Data-driven methods for analysing nonlinear propagation in optical fibres
- Authors
- Publication Date
- Sep 18, 2024
- Source
- HAL
- Keywords
- Language
- English
- License
- Unknown
- External links
Abstract
This thesis aims to apply machine learning methods specifically tailored to the analysis and interpretation of optical pulses as they propagate in a single pass through an optical fiber, and under a variety of conditions. In particular, we will focus on data-driven model discovery approaches that involve the use of machine learning to analyze physical system data with the aim of discovering interpretable and generalizable models and developing methods that can substantially accomplish and/or complement conventional theoretical analysis. To this end, both supervised and unsupervised learning methods will be used to deepen understanding of ultrafast nonlinear phenomena in fiber optics systems.
