Time resolved study of temperature sensing using Gd2O3:Er,Yb: deep learning approach

This paper examines the potential applications of machine learning algorithms in the analysis of optical spectra from Gd2O3:Er,Yb thermophosphor. The material was synthesized using the solution combustion method. For data acquisition, we employed pulsed laser diode excitation at 980 nm and utilized a streak camera with a spectrograph to obtain time-resolved spectral data of the optical emission from Gd2O3:Er,Yb. To ensure data consistency and facilitate visualization, we employed principal component analysis and Uniform Manifold Approximation and Projection clustering. Our findings demonstrate that, instead of the conventional approach of identifying spectral peaks and calculating intensity ratios, it is feasible to train computer software to recognize time-resolved spectra associated with different temperatures of the thermophosphor. Through our analysis, we have successfully devised a technique for remote temperature estimation by leveraging deep learning artificial neural networks.

Automated summary

This paper explores the potential applications of machine learning algorithms in the analysis of optical spectra from Gd2O3:Er,Yb thermophosphor. By training computer software to recognize time-resolved spectra associated with different temperatures, remote temperature estimation can be achieved using deep learning artificial neural networks.