiscale nanoelectronics modeling tool.” (2011).

  2. Luy, J.F., Casel, A., Behr, W., Kasper, E.: A 90-GHz double-drift IMPATT diode made with Si MBE. IEEE Trans. Electron Dev. 34, 1084–1089 (1987)

    Article Google Scholar

  3. Dalle, C., Rolland, P., Lieti, G.: Flat doping profile double-drift silicon IMPATT for reliable CW high power high-efficiency generation in the 94-GHz window. IEEE Trans. Electron Dev. 37, 227–236 (1990)

    Article Google Scholar

  4. Wollitzer, M., Buchler, J., Schafflr, F., Luy, J.F.: D-band Si-IMPATT diodes with 300 mW CW output power at 140 GHz. Electron. Lett. 32, 122–123 (1996)

    Article Google Scholar

  5. Midford, T.A., Bernick, R.L.: Millimeter Wave CW IMPATT diodes and oscillators. IEEE Trans. Microw. Theory Tech. 27, 483–492 (1979)

    Article Google Scholar

  6. Okamoto, H., Ikeda, M.: A comparative study of noise properties of Si IMPATT diodes operating at 80 GHz. Proc. IEEE 64, 367–368 (1976)

    Article Google Scholar

  7. Yuan, L., James, A., Cooper, J.A., Melloch, M.R., Webb, K.J.: Experimental demonstration of a silicon carbide IMPATT oscillator. IEEE Electron Dev. Lett. 22, 266–268 (2001)

    Article Google Scholar

  8. Vassilevski, K. V., Zorenko, A. V., Zekentes, K., Tsagaraki, K., Bano, E., Banc, C., Lebedev, A.: 4H-SiC IMPATT diode fabrication and testing. In: Technical Digest of International Conference on SiC and Related Materials, Tsukuba, Japan, 713–714 (2001).

  9. Trew, R.J., Yan, J.B., Mock, P.M.: The potentiality of diamond and SiC electronic devices for microwave and millimeter-wave power applications. Proc. IEEE 79, 598–620 (1991)

    Article Google Scholar

  10. Kawasaki, S., Kumabe, T., Deki, M., Watanabe, H., Tanaka, A., Honda, Y., Arai, M., Amano, H.: 15 GHz GaN Hi–Lo IMPATT diodes with pulsed peak power of 255 W. IEEE Trans. Electron Dev. 71, 1408–1415 (2024)

    Article Google Scholar

  11. Bian, Z., Marshall, A., Pao, C., Lee, T., Chowdhury, S.: Demonstration of millimeter-wave GaN IMPATT oscillator at Ka-band. In: 2023 International Electron Devices Meeting (IEDM), 1–4 (2023). https://doi.org/10.1109/IEDM45741.2023.10413821.

  12. Kawasaki, S., Kumabe, T., Ando, Y., Deki, M., Watanabe, H., Tanaka, A., Honda, Y., Arai, M., Amano, H.: Junction diameter dependence of oscillation frequency of GaN IMPATT diode up to 21 GHz. IEEE Trans. Electron Dev. 44, 1328–1331 (2023)

    Article Google Scholar

  13. Banerjee, P., Acharyya, A., Das, R., Biswas, A., Bhattacharjee, A.K., Mallik, S., Alshahrani, H.M., Elshiekh, E., Abbas, M., Soufiene, B.O.: Mutually injection locked multi-element terahertz oscillator based on AlGaN/GaN high electron mobility avalanche transit time devices. IEEE Access 12, 123656–123677 (2024)

    Article Google Scholar

  14. Ghosh, M., Deb, S.B., Acharyya, A., Biswas, A., Inokawa, H., Satoh, H., Banerjee, A., Seteikin, A.Y., Samusev, I.G.: Edge-terminated AlGaN/GaN/AlGaN multi-quantum well impact avalanche transit time sources for terahertz wave generation. Nanomaterials 14, 873 (2024)

    Article Google Scholar

  15. Acharyya, A., Banerjee, J.P.: Prospects of IMPATT devices based on wide bandgap semiconductors as potential terahertz sources. Appl. Nanosci. 4, 1–14 (2014)

