Model parameters extraction for 850 nm GaAs/AlGaAs laser diodes using simple deep neural network

Jung-Tack Yang; Hyewon Han; Tae-Kyung Kim; An-Sik Choi; Woo-Young Choi

doi:10.1117/12.3000804

12 March 2024 Model parameters extraction for 850 nm GaAs/AlGaAs laser diodes using simple deep neural network

Jung-Tack Yang, Hyewon Han, Tae-Kyung Kim, An-Sik Choi, Woo-Young Choi

Proceedings Volume PC12880, Physics and Simulation of Optoelectronic Devices XXXII; PC1288007 (2024) https://doi.org/10.1117/12.3000804
Event: SPIE OPTO, 2024, San Francisco, California, United States

Abstract

Accurately determining numerical values for key model parameters for any semiconductor devices is extremely important for analyzing the device characteristics and model-based device design optimization. However, their experimental determination can be very difficult since measurement results involve interaction of many parameters and isolating the influence of a single parameter is often not possible. One of the ways to solve this issue is deep learning. We achieve accurate determination of key laser diode model parameters such as internal loss, Auger coefficient, and free-carrier absorption coefficient of a fabricated ridge-waveguide 850 nm GaAs/AlGaAs laser diode(LD) applying the trained deep neural network (DNN). We use a LD TCAD simulator, PICS3D, for producing training and testing data. The accuracy of our approach is confirmed by comparing the simulation result with the actual measurement result for the LD L-I characteristics using extracted model parameters by DNN.

Conference Presentation

Citation Download Citation

Jung-Tack Yang, Hyewon Han, Tae-Kyung Kim, An-Sik Choi, and Woo-Young Choi "Model parameters extraction for 850 nm GaAs/AlGaAs laser diodes using simple deep neural network", Proc. SPIE PC12880, Physics and Simulation of Optoelectronic Devices XXXII, PC1288007 (12 March 2024); https://doi.org/10.1117/12.3000804

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available