Convolutional neural networks driving thermally enhanced upconversion luminescence for temperature sensing: achieving high accuracy and robustness across a wide temperature range

Abstract

The accuracy of luminescence thermometry is seriously hindered by thermal-induced luminescence quenching as well as traditional single spectral parameter-based analytical methods, which rely on subjective experience of humans and fail to effectively utilize the spectral features. Herein, thermally intensified luminescence of Cr³⁺ is successfully achieved in Gd₃Ga₅O₁₂:Yb³⁺–Er³⁺–Cr³⁺ under 980 nm laser excitation and about 10-fold enhancement is observed at 853 K compared with that at 303 K. The reabsorption of Er³⁺ luminescence by Cr³⁺ and the phonon-assisted energy transfer from Er³⁺ to Cr³⁺ are responsible for the Cr³⁺ luminescence, and the latter is the key to the enhanced luminescence, which guarantees good signal-to-noise ratio of emissions at high temperatures. A convolutional neural network (CNN) is subsequently proposed to extract thermal information from the UC (upconversion) emissions, and the maximum error is just about 0.63 K in the temperature range of 303–853 K, along with an average error of only 0.15 K, much better than those obtained with conventional ratiometric approaches. Additionally, luminescence thermometry driven by CNNs can effectively resist the interference of background light and ensure measurement accuracy, further demonstrating the excellent robustness of the proposed thermometry strategy.