Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks

This work investigates the application of artificial neural network (ANN)-based regression models to predict the static and dynamic characteristics of GaN impact avalanche transit time (IMPATT) sources in the terahertz (THz) frequency regime. A comprehensive dataset, derived from self-consistent qua...

Full description

Saved in:
Bibliographic Details
Main Authors: Santu Mondal, Sneha Ray, Aritra Acharyya, Rudra Sankar Dhar, Arindam Biswas, Hiroaki Satoh, Gurudas Mandal, Vitaliy Maksimenko, Victor Krishtop
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10988773/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849761299986120704
author Santu Mondal
Sneha Ray
Aritra Acharyya
Rudra Sankar Dhar
Arindam Biswas
Hiroaki Satoh
Gurudas Mandal
Vitaliy Maksimenko
Victor Krishtop
author_facet Santu Mondal
Sneha Ray
Aritra Acharyya
Rudra Sankar Dhar
Arindam Biswas
Hiroaki Satoh
Gurudas Mandal
Vitaliy Maksimenko
Victor Krishtop
author_sort Santu Mondal
collection DOAJ
description This work investigates the application of artificial neural network (ANN)-based regression models to predict the static and dynamic characteristics of GaN impact avalanche transit time (IMPATT) sources in the terahertz (THz) frequency regime. A comprehensive dataset, derived from self-consistent quantum drift-diffusion (SCQDD) simulations of GaN IMPATT structures designed for a wide frequency range from the microwave frequency bands, up to 5 THz, is used to train the ANN models. The models effectively capture the impact of variations in structural, doping, and biasing parameters on device performance. The proposed ANN approach significantly reduces computational time for predicting breakdown characteristics, power output, and conversion efficiency properties of IMPATT sources, achieving similar accuracy to traditional SCQDD simulations while requiring only 7.8&#x2013;20.1% of the computational time. Mean square errors are observed to be on the order of <inline-formula> <tex-math notation="LaTeX">$10^{-4}$ </tex-math></inline-formula>&#x2013;<inline-formula> <tex-math notation="LaTeX">$10^{-6}$ </tex-math></inline-formula>, demonstrating the models&#x2019; high accuracy. Experimental validation shows strong agreement in terms of breakdown voltage, power output, and efficiency, supporting the potential of machine learning to streamline the design and optimization of high-frequency semiconductor devices.
format Article
id doaj-art-00218b0f556d41c0a156aedc2436e373
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-00218b0f556d41c0a156aedc2436e3732025-08-20T03:06:04ZengIEEEIEEE Access2169-35362025-01-0113842848430210.1109/ACCESS.2025.356741010988773Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural NetworksSantu Mondal0https://orcid.org/0009-0000-6458-5560Sneha Ray1Aritra Acharyya2https://orcid.org/0000-0003-0231-4145Rudra Sankar Dhar3https://orcid.org/0000-0002-6571-3808Arindam Biswas4https://orcid.org/0000-0002-2576-8919Hiroaki Satoh5https://orcid.org/0000-0002-5868-0219Gurudas Mandal6Vitaliy Maksimenko7https://orcid.org/0009-0007-2296-140XVictor Krishtop8https://orcid.org/0000-0001-8871-8751Department of Information Technology, Asansol Engineering College, Asansol, West Bengal, IndiaDepartment of Electronics and Communication Engineering, Kalyani Government Engineering College, Nadia, Kalyani, West Bengal, IndiaDepartment of Electronics and Communication Engineering, Kalyani Government Engineering College, Nadia, Kalyani, West Bengal, IndiaDepartment of Electronics and Communication Engineering, National Institute of Technology at Mizoram, Aizawl, Mizoram, IndiaDepartment of Mining Engineering, School of Mines and Metallurgy, Kazi Nazrul University, Asansol, Burdwan, West Bengal, IndiaResearch Institute of Electronics, Shizuoka University, Hamamatsu, JapanCentre for IoT and AI Integration with Education-Industry-Agriculture, Kazi Nazrul University, Asansol, West Bengal, IndiaGeneral Physics Department, Perm National Research Polytechnic University, Perm, RussiaGeneral Physics Department, Perm National Research Polytechnic University, Perm, RussiaThis work investigates the application of artificial neural network (ANN)-based regression models to predict the static and dynamic characteristics of GaN impact avalanche transit time (IMPATT) sources in the terahertz (THz) frequency regime. A comprehensive dataset, derived from self-consistent quantum drift-diffusion (SCQDD) simulations of GaN IMPATT structures designed for a wide frequency range from the microwave frequency bands, up to 5 THz, is used to train the ANN models. The models effectively capture the impact of variations in structural, doping, and biasing parameters on device performance. The proposed ANN approach significantly reduces computational time for predicting breakdown characteristics, power output, and conversion efficiency properties of IMPATT sources, achieving similar accuracy to traditional SCQDD simulations while requiring only 7.8&#x2013;20.1% of the computational time. Mean square errors are observed to be on the order of <inline-formula> <tex-math notation="LaTeX">$10^{-4}$ </tex-math></inline-formula>&#x2013;<inline-formula> <tex-math notation="LaTeX">$10^{-6}$ </tex-math></inline-formula>, demonstrating the models&#x2019; high accuracy. Experimental validation shows strong agreement in terms of breakdown voltage, power output, and efficiency, supporting the potential of machine learning to streamline the design and optimization of high-frequency semiconductor devices.https://ieeexplore.ieee.org/document/10988773/Artificial neural networks (ANN)avalanche transit time (ATT)IMPATT diodeslarge-signal simulationmachine learningself-consistent quantum drift-diffusion (SCQDD) model
spellingShingle Santu Mondal
Sneha Ray
Aritra Acharyya
Rudra Sankar Dhar
Arindam Biswas
Hiroaki Satoh
Gurudas Mandal
Vitaliy Maksimenko
Victor Krishtop
Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks
IEEE Access
Artificial neural networks (ANN)
avalanche transit time (ATT)
IMPATT diodes
large-signal simulation
machine learning
self-consistent quantum drift-diffusion (SCQDD) model
title Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks
title_full Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks
title_fullStr Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks
title_full_unstemmed Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks
title_short Accelerated Prediction of Terahertz Performance Metrics in GaN IMPATT Sources via Artificial Neural Networks
title_sort accelerated prediction of terahertz performance metrics in gan impatt sources via artificial neural networks
topic Artificial neural networks (ANN)
avalanche transit time (ATT)
IMPATT diodes
large-signal simulation
machine learning
self-consistent quantum drift-diffusion (SCQDD) model
url https://ieeexplore.ieee.org/document/10988773/
work_keys_str_mv AT santumondal acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT sneharay acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT aritraacharyya acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT rudrasankardhar acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT arindambiswas acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT hiroakisatoh acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT gurudasmandal acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT vitaliymaksimenko acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks
AT victorkrishtop acceleratedpredictionofterahertzperformancemetricsinganimpattsourcesviaartificialneuralnetworks