Demystifying the Black Box: Making Machine Learning Models Explainable in Spectroscopy
Spectroscopy · 08.09.2025
DOI: 10.56530/spectroscopy.ps4569v3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Spectroscopy, online erschienen am 08.09.2025. Verfasst von Jerome Workman. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 5 Literaturangaben.
Abstract (Originalsprache)
Machine learning models, particularly deep learning approaches, have achieved remarkable performance in spectral analysis, including atomic, near-infrared (NIR), Raman, and infrared spectroscopy. However, their interpretability remains a major challenge. This tutorial reviews key XAI techniques that provide insights into model predictions, allowing researchers to understand which spectral regions contribute to analytical outcomes. Detailed matrix-based formulations of these techniques are provided, along with illustrative examples. We conclude with a discussion of current limitations, best practices, and future research directions in explainable spectroscopy.
Zitieren
APA
Workman, J. (2025). Demystifying the Black Box: Making Machine Learning Models Explainable in Spectroscopy. Spectroscopy. https://doi.org/10.56530/spectroscopy.ps4569v3
Vancouver
Workman J. Demystifying the Black Box: Making Machine Learning Models Explainable in Spectroscopy. Spectroscopy. 2025. doi:10.56530/spectroscopy.ps4569v3
BibTeX
@article{Workman2025,
author = {Workman, Jerome},
title = {Demystifying the Black Box: Making Machine Learning Models Explainable in Spectroscopy},
journal = {Spectroscopy},
year = {2025},
doi = {10.56530/spectroscopy.ps4569v3}
}
EUVIMED