Engineering spectro-temporal light states with physics-embedded deep learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shilong, Virally, Stéphane, Demontigny, Gabriel, Cusson, Patrick, Seletskiy, Denis V.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916816361619456
author Liu, Shilong
Virally, Stéphane
Demontigny, Gabriel
Cusson, Patrick
Seletskiy, Denis V.
author_facet Liu, Shilong
Virally, Stéphane
Demontigny, Gabriel
Cusson, Patrick
Seletskiy, Denis V.
contents Frequency synthesis and spectro-temporal control of optical wave packets are central to ultrafast science, with supercontinuum (SC) generation standing as one remarkable example. Through passive manipulation, femtosecond (fs) pulses from nJ-level lasers can be transformed into octave-spanning spectra, supporting few-cycle pulse outputs when coupled with external pulse compressors. While strategies such as machine learning have been applied to control the SC's central wavelength and bandwidth, their success has been limited by the nonlinearities and strong sensitivity to measurement noise. Here, we propose and demonstrate how a physics-embedded convolutional neural network (P-CNN) that embeds spectro-temporal correlations can circumvent such challenges, resulting in faster convergence and reduced noise sensitivity. This innovative approach enables on-demand control over spectro-temporal features of SC, achieving few-cycle pulse shaping without external compressors. This approach heralds a new era of arbitrary spectro-temporal light state engineering, with implications for ultrafast photonics, photonic neuromorphic computation, and AI-driven optical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14410
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Engineering spectro-temporal light states with physics-embedded deep learning
Liu, Shilong
Virally, Stéphane
Demontigny, Gabriel
Cusson, Patrick
Seletskiy, Denis V.
Optics
Pattern Formation and Solitons
Classical Physics
Quantum Physics
Frequency synthesis and spectro-temporal control of optical wave packets are central to ultrafast science, with supercontinuum (SC) generation standing as one remarkable example. Through passive manipulation, femtosecond (fs) pulses from nJ-level lasers can be transformed into octave-spanning spectra, supporting few-cycle pulse outputs when coupled with external pulse compressors. While strategies such as machine learning have been applied to control the SC's central wavelength and bandwidth, their success has been limited by the nonlinearities and strong sensitivity to measurement noise. Here, we propose and demonstrate how a physics-embedded convolutional neural network (P-CNN) that embeds spectro-temporal correlations can circumvent such challenges, resulting in faster convergence and reduced noise sensitivity. This innovative approach enables on-demand control over spectro-temporal features of SC, achieving few-cycle pulse shaping without external compressors. This approach heralds a new era of arbitrary spectro-temporal light state engineering, with implications for ultrafast photonics, photonic neuromorphic computation, and AI-driven optical systems.
title Engineering spectro-temporal light states with physics-embedded deep learning
topic Optics
Pattern Formation and Solitons
Classical Physics
Quantum Physics
url https://arxiv.org/abs/2411.14410