EUVIMEDEUVIMED entdecken
Crossref

Calibration Transfer of Deep Learning Models among Multiple Raman Spectrometers via Low-Rank Adaptation

Jiahui Lai, Miaomiao Li, Song Chen, Jia Long, Yi Chen, Hongmei Lu iD, Congming Zou, Zhimin Zhang iD

Analytical Chemistry · 09.09.2025 · 97 (35) · 19009-19018

DOI: 10.1021/acs.analchem.5c01846 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 26.08.2025. Verfasst von Jiahui Lai und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Chemistry and Chemical Engineering, Central South University, Hunan, Changsha 410083, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Natural Science Foundation of Hunan Province, National Natural Science Foundation of China, Yunnan Academy of Tobacco Agricultural Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While deep learning-enhanced Raman spectroscopy enables rapid sample analysis, model portability among spectrometers remains hindered by systematic interdevice variations. In this study, a Low-Rank Adaptation-based Calibration Transfer method (LoRA-CT) is proposed to perform parameter-efficient fine-tuning of deep learning models across spectrometers. By decomposing weight updates into low-rank matrices, LoRA-CT achieves superior calibration transfer with minimal samples, reducing trainable parameters by 600× compared to full parameter fine-tuning. Experimental validation across three data sets (solvent mixtures and blended oils) demonstrates that LoRA-CT with very few transfer samples significantly outperforms conventional methods. On the methanol mixture test set, it achieves R2 = 0.952 (vs 0.846 for piecewise direct standardization and 0.863 for full parameter fine-tuning) with lower RMSE (0.072 vs 0.117 and 0.114). The modular design enables dynamic switching between spectrometers through plug-and-play LoRA modules. This work establishes a new paradigm for resource-efficient spectroscopic model deployment, particularly advantageous for portable spectrometers and multi-instrument industrial systems where sample scarcity and computational constraints coexist.

Autor:innen und Institutionen

  • College of Chemistry and Chemical Engineering, Central South University, Hunan, Changsha 410083, China.
  • Yunnan Academy of Tobacco Agricultural Sciences, Kunming, Yunnan 650021, China.

ORCID-Profile: Hongmei Lu, Zhimin Zhang

Förderung

  • Natural Science Foundation of Hunan Province
  • National Natural Science Foundation of China
  • Yunnan Academy of Tobacco Agricultural Sciences
  • Yunnan Revitalization Talents Support Plan

Zitieren

APA

Lai, J., Li, M., Chen, S., Long, J., Chen, Y., Lu, H., Zou, C., & Zhang, Z. (2025). Calibration Transfer of Deep Learning Models among Multiple Raman Spectrometers via Low-Rank Adaptation. Analytical Chemistry, 97(35), 19009-19018. https://doi.org/10.1021/acs.analchem.5c01846

Vancouver

Lai J, Li M, Chen S, Long J, Chen Y, Lu H, et al. Calibration Transfer of Deep Learning Models among Multiple Raman Spectrometers via Low-Rank Adaptation. Analytical Chemistry. 2025;97(35):19009-19018. doi:10.1021/acs.analchem.5c01846

BibTeX
@article{Lai2025,
  author = {Lai, Jiahui and Li, Miaomiao and Chen, Song and Long, Jia and Chen, Yi and Lu, Hongmei and Zou, Congming and Zhang, Zhimin},
  title = {Calibration Transfer of Deep Learning Models among Multiple Raman Spectrometers via Low-Rank Adaptation},
  journal = {Analytical Chemistry},
  year = {2025},
  volume = {97},
  number = {35},
  pages = {19009--19018},
  doi = {10.1021/acs.analchem.5c01846}
}
Kostenlos starten →