MIR laser CEP estimation using machine learning concepts in bulk high harmonic generation

Abstract

Monitoring the carrier-envelope phase (CEP) is of paramount importance for experiments involving few-cycle intense laser fields. Common measurement techniques include f-2f interferometry or stereo-ATI setups. Here we demonstrate a new concept, both by simulations and by experiments, for CEP estimation in the mid-infrared regime using machine learning (ML) techniques that rely on the observation of the spectrum of high harmonic generation (HHG) in bulk material. Once the ML model is trained, the method provides a way for cheap and compact in-situ CEP tagging. This technique can complement other CEP monitoring methods, can capture the complex correlation between the CEP and the observable HHG spectra, and is readily generalizable for any laser wavelengths.