Accelerated Discovery of Large Electrostrains in BaTiO3‐Based Piezoelectrics Using Active Learning. Issue 7 (8th January 2018)

• Record Type: Journal Article
• Authors: Yuan, Ruihao; Liu, Zhen; Balachandran, Prasanna V.; Xue, Deqing; Zhou, Yumei; Ding, Xiangdong; Sun, Jun; Xue, Dezhen; Lookman, Turab
• Is Part Of: Advanced materials. Volume 30:Issue 7(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-01-08
• Subjects: active learning -- electrostrain -- machine learning -- optimal experimental design -- piezoelectric; Materials -- Periodicals; Chemical vapor deposition -- Periodicals; 620.11
• DOI: 10.1002/adma.201702884
• Languages: English
• ISSNs: 0935-9648

Abstract

Abstract: A key challenge in guiding experiments toward materials with desired properties is to effectively navigate the vast search space comprising the chemistry and structure of allowed compounds. Here, it is shown how the use of machine learning coupled to optimization methods can accelerate the discovery of new Pb‐free BaTiO3 (BTO‐) based piezoelectrics with large electrostrains. By experimentally comparing several design strategies, it is shown that the approach balancing the trade‐off between exploration (using uncertainties) and exploitation (using only model predictions) gives the optimal criterion leading to the synthesis of the piezoelectric (Ba0.84 Ca0.16 )(Ti0.90 Zr0.07 Sn0.03 )O3 with the largest electrostrain of 0.23% in the BTO family. Using Landau theory and insights from density functional theory, it is uncovered that the observed large electrostrain is due to the presence of Sn, which allows for the ease of switching of tetragonal domains under an electric field. Abstract : Accelerated materials discovery requires guiding experimentalists toward finding materials with targeted properties in as few measurements as possible. This work experimentally compares design strategies to discover new piezoelectrics with large strains at low electric fields in the lead‐free barium titanate family. The procedure by which new compositions can be obtained in an iterative feedback loop using machine learning is demonstrated.