Discovery of wurtzite solid solutions with enhanced piezoelectric response using machine learning

This is the authors' abstract. We don't add key points for this paper.

While many piezoelectric materials are known, there is still great potential to improve on the figures of merit of existing materials through compositional doping and forming solid solutions. Specifically, it has been shown that doping and alloying wurtzite-structured materials can improve the piezoelectric response; however, a vast compositional space has remained unexplored. In this work, we apply a multilevel screening protocol combining machine learning, chemical intuition, and thermodynamics to systematically discover dopant combinations in the wurtzite material space that improve the desired piezoelectric response. Through our protocol, we use computationally inexpensive screening calculations to consider more than 3000 possible ternary wurtzite solid solutions from nine different wurtzite base systems: AlN, BeO, CdS, CdSe, GaN, ZnO, ZnS, ZnSe, and AgI. Finally, based on thermodynamic analysis and explicit piezoelectric response calculations, we predict 11 materials with improved piezoelectric response, due to the incorporation of electropositive dopants.