Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Inverse Design of Microresonators Using Machine Learning

Pal A, Ghosh A, Zhang S, Bi T, Del'Haye P (2023)

---

Publication Type: Conference contribution

Publication year: 2023

Publisher: Institute of Electrical and Electronics Engineers Inc.

Conference Proceedings Title: 2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

Event location: Munich, DEU

ISBN: 9798350345995

DOI: 10.1109/CLEO/EUROPE-EQEC57999.2023.10232825

Abstract

The rapidly increasing number of ways to fabricate integrated microresonators have led to a demand for optimization of such structures based on the desired optical properties. Tweaking the geometry of photonic structures can alter their dispersion profiles, which can counter optical nonlinearities and influence the intracavity optical dynamics. The parameter Dint describes the integrated dispersion which can be written as, (Equation presented) Here, ωm is the angular resonance frequency of the m^th mode with respect to the pump mode m0 at angular pump frequency ω0. D1 refers to the angular free spectral range around the pump mode. Conventional photonic inverse design works [1,2] start with a design from empirical knowledge and then iteratively optimize the structure, which is both time-consuming and also requires additional quality factor engineering. However, machine learning (ML) being a faster alternative has shown significant applications in the field of photonics [3,4]. In this work [5], ML is used to predict the structure of a micro-ring Si3N4 resonator based on the desired dispersion profile. The regressor model is trained using 75% of the dispersion dataset simulated using a finite element method. For generating the simulation dataset around the wavelength of 1 μm to 2 μm, the radii, widths and heights of the core are varied in ranges close to the resonators fabricated in our lab from sputtered Si3N4 film [6]. Two ML algorithms, Decision Tree (DT) and Random Forest (RF), are compared. RF yielded better prediction results.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Pal, A., Ghosh, A., Zhang, S., Bi, T., & Del'Haye, P. (2023). Inverse Design of Microresonators Using Machine Learning. In 2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023. Munich, DEU: Institute of Electrical and Electronics Engineers Inc..

MLA:

Pal, Arghadeep, et al. "Inverse Design of Microresonators Using Machine Learning." Proceedings of the 2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023, Munich, DEU Institute of Electrical and Electronics Engineers Inc., 2023.

BibTeX: Download