EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Material Classification in Reflective Terahertz Time-Domain Spectroscopy Through Rough-Surface Training

Sebastian T. Gassel, Niklas Schulz, Martin R. Hofmann, Carsten Brenner

Journal of Infrared, Millimeter, and Terahertz Waves · 2026-02 · 47 (2)

DOI: 10.1007/s10762-026-01112-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Infrared, Millimeter, and Terahertz Waves, online erschienen am 22.01.2026. Verfasst von Sebastian T. Gassel und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ruhr-Universität Bochum.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We investigate machine-learning-based material classification in reflective terahertz time-domain spectroscopy (THz-TDS) under controlled surface morphologies. Spectra are acquired from a representative set of engineering materials with either flat surfaces or rough line profiles using a goniometric reflection setup, and a curated dataset of amplitude and unwrapped-phase spectra is prepared for training and evaluation. Classical classifiers, including support vector machines and random forests, are benchmarked across morphology splits. We find that surface morphology is a dominant factor for generalization. Models trained only on flat samples perform poorly when applied to previously unseen rough surfaces, whereas training on a combined set that includes both morphologies restores robust cross-morphology performance. On the combined data, random forests generally outperform support vector machines, and adding phase information improves results further, though careful safeguards are needed to prevent overfitting or leakage related to sample positioning. Feature-importance analysis shows a morphology-dependent shift: flat surfaces favor higher-frequency content, while rough surfaces emphasize lower-frequency bands, consistent with scattering-induced amplitude loss and reduced spectral bandwidth. These findings translate into practical guidance for reflection-based THz-TDS classification: include realistic rough surfaces during training, leverage phase information with appropriate regularization and validation, and design features that account for frequency-dependent scattering.

Förderung

  • Ruhr-Universität Bochum

Zitieren

APA

Gassel, S. T., Schulz, N., Hofmann, M. R., & Brenner, C. (2026). Robust Material Classification in Reflective Terahertz Time-Domain Spectroscopy Through Rough-Surface Training. Journal of Infrared, Millimeter, and Terahertz Waves, 47(2). https://doi.org/10.1007/s10762-026-01112-9

Vancouver

Gassel ST, Schulz N, Hofmann MR, Brenner C. Robust Material Classification in Reflective Terahertz Time-Domain Spectroscopy Through Rough-Surface Training. Journal of Infrared, Millimeter, and Terahertz Waves. 2026;47(2). doi:10.1007/s10762-026-01112-9

BibTeX
@article{Gassel2026,
  author = {Gassel, Sebastian T. and Schulz, Niklas and Hofmann, Martin R. and Brenner, Carsten},
  title = {Robust Material Classification in Reflective Terahertz Time-Domain Spectroscopy Through Rough-Surface Training},
  journal = {Journal of Infrared, Millimeter, and Terahertz Waves},
  year = {2026},
  volume = {47},
  number = {2},
  doi = {10.1007/s10762-026-01112-9}
}
Kostenlos starten →