Search for ABO₃ Type Ferroelectric Perovskites with Targeted Multi-Properties by Machine Learning Strategies

Abstract

Ferroelectric perovskites are one of the most promising functional materials due to the pyroelectric and piezoelectric effect. In the practical applications of ferroelectric perovskites, it is often necessary to meet the requirements of multiple properties. In this work, a multiproperties machine learning strategy was proposed to accelerate the discovery and design of new ferroelectric ABO3-type perovskites. First, a classification model was constructed with data collected from publications to distinguish ferroelectric and nonferroelectric perovskites. The classification accuracies of LOOCV and the test set are 87.29% and 86.21%, respectively. Then, two machine learning strategies, Machine-Learning Workflow and SISSO, were used to construct the regression models to predict the specific surface area (SSA), band gap (E g), Curie temperature (T c), and dielectric loss (tan δ) of ABO3-type perovskites. The correlation coefficients of LOOCV in the optimal models for SSA, E g, and T c are 0.935, 0.891, and 0.971, respectively, while the correlation coefficient of the predicted and experimental values of the SISSO model for tan δ prediction could reach 0.913. On the basis of the models, 20 ABO3 ferroelectric perovskites with three different application prospects were screened out with the required properties, which could be explained by the patterns between the important descriptors and the properties by using SHAP. Furthermore, the constructed models were developed into web servers for the researchers to accelerate the rational design and discovery of ABO3 ferroelectric perovskites with desired multiple properties.

New Opportunity: Machine Learning for Polymer Materials Design and Discovery

“…Figure illustrates the flow chart of ML process used for polymer materials design and discovery, which contains data preparation, feature selection, model selection, model evaluation, and model application. [ 84–86 ]…”

“…Figure 5 illustrates the flow chart of ML process used for polymer materials design and discovery, which contains data preparation, feature selection, model selection, model evaluation, and model application. [84][85][86] The quality of data is the cornerstone of the ML model, which directly influence the performance and applications of the model. Therefore, it is quite important to collect reliable data before ML modelling.…”

Prediction of dielectric constants of ABO3-type perovskites using machine learning and first-principles calculations

“…4 Perovskite materials have attracted increasing interest because of their excellent properties 5 for use in solar cells, 6,7 fuel cells, 8,9 catalysts, 10,11 and optoelectronic devices. 12,13 In particular, ABO 3 perovskite compounds are widely used because of their controllable structures with outstanding stabilities and low synthesis prices. They can be used in numerous applications, such as photocatalysts, sensors, and capacitors.…”

“…They can be used in numerous applications, such as photocatalysts, sensors, and capacitors. [14][15][16][17][18] They are also widely used as a central component in multi-layer ceramic capacitors (MLCCs) to process data and protect electric circuits. 19 For example, BaTiO 3 , one of the most representative ABO 3 -type perovskites with a high dielectric constant, has been commercialized in the MLCC industry.…”

Machine Learning-Assisted Design of Yttria-Stabilized Zirconia Thermal Barrier Coatings with High Bonding Strength

“…Machine learning is the core of artificial intelligence with the ability to reorganize the existing knowledge structure and figure out implicit relationships, and it has been applied in many areas such as medical treatment, finance, materials, and chemistry with significant progress. − In materials design, machine learning has occupied an important part in the development and design of alloys, polymers, perovskites, and other materials by virtue of the advantages of obtaining performance and trends from available data without knowing the underlying physical mechanism. − Yang et al used machine learning combined with high-throughput screening and pattern recognition back-projection technology to break the upper limit of the hardness of the existing high-entropy alloys and designed the hardness of Co 18 Cr 7 Fe 35 Ni 5 V 35 to be 1148 HV, which is 24.8% higher than the hardness of the alloy with the highest hardness in the original data set. Chen et al used a step-by-step screening method of the packaging algorithm to screen out a subset of features for ridge regression, XGBoost, and support vector regression (SVR) models and integrated the three models to design low-melting-point alloys.…”