The piezoelectric performance serves as the basis for the applications of piezoelectric ceramics. The ability to rapidly and accurately predict the piezoelectric coefficient (d₃₃) is of much practical importance for exploring high-performance piezoelectric ceramics. In this work, a data-driven approach combining feature engineering, statistical learning, machine learning (ML), experimental design, and synthesis is trialed to investigate its accuracy in predicting d₃₃ of potassium–sodium–niobate ((K,Na)NbO₃, KNN)-based ceramics. The atomic radius (AR), valence electron distance (DV) (Schubert), Martynov–Batsanov electronegativity (EN-MB), and absolute electronegativity (EN) are summarized as the four most representative features in describing d₃₃ out of all 27 possible features for the piezoelectric ceramics. These four features contribute greatly to regression learning for predicting d₃₃ and classification learning for distinguishing polymorphic phase boundary (PPB). The ML method developed in this work exhibits a high accuracy in predicting d₃₃ of the piezoelectric ceramics. An example of KNN combined with 6 mol% LiNbO₃ demonstrates d₃₃ of 184 pC/N, which is highly consistent with the predicted result. This work proposes a novel feature-oriented guideline for accelerating the design of piezoelectric ceramic systems with large d₃₃, which is expected to be widely used in other functional materials.

The application of piezoelectric ceramics at high temperature is limited because they can't have both high piezoelectric coefficient and high Curie temperature. While, BiScO₃–PbTiO₃-based piezoelectric ceramics possessing high Curie temperature and piezoelectric properties simultaneously have drawn increasing attention due to their potential applications at high temperature. Here, we reported a novel compositional design of (1-x)[0.36BiScO₃-0.64PbTiO₃]-xBi(Sn_1/3Nb_2/3)O₃ (abbreviated as BS-PT-xBSN). BS-PT-xBSN ceramic samples were synthesized by conventional solid state reaction method. According to the ternary phase diagram of BS-PT-xBSN ceramics brought up in this work, the morphotropic phase boundaries (MPB) were confirmed, which is located in the vicinity of x = 0.02. It canbe identified that the x = 0.02 sample near MPB has the optimal electric performance which are giant piezoelectric coefficient (d₃₃ ~ 450 pC/N, higher 18 % than undoped samples) and high Curie temperature (T_c ~ 368 ℃) as well as large remant polarization (P_r ~ 46.6 μC/cm²). In addition, the variation of P_r is 3 % in the temperature range of 30–180 ℃ and the depolarization temperature of x = 0.02 ceramics is about 280 ℃. Structural analysis such as in-situ PFM and TEM confirms that giant piezoelectricity and depolarization temperature are attributed to the appearance of nano-domain and complexity of domains as well as the stable domain configuration. This work not only reveal the high potential of BS-PT-xBSN for high-temperature piezoelectric applications but also open up a feasible approach to design new high-temperature piezoelectric ceramics.