Accelerating the combinatorial optimization process for phosphor materials by Bayesian optimization

Abstract

We investigated the acceleration of the combinatorial optimization process for phosphor materials using a machine learning method based on Bayesian optimization. Combinatorial pulsed laser deposition can be used to create a library of single-crystalline films with varying chemical compositions. However, the systematic evaluation of the target functional properties requires a long measurement time, impairing rapid material screening. In this study, Bayesian optimization was applied to sequential measurements of the photoluminescence (PL) properties of EuxY2−xO3 films to accelerate the combinatorial high-throughput evaluation. Although a conventional combinatorial PL evaluation of a binary composition-gradient film is composed of a sequential measurement of 80 points, the autonomous PL mapping technique based on Bayesian optimization drastically reduced the measurement points to only six points, demonstrating that the optimum chemical composition can be identified in a shorter experimental time.

The use of He buffer gas for moderating the plume kinetic energy during Nd:YAG-PLD growth of EuxY2−xO3 phosphor films

“…35,36 An Y 2 O 3 ceramic target was ablated with the fourth harmonic (266 nm) pulses from a Nd: YAG laser (LOTIS LS-2145 N/4) at a pulse rate of 10 Hz and a fluence of 2.3 J/cm 2 . 35,37,38 During film growth, the substrate holder temperature was maintained at 600 °C with a laser heating system (Pascal Ltd. PHE-DL-10) based on an infrared semiconductor laser operating at 808 nm. 14,39 For buffered growth experiments, He gas was mixed with oxygen at a volume ratio of He:O 2 = 1000:1 with a mass flow controller and introduced into the PLD chamber via a variable leak valve.…”

“…The synthesis parameters, such as the Nd:YAG laser energy and the growth temperature, were optimized in a previous study on Y 2 O 3 film growth. 35,37,38 To investigate the He buffer gas effect on the phosphor properties, Eu x Y 2−x O 3 composition-gradient films were deposited on SrTiO 3 (001) substrates using combinatorial PLD (Pascal Ltd. MC-LMBE). [40][41][42][43] A schematic illustration of the combinatorial PLD is shown in Fig.…”