Luminescence Thermometry 2.0: Machine-Learning Temperature Read-Out with Luminescence of YOF: Yb3+, Er3+ Nanoparticles
- 1Centre of Excellence for Photoconversion, Vinča Institute of Nuclear Sciences—National Institute of the Republic of Serbia, University of Belgrade, P.O. Box 522, 11001 Belgrade, Serbia
- 2National Institute of Research and Development for Electrochemistry and Condensed Matter, INCEMC, Str. Dr. A. Păunescu Podeanu Nr.144, 300569 Timisoara, Romania
Abstract
Here, we evaluate a full-spectrum, data-driven readout framework, termed Luminescence Thermometry 2.0, in which normalized emission spectra are used directly as inputs to temperature regression. We benchmark this approach against conventional luminescence-intensity ratio thermometry using the same experimental dataset obtained from the upconversion and downshifting emissions of Er3+,Yb3+-co-doped yttrium oxyfluoride nanoparticles. Relative to the best-performing conventional LIR calibration, full-spectrum regression reduces the absolute prediction bias by up to approximately 2.5-fold and the prediction spread by 24% for visible green upconversion. For near-infrared emission, the corresponding reductions reach approximately 2.2-fold and 8.6-fold, respectively. The approach reduces feature-selection bias and exploits temperature-encoded information that conventional analysis discards. Shapley additive explanations for the best-performing Gaussian process regression model identify the Er3+ spectral regions that dominate temperature prediction, linking the improved performance to physically meaningful emission features. These results demonstrate improved temperature readout using full-spectrum regression for YOF:Er3+/Yb3+ under the investigated conditions. Matched synthetic-background tests showed that training-set augmentation reduced background-induced set-point bias, with effects that depended on the regression method and normalization.
Related
- Sensitized near-infrared luminescence in sulfur-coordinated lanthanide complexes for machine learning-enhanced thermometry
- Multi-fidelity machine learning interatomic potential for the energetics and finite temperature structure of Pt surfaces and nanoparticles
- Multi-mechanism luminescence and negative thermal quenching in Yb ³⁺ /Nd ³⁺ co-doped fiber microspheres toward optical thermometry
- Exploring calibration-free luminescence thermometry with Mn ⁴⁺ anti-Stokes/Stokes emission
- Growth driven phase transitions in Zinc Oxide nanoparticles through machine-learning assisted simulations
BibTeX
@article{ristic2026luminescence,
title = {{Luminescence Thermometry 2.0: Machine-Learning Temperature Read-Out with Luminescence of YOF: Yb3+, Er3+ Nanoparticles}},
author = {Zoran Ristić and Jovana Periša and Aleksandar Ćirić and Milica Maričić and Anđela Rajčić and Tamara Gavrilović and Željka Antić and Miroslav D. Dramićanin},
journal = {Nanomaterials (Basel, Switzerland)},
year = {2026},
month = sep,
doi = {10.3390/nano16191238},
url = {https://europepmc.org/article/PMC/PMC13667202},
note = {CC BY},
}
RIS
TY - JOUR
TI - Luminescence Thermometry 2.0: Machine-Learning Temperature Read-Out with Luminescence of YOF: Yb3+, Er3+ Nanoparticles
AU - Zoran Ristić
AU - Jovana Periša
AU - Aleksandar Ćirić
AU - Milica Maričić
AU - Anđela Rajčić
AU - Tamara Gavrilović
AU - Željka Antić
AU - Miroslav D. Dramićanin
PY - 2026
DA - 2026/09/30
JO - Nanomaterials (Basel, Switzerland)
DO - 10.3390/nano16191238
UR - https://europepmc.org/article/PMC/PMC13667202
AB - Here, we evaluate a full-spectrum, data-driven readout framework, termed Luminescence Thermometry 2.0, in which normalized emission spectra are used directly as inputs to temperature regression. We benchmark this approach against conventional luminescence-intensity ratio thermometry using the same experimental dataset obtained from the upconversion and downshifting emissions of Er3+,Yb3+-co-doped yttrium oxyfluoride nanoparticles. Relative to the best-performing conventional LIR calibration, full-spectrum regression reduces the absolute prediction bias by up to approximately 2.5-fold and the prediction spread by 24% for visible green upconversion. For near-infrared emission, the corresponding reductions reach approximately 2.2-fold and 8.6-fold, respectively. The approach reduces feature-selection bias and exploits temperature-encoded information that conventional analysis discards. Shapley additive explanations for the best-performing Gaussian process regression model identify the Er3+ spectral regions that dominate temperature prediction, linking the improved performance to physically meaningful emission features. These results demonstrate improved temperature readout using full-spectrum regression for YOF:Er3+/Yb3+ under the investigated conditions. Matched synthetic-background tests showed that training-set augmentation reduced background-induced set-point bias, with effects that depended on the regression method and normalization.
SN - 2079-4991
ER -