We propose a machine learning-based model to extract physical parameters characterizing stationary and dynamic behavior of a VCSEL. The model is trained with circuit-level simulations of light-current and S21 characteristics. Excellent results are achieved as a relative prediction error.

Automated model for characterization of VCSEL circuit-level parameters using machine learning / Marchisio, Andrea; Khan, Ihtesham; Tunesi, Lorenzo; Masood, Muhammad Umar; Ghillino, Enrico; Curri, Vittorio; Carena, Andrea; Bardella, Paolo. - ELETTRONICO. - (2023), pp. 264-266. (Intervento presentato al convegno European Conference on Integrated Optics tenutosi a Enschede, Paesi Bassi nel 19-21 Aprile 2023).

Automated model for characterization of VCSEL circuit-level parameters using machine learning

Marchisio, Andrea;Khan, Ihtesham;Tunesi, Lorenzo;Masood, Muhammad Umar;Curri, Vittorio;Carena, Andrea;Bardella, Paolo
2023

Abstract

We propose a machine learning-based model to extract physical parameters characterizing stationary and dynamic behavior of a VCSEL. The model is trained with circuit-level simulations of light-current and S21 characteristics. Excellent results are achieved as a relative prediction error.
File in questo prodotto:
File Dimensione Formato  
2023_ECIO_Automated_Model_for_Characterization_of_VCSEL_Circuit_level_Parameters_Using_Machine_Learning.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 291.65 kB
Formato Adobe PDF
291.65 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2978489