Improving the High Pressure Sensing Characteristics of Y2MoO6:Eu3 Using Machine Learning Approach+

This study investigates the high-pressure luminescence characteristics of Y2MoO6:Eu3+, a material prepared by a self-initiated and self-sustained reaction. Using a 405 nm laser diode and an Ocean optics spectrometer, we acquired emission spectra under varying pressures. While the pressure-dependent curve, based on the intensities of two key peaks, clearly showed a crystal phase transition, the resulting non-unique relationship between pressure and peak intensity hindered its use for precise sensing. We address this limitation by introducing a machine learning approach. Our method uses Uniform Manifold Approximation and Projection (UMAP) for initial data visualization and a deep neural network to accurately estimate pressure from the full luminescence spectrum.