Computer-automated design of mode-locked fiber lasers

Abstract

We automate the mode-locked fiber laser design process using a modified genetic algorithm and an intuitive optimization loss function to control highly accurate polarization-resolved simulations of laser start-up dynamics without user interaction. We reconstruct both the cavity designs and output pulse characteristics of experimentally demonstrated Yb-fiber all-normal dispersion, dispersion-managed, and wavelength-tuneable all-anomalous dispersion Tm-fiber femtosecond lasers with exceptional accuracy using minimal prior knowledge, and show that our method can be used to predict new cavity designs and novel mode locking states that meet target pulse requirements. Our approach is directly applicable to a broad range of mode locking regimes, wavelengths, pulse energies, and repetition rates, requires no training or knowledge of the loss function gradients, and is scalable for use on supercomputers and inexpensive desktop computers.