Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning
The tunnel junction (TJ) is a crucial structure for numerous III-nitride devices. A fundamental challenge for TJ design is to minimize the TJ resistance at high current densities. In this work, we propose the asymmetric p-AlGaN/i-InGaN/n-AlGaN TJ structure for the first time. P-AlGaN/i-InGaN/n-AlGaN...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Nanomaterials |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-4991/11/10/2466 |
_version_ | 1797513704613347328 |
---|---|
author | Rongyu Lin Peng Han Yue Wang Ronghui Lin Yi Lu Zhiyuan Liu Xiangliang Zhang Xiaohang Li |
author_facet | Rongyu Lin Peng Han Yue Wang Ronghui Lin Yi Lu Zhiyuan Liu Xiangliang Zhang Xiaohang Li |
author_sort | Rongyu Lin |
collection | DOAJ |
description | The tunnel junction (TJ) is a crucial structure for numerous III-nitride devices. A fundamental challenge for TJ design is to minimize the TJ resistance at high current densities. In this work, we propose the asymmetric p-AlGaN/i-InGaN/n-AlGaN TJ structure for the first time. P-AlGaN/i-InGaN/n-AlGaN TJs were simulated with different Al or In compositions and different InGaN layer thicknesses using TCAD (Technology Computer-Aided Design) software. Trained by these data, we constructed a highly efficient model for TJ resistance prediction using machine learning. The model constructs a tool for real-time prediction of the TJ resistance, and the resistances for 22,254 different TJ structures were predicted. Based on our TJ predictions, the asymmetric TJ structure (p-Al<sub>0.7</sub>Ga<sub>0.3</sub>N/i-In<sub>0.2</sub>Ga<sub>0.8</sub>N/n-Al<sub>0.3</sub>Ga<sub>0.7</sub>N) with higher Al composition in p-layer has seven times lower TJ resistance compared to the prevailing symmetric p-Al<sub>0.3</sub>Ga<sub>0.7</sub>N/i-In<sub>0.2</sub>Ga<sub>0.8</sub>N/n-Al<sub>0.3</sub>Ga<sub>0.7</sub>N TJ. This study paves a new way in III-nitride TJ design for optical and electronic devices. |
first_indexed | 2024-03-10T06:20:21Z |
format | Article |
id | doaj.art-a27c7b7e2ce249b281b6764ec21bc696 |
institution | Directory Open Access Journal |
issn | 2079-4991 |
language | English |
last_indexed | 2024-03-10T06:20:21Z |
publishDate | 2021-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Nanomaterials |
spelling | doaj.art-a27c7b7e2ce249b281b6764ec21bc6962023-11-22T19:21:42ZengMDPI AGNanomaterials2079-49912021-09-011110246610.3390/nano11102466Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine LearningRongyu Lin0Peng Han1Yue Wang2Ronghui Lin3Yi Lu4Zhiyuan Liu5Xiangliang Zhang6Xiaohang Li7Advanced Semiconductor Laboratory, King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaLaboratory Machine, Intelligence and kNowledge Engineering (MINE), King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaAdvanced Semiconductor Laboratory, King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaAdvanced Semiconductor Laboratory, King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaAdvanced Semiconductor Laboratory, King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaAdvanced Semiconductor Laboratory, King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaLaboratory Machine, Intelligence and kNowledge Engineering (MINE), King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaAdvanced Semiconductor Laboratory, King Abdullah University of Science and Technology, Thuwal 23955, Saudi ArabiaThe tunnel junction (TJ) is a crucial structure for numerous III-nitride devices. A fundamental challenge for TJ design is to minimize the TJ resistance at high current densities. In this work, we propose the asymmetric p-AlGaN/i-InGaN/n-AlGaN TJ structure for the first time. P-AlGaN/i-InGaN/n-AlGaN TJs were simulated with different Al or In compositions and different InGaN layer thicknesses using TCAD (Technology Computer-Aided Design) software. Trained by these data, we constructed a highly efficient model for TJ resistance prediction using machine learning. The model constructs a tool for real-time prediction of the TJ resistance, and the resistances for 22,254 different TJ structures were predicted. Based on our TJ predictions, the asymmetric TJ structure (p-Al<sub>0.7</sub>Ga<sub>0.3</sub>N/i-In<sub>0.2</sub>Ga<sub>0.8</sub>N/n-Al<sub>0.3</sub>Ga<sub>0.7</sub>N) with higher Al composition in p-layer has seven times lower TJ resistance compared to the prevailing symmetric p-Al<sub>0.3</sub>Ga<sub>0.7</sub>N/i-In<sub>0.2</sub>Ga<sub>0.8</sub>N/n-Al<sub>0.3</sub>Ga<sub>0.7</sub>N TJ. This study paves a new way in III-nitride TJ design for optical and electronic devices.https://www.mdpi.com/2079-4991/11/10/2466tunnel junctionmachine learningIII-nitride |
spellingShingle | Rongyu Lin Peng Han Yue Wang Ronghui Lin Yi Lu Zhiyuan Liu Xiangliang Zhang Xiaohang Li Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning Nanomaterials tunnel junction machine learning III-nitride |
title | Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning |
title_full | Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning |
title_fullStr | Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning |
title_full_unstemmed | Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning |
title_short | Low Resistance Asymmetric III-Nitride Tunnel Junctions Designed by Machine Learning |
title_sort | low resistance asymmetric iii nitride tunnel junctions designed by machine learning |
topic | tunnel junction machine learning III-nitride |
url | https://www.mdpi.com/2079-4991/11/10/2466 |
work_keys_str_mv | AT rongyulin lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT penghan lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT yuewang lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT ronghuilin lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT yilu lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT zhiyuanliu lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT xiangliangzhang lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning AT xiaohangli lowresistanceasymmetriciiinitridetunneljunctionsdesignedbymachinelearning |