Removal of cross-phase modulation artifacts in ultrafast pump-probe dynamics by deep learning

Pump-probe spectroscopy is a gold standard technique to investigate ultrafast electronic dynamics of material systems. Pulsed laser sources employed to pump and probe samples feature typically high peak power, which may give rise to coherent artifacts under a wide range of experimental conditions. Among those, the Cross-Phase Modulation (XPM) artifact has gathered particular attention as it produces particularly high signal distortions, in some cases hiding a relevant portion of the dynamics of interest. Here, we present a novel approach for the removal of XPM coherent artifacts in ultrafast pump-probe spectroscopy, based on deep learning. We developed XPMnet, a convolutional neural network able to reconstruct electronic relaxation dynamics otherwise embedded in artifact distortions, thus enabling the retrieval of fundamental information to characterize the material system under investigation. We validated XPMnet on Indium Tin Oxide (ITO), a heavily doped semiconductor displaying a plasmon resonance in the near-infrared, which is a key material for the development of infrared plasmonic devices. Pump-probe measurements of ITO show strong XPM artifacts that overwhelm the electronic cooling dynamics of interest due to the low optical density of the material at near-infrared photon energies. XPMnet retrieved ITO electronic dynamics in excellent agreement with expected outcomes in terms of material-specific time constants. This artificial intelligence method constitutes a powerful solution for XPM artifact removal, providing high accuracy and short execution time. We believe that this model could be integrated in real time in pump-probe setups to increase the amount of information one can derive from ultrafast spectroscopy measurements