A Machine Learning‐Assisted Approach to a Rapid and Reliable Screening for Mechanically Stable Perovskite‐Based Materials

Abstract

The present work is designed to discover new perovskite-based materials, which are expected to show high mechanical stability during their applications, using machine learning (ML) techniques, and based on the Pugh's criterion for distinguishing brittle and ductile behaviors. For this purpose, ML models to predict the moduli of materials, bulk (B) and shear (G), are built using their crystal structure and composition information. The ML process is initiated with the information of 5663 compounds, including composition, crystal structure and moduli, as listed in AFLOW database. Following a procedure of data characteristics, feature generation, feature processing, training, and testing, the ML models are constructed with acceptable accuracy (tenfold cross-validation R 2 score of 0.90 and 0.89 for B and G, respectively). The validation process of the models, which is conducted using the corresponding density functional theory calculations, reveals that these models are reliable to be employed in a largescale screening process. Indeed, the B-and G-based ML models are incorporated in a screening process, and this is also conjugated with other screening criterions, to find out thermodynamically stable and formable perovskite-based materials with improved mechanical performance.

Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects

“…Nowadays, the applications of ML in PSCCM are mainly focused on three directions, namely, the screening of highthroughput materials, the prediction of target properties, and the guidance of experiments. [251,252] ML mainly plays a role in accelerating and inspiring the design of PSCCM. Nonetheless, the combinations of ML and PSCCM are still in a rudimentary and wildly growing stage with numerous difficulties and challenges due to the unsuitable applications of ML technologies, the complex properties of PSCCM.…”

Machine learning in energy chemistry: introduction, challenges and perspectives

“…Jaafreh et al investigated the mechanical strength of perovskite-based materials using the AdaBoost algorithm with the volume and shear quantities of the elastic modulus and its scaling criterion (satisfying G/B smaller than 0.57 for ductility at room temperature (RT)). Based on the model, they identified about 770 perovskites with mechanical strength 150 . Howard et al proposed a reap-rest-recovery (3R) cycle machine learning framework to avoid permanent failure of perovskites due to exposure to water vapor and oxidation 151 .…”

“…Based on the model, they identified about 770 perovskites with mechanical strength. 148 Howard et al proposed a reap-rest-recovery (3R) cycle machine learning framework to avoid permanent failure of perovskites due to exposure to water vapor and oxidation. 149 Due to the complexity of factors such as device stability, more effective models with interpretability still need to be developed for evaluation to help find a suitable device.…”

Interpretable machine learning-assisted screening of perovskite oxides

“…This is achieved by the calculation of their energy above the convex hull (E h ). [16][17][18][19][20] Basically, E h is calculated with the energy difference between the perovskite oxides and the convex hull which is constructed by linking phases or linear combination of phases with the lowest formation energy using tie lines at specic compositions. 17,21 It can be calculated by eqn (3) and (4): 17…”

“…This is achieved by the calculation of their energy above the convex hull ( E h ). 16–20 Basically, E h is calculated with the energy difference between the perovskite oxides and the convex hull which is constructed by linking phases or linear combination of phases with the lowest formation energy using tie lines at specific compositions. 17,21 It can be calculated by eqn (3) and (4): 17 where and E (ABO 3 ) are the formation energy and total energy of the ABO 3 compound, respectively, μ A , μ B and μ O are the chemical potentials of A, B and O, respectively, and and H f are the energy above the convex hull and the convex hull energy of the ABO 3 compound, respectively.…”