Accelerated Search for BaTiO3‐Based Ceramics with Large Energy Storage at Low Fields Using Machine Learning and Experimental Design. Issue 21 (2nd September 2019)

• Record Type: Journal Article
• Authors: Yuan, Ruihao; Tian, Yuan; Xue, Dezhen; Xue, Deqing; Zhou, Yumei; Ding, Xiangdong; Sun, Jun; Lookman, Turab
• Is Part Of: Advanced science. Volume 6:Issue 21(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-09-02
• Subjects: Bayesian optimization -- ceramics -- energy storage -- machine learning -- optimal experimental design; Science -- Periodicals; 505
• DOI: 10.1002/advs.201901395
• Languages: English
• ISSNs: 2198-3844

Abstract

Abstract: The problem that is considered is that of maximizing the energy storage density of Pb‐free BaTiO3 ‐based dielectrics at low electric fields. It is demonstrated that how varying the size of the combinatorial search space influences the efficiency of material discovery by comparing the performance of two machine learning based approaches where different levels of physical insights are involved. It is started with physics intuition to provide guiding principles to find better performers lying in the crossover region in the composition–temperature phase diagram between the ferroelectric phase and relaxor ferroelectric phase. Such an approach is limiting for multidopant solid solutions and motivates the use of two data‐driven machine learning and design strategies with a feedback loop to experiments. Strategy I considers learning and property prediction on all the compounds, and strategy II learns to preselect compounds in the crossover region on which prediction is carried out. By performing only two active learning loops via strategy II, the compound (Ba0.86 Ca0.14 )(Ti0.79 Zr0.11 Hf0.10 )O3 is synthesized with the largest energy storage density ≈73 mJ cm −3 at a field of 20 kV cm −1, and an insight into the relative performance of the strategies using varying levels of knowledge is provided. Abstract : Discovery of new materials with targeted properties is often a "needle in the haystack" problem. The size of the "haystack" can be effectively narrowed down by domain expert knowledge, leaving only potential materials with better properties. The searching process by data‐driven machine learning and an optimization strategy within such a preselected "haystack" is further accelerated.