Phosphorescent Material Search Using a Combination of High-Throughput Evaluation and Machine Learning

Abstract

High-throughput experiments including combinatorial chemistry are useful for generating large amounts of data within a short period of time. Machine learning can be used to predict the regularity of a response variable using a statistical model of a data set. Because a combination of these methods can accelerate the material development, we applied such a combination to a search of semiconducting thin films prepared on an Eu and Dy codoped SrAl2O4-based phosphorescent material to improve the lifetime of its afterglow. Oxide targets MgO, GeO2, Ga2O3, ZnO, Bi2O3, Ta2O5, TiO2, and Y2O3 were deposited to form a thin film on a SrAl2O4 substrate as a combinatorial library with a systematical change in these ratios. The sample was calcined under several conditions, and a data set of 800 examples was obtained using a high-throughput evaluation. The 800 examples were then randomly divided into training and test data sets. The lifetime of the afterglow was interpolated through machine learning using the film thickness of each element and the calcined condition of the training data set as explanatory variables. The accuracy of the interpolation was evaluated using a correlation coefficient and the root mean squared error of the predicted values with respect to the experimental values of the test data set. As a result, it was found that a MgO thin film is effective at improving the lifetime of the afterglow and that its optimum condition is a film thickness of approximately 100 nm with calcination at 400–600 °C in air.

Optimization of Material Composition of Li‐Intercalated Metal–Organic Framework Electrodes Using a Combination of Experiments and Machine Learning of X‐Ray Diffraction Patterns

“…[7] For instance, our search for persistent phosphorescent materials with complicated structures made use of combinatorial chemistry and machine learning for high throughput evaluation. [8] In this study, we apply a combination of experiments and machine learning to a search for negative electrode materials for Li-ion batteries.…”

Emerging Ultraviolet Persistent Luminescent Materials

“…[117] The strategies through artificial intelligence can also be used to design PersL materials. [118] The compositions of PersL materials are tuned and PL and PersL are optimized. Up to now, most attempts are on Eu-doped MAl 2 O 4 (M = Ca, Sr Mg, Ba, etc.)…”

“…[119][120][121] For such a single system, the constructed prediction model of the lifetime using ML techniques seems reliable. [118] However, in terms of other PersL materials, very little information is available. ML-aided screening, design, and prediction of UV PersL materials can be one of the exploring directions.…”

Optimized Multimetal Sensitized Phosphor for Enhanced Red Up-Conversion Luminescence by Machine Learning

“…Thus, it is important to evaluate the optimization accuracy and effect to show whether the system is steady to produce the same phosphors when the composition is fixed. In the combinatorial optimization, machine learning, signal processing, adaptive control, and artificial life fields, the support vector machine (SVM) is one of the most robust and accurate methods among all the well-known data mining algorithms . The SVM belongs to the supervised learning binary classification algorithm and can support linear and nonlinear classification.…”

“…In the combinatorial optimization, machine learning, signal processing, adaptive control, and artificial life fields, the support vector machine (SVM) is one of the most robust and accurate methods among all the well-known data mining algorithms. 56 The SVM belongs to the supervised learning binary classification algorithm and can support linear and nonlinear classification. The basic model of SVM is to find the best separating hyperplane in the feature space to maximize the positive and negative sample intervals on the training set.…”