An interpretable machine learning strategy for pursuing high piezoelectric coefficients in (K0.5Na0.5)NbO3-based ceramics

Abstract Perovskite-type lead-free piezoelectric ceramics allow access to illustrious piezoelectric coefficients ( d 33 ) through intricate composition design and experimental modulation. Developing a swift and accurate technology for identifying (K, Na)NbO 3 (KNN)-based ceramic compositions with high d 33 in exceedingly large “compositional” space will establish an innovative research paradigm surpassing the traditional empirical trial-and-error method. Herein, we demonstrate an interpretable machine learning (ML) framework for quick evaluation of KNN-based ceramics with high d 33 based on data from published literature. Specifically, a thorough feature construction was carried out from the global and local dimensions to establish tree regression models with d 33 as the target property. Subsequently, the feature-property mapping rules of KNN-based piezoelectric ceramics are further optimized through feature screening. To intuitively understand the correlation mechanisms between ML regression targets and features, the sure independence screening and sparsifying operator (SISSO) method was employed to extract the essential descriptors to explain d 33 . A straightforward descriptor, $${\text{e}}^{({{NM}}_{\text{B}}-{{MV}}_{\text{B}})}\cdot {ST}/{(I{D}_{\text{A}})}^{2}$$ e ( NM B − MV B ) ⋅ ST / ( I D A ) 2 , consisting of only four easily accessible parameters, can accelerate the evaluation of a series of novel KNN-based ceramics with high d 33 while exhibiting strong theoretical interpretability. This work not only provides a tool for the rapid discovery of high piezoelectric performance in KNN-based ceramics but also offers a data-driven route for the design of property descriptors in perovskites.