Deep learning of ultrafast pulses with a multimode fiber

TL;DR

This paper introduces a deep learning-based method for ultrafast pulse characterization using speckle patterns from a multimode fiber, enabling single-shot measurements with a simple setup.

Contribution

It presents a novel self-referenced technique utilizing multimode fiber speckle patterns and deep learning for accurate, single-shot ultrafast pulse characterization.

Findings

Effective phase recovery using speckle patterns

Ambiguity removal through mode diversity

Single-shot pulse measurement capability

Abstract

Characterizing ultrashort optical pulses has always been a critical but difficult task, which has a broad range of applications. We propose and demonstrate a self-referenced method of characterizing ultrafast pulses with a multimode fiber. The linear and nonlinear speckle patterns formed at the distal end of a multimode fiber are used to recover the spectral amplitude and phase of an unknown pulse. We deploy a deep learning algorithm for phase recovery. The diversity of spatial and spectral modes in a multimode fiber removes any ambiguity in the sign of the recovered spectral phase. Our technique allows for single-shot pulse characterization in a simple experimental setup. This work reveals the potential of multimode fibers as a versatile and multi-functional platform for optical sensing.