    Article Google Scholar

  16. Gilden, M., Hines, M.E.: Electronic tuning effects in read microwave avalanche diode. IEEE Trans. Electron Dev. 13, 169–175 (1966)

    Article Google Scholar

  17. Gummel, H.K., Blue, J.L.: A small-signal theory of avalanche noise in IMPATT diodes. IEEE Trans. Electron Dev. 14, 569–580 (1967)

    Article Google Scholar

  18. Fisher, S.T.: Small-signal impedance of avalanche junctions with unequal electron and hole ionization rates and drift velocities. IEEE Trans. Electron Dev. 14, 313–322 (1967)

    Article Google Scholar

  19. Kwok, S.P., Haddad, G.I.: Effect of tunnelling on an IMPATT oscillator. J. Appl. Phys. 43, 3824–3830 (1972)

    Article Google Scholar

  20. Culshaw, B.: Effect of carrier diffusion on operation of avalanche diodes. Electron. Lett. 10, 143-SS (1974).

  21. Lee, C.M., Seddik, M.E., Haddad, G.I.: Effect of ionization rates on Si IMPATT diodes. IEEE Trans. Electron Dev. 21, 808 (1974)

    Article Google Scholar

  22. Scharfetter, D.L., Gummel, H.K.: Large-signal analysis of a silicon read diode oscillator. IEEE Trans. Electron Dev. 6, 64–77 (1969)

    Article Google Scholar

  23. Gupta, M.S., Lomax, R.J.: A current-excited large-signal analysis of IMPATT devices and its circuit implementations. IEEE Trans. Electron Dev. 20, 395–399 (1973)

    Article Google Scholar

  24. Acharyya, A., Chatterjee, S., Goswami, J., Banerjee, S., Banerjee, J.P.: Quantum drift-diffusion model for IMPATT devices. J. Comput. Electron. 13, 739–752 (2014)

    Article Google Scholar

  25. Acharyya, A., Goswami, J., Banerjee, S., Banerjee, J.P.: Quantum-corrected drift-diffusion model for terahertz IMPATTs based on different semiconductors. J. Comput. Electron. 14, 309–320 (2015)

    Article Google Scholar

  26. Ghosh, M., Ghosh, S., Acharyya, A.: Self-consistent quantum drift-diffusion model for multiple quantum well IMPATT diodes. J. Comput. Electron. 15, 1370–1387 (2017)

    Article Google Scholar

  27. Ghosh, M., Ghosh, S., Bandyopadhyay, P.K., Biswas, A., Bhattacharjee, A.K., Acharyya, A.: Noise performance of 94 GHz multiple quantum well double-drift region IMPATT sources. J. Active Pass. Electron Devices 13, 195–207 (2018)

    Google Scholar

  28. Xu, Jianjun, and David E. Root. “Advances in artificial neural network models of active devices.” 2015 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO). IEEE, 2015.

  29. Hammouda, H.B., et al.: Neural based models of semiconductor devices for SPICE simulator. Am. J. Appl. Sci. 54, 385–391 (2008)

    Google Scholar

  30. Wang, F., Zhang, Q.-J.: Knowledge-based neural models for microwave design. IEEE Trans. Microw. Theory Tech. 45(12), 2333–2343 (1997)

    Article Google Scholar

  31. Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251–257 (1991)

    Article MathSciNet Google Scholar

  32. Zhang, L., Chan, M.: Artificial neural network design for compact modeling of generic transistors. J. Comput. Electron. 16, 825–832 (2017). https://doi.org/10.1007/s10825-017-0984-9

    Article Google Scholar

  33. Wang, J., Kim, Y.H., Ryu, J., Jeong, C., Choi, W., Kim, D.: Artificial neural network-based compact modeling methodology for advanced transistors. IEEE Trans. Electron Dev. 68, 1318–1325 (2021)

