Accelerated Discovery of Large Electrostrains in BaTiO₃‐Based Piezoelectrics Using Active Learning

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 BaTiO (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 (Ba Ca )(Ti Zr Sn )O 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.

A Critical Review of Machine Learning of Energy Materials

“…This strategy has helped the authors find the (Ba 0.5 Ca 0.5 )TiO 3 –Ba(Ti 0.7 Zr 0.3 )O 3 system with better MPB verticality but at the expense of poorer piezoelectric response d 33 . Similarly, Yuan et al have used Bayesian learning to lead the synthesis of the piezoelectric (Ba 0.84 Ca 0.16 )(Ti 0.90 Zr 0.07 Sn 0.03 )O 3 compound with largest electrostrain of 0.23% in the BaTiO 3 ‐based family and (Ba 0.85 Ca 0.15 ) (Ti 0.91 Zr 0.09 )O 3 compound with “optimal” d 33 of 362 pC N −1 . While these studies paved a way in accelerating the discovery of targeted piezoelectric materials, one objective optimization may sometimes lead to the expense of other properties not in the optimized targets or failure in reproducing the best available results …”

Discovery of Self-Assembling π-Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular Simulation

“…[40][41][42][43][44] In this manner, active learning predicts an optimal sequence in which to consider the molecular candidates in order to identify the optimal ones with minimal data collection effort. For this reason, active learning and allied approaches have been rapidly gaining traction in the materials discovery, engineering, and design communities, with these approaches being deployed, for example, in the experimental discovery of novel shape memory alloys, 45 piezoelectrics, 46 high glass transition polymers, 40 the computational discovery of drugs, 43 and magnetocaloric, superconducting, and thermoelectric materials. 41 Our primary goal is to efficiently identify members of the DXXX-OPV3-XXXD family that exhibit self-assembly into desired pseudo-1D nanoaggregates with good overlap between the π-conjugated cores and are thus most promising in displaying emergent optical and electronic functionality.…”

Efficient Optimization of the Performance of Mn2+‐Doped Kesterite Solar Cell: Machine Learning Aided Synthesis of High Efficient Cu2(Mn,Zn)Sn(S,Se)4 Solar Cells

“…The machine learning prediction can adaptively guide a next exploration of materials. The machine learning approach has been employed to couple tightly with experiments for the optimization of materials with targeted properties, such as the discovering shape memory alloys with high transformation temperatures, the synthesis of short polymer fiber materials, the design of piezoelectric oxide with large electrostrains, and so on. It has reduced the cost and time in the experimental designs significantly.…”