Multi-objective optimization of SOI-based Mach-Zehnder modulators employing deep neural networks and a non-dominant genetic algorithm

Author(s)

de Paula, Romulo, Jr. ; Sutili, Tiago ; Figueiredo, Rafael C. ; Bustamante, Yesica R. R. ; Hernandez-Figueroa, Hugo Enrique ; Abreu, Leandra ; Aldaya, Ivan

• Document type: Journal article
• Source: 2024 INTERNATIONAL CONFERENCE ON OPTICAL MEMS AND NANOPHOTONICS, OMN; v. N/A, p. 2-pg., 2024-01-01.

Abstract

We combine an artificial neural network model of an integrated Mach-Zehnder modulator with a multi-objective optimization algorithm to optimize the modulator's parameters. The use of a multi-objective algorithm leads to a set of non-dominant optimized configurations with different values of figures of merit. (AU)

• FAPESP's process: 21/00199-8 - SMART NEtworks and ServiceS for 2030 (SMARTNESS)
• Grantee: Christian Rodolfo Esteve Rothenberg
• Support Opportunities: Research Grants - Research Centers in Engineering Program
• FAPESP's process: 24/01712-9 - Compensation for transmission impairments in advanced optical communication systems employing artificial intelligence
• Grantee: Ivan Aritz Aldaya Garde
• Support Opportunities: Regular Research Grants
• FAPESP's process: 21/11380-5 - CPTEn - São Paulo Center for the Study of Energy Transition
• Grantee: Luiz Carlos Pereira da Silva
• Support Opportunities: Research Grants - Science Centers for Development
• FAPESP's process: 22/11596-0 - Scientific EMU: acquisition of transmission and characterization equipment for ultra-high-speed data links
• Grantee: Darli Augusto de Arruda Mello
• Support Opportunities: Research Infrastructure Program - Scientific
• FAPESP's process: 21/06506-0 - Strongly resonant all-dielectric metasurfaces based on quasi-dark and toroidal modes
• Grantee: Hugo Enrique Hernández Figueroa
• Support Opportunities: Regular Research Grants