Reducing errors in THz material parameter determination by model-based time-domain extraction methods

We demonstrate a reduction of THz material parameter estimation errors by a factor of 40, using a time-domain material-model-based extraction method, in comparison with the respective frequency-domain approach. Based on simulated and experimentally measured THz time-domain spectroscopy data with different levels of the signalto-noise ratios (SNR), an improved robustness of the time-domain scheme with regard to noise is demonstrated. This approach thereby provides an additional tool for the extraction of material parameters, which is especially suited for the evaluation of spectral data of samples with strong resonant absorption features, even if the SNR at those features drops below 0 dB. The cause for the difference in performance between the frequency-domain and time-domain methods is identified and a formal description provided. (C) 2021 Optical Society of America