Decoratype-based materials informatics: Polaritype identification, convex hull DFT calculations, training data, and predicted compounds data

We introduce decoratypes as a structure taxonomy that classifies
compounds based on site decorations of specific structural prototypes.
Building on this foundation, a ferroelectric materials discovery framework
is developed, integrating decorotypes with an active learning approach to
accelerate exploration. In addition, six novel ferroelectric candidates
are predicted, including three strain-activated ferroelectrics and three
strain-activated hyperferroelectrics. These findings highlight the
potential of the decoratype taxonomy to enhance our understanding of
structure-driven material properties and facilitate the discovery of
promising yet underexplored regions of chemical space. This repository
contains density functional theory (DFT) convex hull calculations,
materials data used to train the polaritype-based active learning model,
and candidate compounds predicted by the recommender model.

我们提出装饰型（decoratypes）作为一种结构分类体系，基于特定结构原型的位点修饰特征对化合物进行分类。在此研究基础上，我们开发了一套铁电材料发现框架，将装饰型与主动学习（active learning）方法相结合，以加速材料探索进程。此外，我们共预测得到六种新型铁电候选材料，其中包含三种应变激活型铁电体与三种应变激活型超铁电体。上述研究成果彰显了装饰型分类体系的应用潜力，既有助于加深我们对结构驱动型材料性能的认知，也可推动发现化学空间中尚未被充分探索的高潜力区域。本数据集仓库包含密度泛函理论（DFT）凸包计算结果、用于训练基于极性型（polaritype）的主动学习模型的材料数据，以及由推荐模型预测得到的候选化合物。