Neural-network-powered pulse reconstruction from one-dimensional interferometric correlation traces

Abstract

Any ultrafast optical spectroscopy experiment is usually accompanied by the necessary routine of ultrashort-pulse characterization. The majority of pulse characterization approaches solve either a one-dimensional (e.g., via interferometry) or a two-dimensional (e.g., via frequency-resolved measurements) problem. Solution of the two-dimensional pulse-retrieval problem is generally more consistent due to the problem’s over-determined nature. In contrast, the one-dimensional pulse-retrieval problem, unless constraints are added, is impossible to solve unambiguously as ultimately imposed by the fundamental theorem of algebra. In cases where additional constraints are involved, the one-dimensional problem may be possible to solve, however, existing iterative algorithms lack generality, and often stagnate for complicated pulse shapes. Here we use a deep neural network to unambiguously solve a constrained one-dimensional pulse-retrieval problem and show the potential of fast, reliable and complete pulse characterization using interferometric correlation time traces determined by the pulses with partial spectral overlap.