Sample classification using machine learning-assisted entangled two-photon absorption

Entangled two-photon absorption (eTPA) has been recognized as a potentially powerful tool for the implementation of ultra-sensitive spectroscopy. Unfortunately, there exists a general agreement in the quantum optics community that experimental eTPA signals, particularly those obtained from molecular solutions, are extremely weak. Consequently, obtaining spectroscopic information about an arbitrary sample via conventional methods rapidly becomes an unrealistic endeavor. To address this problem, the authors introduce an experimental scheme that reduces the amount of data needed to identify and classify unknown samples via their electronic structure. Their proposed method makes use of machine learning to extract information about the number of intermediate levels that participate in the two-photon excitation of the absorbing medium. This is achieved by training artificial neural networks (ANNs) with various eTPA signals where the delay between the absorbed photons is externally controlled. Inspired by multiple experimental studies of eTPA, the authors consider model systems comprising one to four intermediate levels, whose energies are randomly chosen from four different intermediate-level bandgaps, namely, Δλ=10, 20, 30, and 40 nm. Within these bandgaps, and with the goal of testing the efficiency of their artificial intelligence algorithms, the authors make use of three different wavelength spacing 1, 0.5, and 0.1 nm. The authors find that for a proper entanglement time between the absorbed photons, classification average efficiencies exceed 99% for all configurations. Their results demonstrate the potential of ANNs for facilitating the experimental implementation of eTPA spectroscopy.