    Article Google Scholar

  34. Zhang, Q. J., Gupta, K. C.: Neural networks for RF and microwave design. Artech House, Norwood (2000).

  35. Xu, J., Yagoub, M.C.E., Ding, R., Zhang, Q.J.: Exact adjoint sensitivity analysis for neural-based microwave modeling and design. IEEE Trans. Microw. Theory Tech. 51, 226–237 (2003). https://doi.org/10.1109/TMTT.2002.806910

    Article Google Scholar

  36. Xu, J., Gunyan, D., Iwamoto, M., Horn, J. M., Cognata, A., Root, D. E.: Drain-source symmetric artificial neural network-based FET model with robust extrapolation beyond training data. In: IEEE MTT-S Int. Microw. Symp. Dig., Honolulu, 2011–2014 (2007). https://doi.org/10.1109/MWSYM.2007.380244.

  37. Li, M., Irsoy, O., Cardie, C., Xing, H.G.: Physics-inspired neural networks for efficient device compact modeling. IEEE. J. Explor. Solid-State Comput. Dev. Circuit 2, 44–49 (2016). https://doi.org/10.1109/JXCDC.2016.2636161

    Article Google Scholar

  38. Lei, Y., Huo, X., Yan, B.: Deep neural network for device modeling. In: Proc. IEEE 2nd Electron Devices Technol. Manuf. Conf. (EDTM), pp. 154–156, Kobe, Japan (2018). https://doi.org/10.1109/EDTM.2018.8421454

  39. Zhang, L., Chan, M.: Artificial neural network design for compact modeling of generic transistors. J. Comput. Electron. 16(3), 825–832 (2017). https://doi.org/10.1007/s10825-017-0984-9

    Article Google Scholar

  40. Kim, Y., Myung, S., Ryu, J., Jeong, C., Kim, D.S.: Physics-augmented neural compact model for emerging device technologies. In: Proc. Int. Conf. Simulation Semiconductor Processes Devices (SISPAD), pp. 257–260, Kobe, Japan (2020). https://doi.org/10.23919/SISPAD49475.2020.9241638

  41. Chen, Q., Chen, G.: Artificial neural network compact model for TFTs. In: Proc. 7th Int. Conf. Comput. Aided Design Thin-Film Transistor Technol. (CAD-TFT), p. 1, Beijing, China (2016). https://doi.org/10.1109/CAD-TFT.2016.7785057

  42. Root, D.: Future device modeling trends. IEEE Microw. Mag. 13(7), 45–59 (2012). https://doi.org/10.1109/MMM.2012.2216095

    Article Google Scholar

  43. Huang, A., Zhong, Z., Guo, Y.-X., Wu, W.: A dimension-reduced artificial neural network for the compact modeling of semiconductor devices. In: IEEE MTT-S Int. Microw. Symp. Dig., pp. 1–4, Chengdu, China (2018). https://doi.org/10.1109/IEEE-IWS.2018.8400840

  44. Zhang, Z., et al.: New-generation design-technology co-optimization (DTCO): Machine-learning assisted modeling framework. In: Proc. Silicon Nanoelectron. Workshop (SNW), pp. 1–2, Kyoto, Japan (2019). https://doi.org/10.23919/SNW.2019.8782897

  45. Paszke, A., et al.: PyTorch: An imperative style, high-performance deep learning library. In: Wallach, H. (ed.) Advances in Neural Information Processing Systems, pp. 8024–8035. Curran Associates, Red Hook, NY (2019). [Online]. Available: https://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf

  46. Cao, L.: GaN-Based Impact-Ionization Avalanche Transit-Time (IMPATT) Diodes and Low-Loss Interconnects for Microwave and Millimeter Wave Applications. PhD Thesis, University of Notre Dame, pp. 87–92 (2020). https://doi.org/10.7274/0v838052b06

  47. Cao, L., Wang, J., Harden, G., Ye, H., Stillwell, R., Hoffman, A.J., Fay, P.: Experimental characterization of impact ionization coefficients for electrons and holes in GaN grown on bulk GaN substrates. Appl. Phys. Lett. 112, 262103 (2018)

    Article Google Scholar

  48. Acharyya, A., Banerjee, S., Banerjee, J.P.: Influence of skin effect on the series resistance of millimeter-wave IMPATT devices. J. Comput. Electron. 12(3), 511–525 (2013)

    Article Google Scholar

  49. Acharyya, A., Banerjee, S., Banerjee, J.P.: A proposed simulation technique to study the series resistance and related millimeter-wave properties of Ka-band Si IMPATTs from the electric field snapshots. Int. J. Microw. Wirel. Technol. 5(1), 91–100 (2013)

    Article Google Scholar

  50. Grant, W.N.: Electron and hole ionization rates in epitaxial silicon. Solid State Electron. 16, 1189–1203 (1973)

    Article Google Scholar

  51. Canali, C., Ottaviani, G., Quaranta, A.A.: Drift velocity of electrons and holes and associated anisotropic effects in silicon. J. Phys. Chem. Solids 32, 1707–1720 (1971)

    Article Google Scholar

  52. ________: Electronic Archive: New Semiconductor Materials, Characteristics and Properties. Available: http://www.ioffe.ru/SVA/NSM/Semicond/index.html (Accessed: September 2020).

  53. Zeghbroeck, B.V.: Principles of Semiconductor Devices. Colorado Press, USA (2011)

    Google Scholar

  54. Acharyya, A., Banerjee, S., Banerjee, J.P.: Effect of junction temperature on the large-signal properties of a 94 GHz silicon-based double-drift region IMPATT device. J. Semicond. 34(2), 024001 (2013)

    Article Google Scholar

  55. Grosan, C., Abraham, A.: Artificial Neural Networks. In: Intelligent Systems. Intelligent Systems Reference Library, vol. 17, pp. 111–126. Springer, Berlin, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21004-4_12

  56. ________: Keras 3 API documentation. Available at: https://keras.io/api/

  57. Kelley, H.J.: Gradient theory of optimal flight paths. Ars J. 30(10), 947–954 (1960)

    Article Google Scholar

  58. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).

  59. Acharyya, A., Banerjee, S., Banerjee, J.P.: Large-signal simulation of 94 GHz pulsed DDR silicon IMPATTs including the temperature transient effect. Radioengineering 21(4), 1218–1225 (2012)

    Google Scholar

  60. Tripathy, P.R., Chaoudhury, S.K., Pati, S.P.: MM-wave double drift IMPATT diode: a comparison of experimental, theoretical and neural network approach. Int. J. Nano Biomater. 7(4), 262–273 (2018)

    Article Google Scholar

Download references

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, National Institute of Technology (NIT) Mizoram, Chaltlang, Aizawl, Mizoram, 796012, India

    Prerona Sanyal & Rudra Sankar Dhar

  2. Department of Electronics and Communication Engineering, Kalyani Government Engineering College, Kalyani, Nadia, West Bengal, 741235, India

    Sneha Ray & Aritra Acharyya

  3. Department of Mining Engineering, Kazi Nazrul University, Asansol, Burdwan, West Bengal, 713340, India

    Arndam Biswas

Contributions

P. S. and A. A. carried out the simulations, and prepared the initial draft of the manuscript, S. R. carried out the simulations, and prepared the revised manuscript, A. B. prepared all the figures and graphs, and reviewed the manuscript, R. S. D. reviewed the manuscript and prepared the final draft of the manuscript.

Corresponding author

Correspondence to Aritra Acharyya.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Cite this article

Sanyal, P., Ray, S., Acharyya, A. et al. Application of machine learning for predicting the millimetre-wave and sub-millimetre-wave characteristics of avalanche transit time sources. J Comput Electron 24, 137 (2025). https://doi.org/10.1007/s10825-025-02382-7

Download citation

  • Received 
  • Accepted 
  • Published 
  • DOI  https://doi.org/10.1007/s10825-025-02382-7

Keywords

  • Machine learning
  • Artificial neural networks (ANN)
  • Millimetre-wave (mm-wave)
  • Sub-millimetre-wave (sub-mm-wave)
  • Avalanche transit time (ATT)
  • IMPATT diodes
  • Large-signal simulation
  • Self-consistent quantum drift-diffusion (SCQDD) model

Copyright © All rights reserved Designed and Developed by Digital Flavers

WhatsApp