资讯：可解释KNN陶瓷高压电系数：机器学习就能又快又好？

针对压电陶瓷的无铅化人们投入了大量的时间和精力，通过繁琐和复杂的组分调控，(K, Na)NbO₃ (KNN)基陶瓷压电系数逐年突破。一方面，传统经验试错的研究范式存在耗时耗材的局限性，另一方面，过去积累的KNN基陶瓷压电系数(d₃₃)相关的文献数据极具挖掘价值。

来自福州大学的吴啸副教授、萨百晟教授和北京航空航天大学的孙志梅教授团队，究构建了一个d₃₃描述符开发框架，提出一个仅包含4个易于获取参数的描述符用于预测d₃₃，并能解释KNN基陶瓷多相共存引发的高d₃₃机理。

他们通过耦合特征工程、机器学习回归和SISSO算法，从244篇已发表的1113个数据点中建立了KNN基陶瓷化学成分与d₃₃的回归映射。该研究根据ABO₃型钙钛矿的元素位置构型，分别从全局和局部进行特征构造，然后利用Pearson相关性筛选、特征重要性和特征穷尽等方法对关键特征进行筛选，最优的极端随机树回归模型的留一交叉验证误差最低至±49 pC/N。

作者将最优的特征集用于SISSO描述符搜索，得到了一个和d₃₃有直观变化趋势的描述符，同时该描述符数值还与KNN基陶瓷相界具备映射关系，即描述符值在较小区间的化学成分更容易获得高压电系数。这一方法在最新发表的63 个KNN基陶瓷高压电系数组分中得到验证。

Fig. 4 Descriptor mapping.

该研究在KNN基陶瓷中建立了d₃₃-组分-相界三者的数学映射模型，为提高钙钛矿的性能提供了一种高度直观和指导性的途径，克服了传统机器学习模型低可信度和难解释的问题。相关论文近期发布于npj Computational Materials 9: 229 (2023)。手机阅读原文，请点击本文底部左下角“阅读原文”，进入后亦可下载全文PDF文件。

Editorial Summary

People have invested a lot of time and energy in making piezoelectric ceramics lead-free. Through cumbersome and complicated composition control, the piezoelectric coefficient of KNN-based ceramics has been breaking through year by year.On the one hand, the traditional empirical trial-and-error research paradigm has the limitation of time-consuming consumables. On the other hand, the literature data related to the piezoelectric coefficient (d₃₃) of KNN-based ceramics accumulated in the past is extremely valuable to explore. This study constructed a d₃₃ descriptor development framework and proposed a descriptor containing only four easily accessible parameters:  is used to predict d₃₃. This descriptor can also explain the high d₃₃mechanism caused by the coexistence of multi-phase KNN-based ceramics. 

The team of Prof. Wu Xiao and Prof. Sa Baisheng from Fuzhou University and Prof. Sun Zhimei from Beihang University established a regression mapping of the chemical composition of KNN-based ceramics with d₃₃from 1113 data points in 244 published articles by coupling feature engineering, machine learning regression and the SISSO algorithm. This study constructed global and local features based on the element position configuration of ABO₃-type perovskites, and then used methods such as Pearson correlation screening, feature importance, and feature exhaustion to screen key features. The optimal extreme random tree regression model has a leave-one-out cross-validation error as low as ±49pC/N.The author used the optimal feature set for the SISSO descriptor search and obtained a descriptor that has an intuitive changing trend with d₃₃.At the same time, the descriptor value also has a mapping relationship with the KNN-based ceramic phase boundary, that is, chemical compositions with descriptor values in a smaller range are more likely to obtain high d₃₃.This method has been verified in the newly published 63 KNN-based ceramic high piezoelectric coefficient compositions. This study established a mathematical mapping model of the d₃₃-composition-phase boundary in KNN-based ceramics, providing a highly intuitive and instructive way to improve the performance of perovskites, and overcoming the low reliability and difficult interpretation problems of traditional machine learning models. This article was recently published in npj Computational Materials 9, 229 (2023).

原文Abstract及其翻译

Bowen Ma, Xiao Wu, Chunlin Zhao, Cong Lin, Min Gao, Baisheng Sa & Zhimei Sun

Abstract Perovskite-type lead-free piezoelectric ceramics allow access to illustrious piezoelectric coefficients (d₃₃) through intricate composition design and experimental modulation. Developing a swift and accurate technology for identifying (K, Na)NbO₃ (KNN)-based ceramic compositions with high d₃₃in 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 d₃₃ 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 d₃₃ 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 d₃₃. A straightforward descriptor, , consisting of only four easily accessible parameters, can accelerate the evaluation of a series of novel KNN-based ceramics with high d₃₃while 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.

摘要 钙钛矿型无铅压电陶瓷通过复杂的成分设计和实验调制，可以获得出色的压电系数(d₃₃)。开发一种快速而准确的技术，用于在极大的“组分”空间中识别具有高d₃₃的(K, Na)NbO₃ (KNN)基陶瓷组分，将摆脱传统经验试错方法耗时耗力的局限性，建立一种创新研究范式。在此，本论文展示了一个可解释的机器学习(ML)框架，基于已发表文献数据来快速评估具有高d₃₃的KNN基陶瓷：从全局和局部两个维度进行全面的特征构建，建立以d₃₃为目标属性的树回归模型；随后，通过特征筛选进一步优化了KNN基压电陶瓷的特征-性能映射规则。为了直观地理解ML回归目标与特征之间的关联机制，我们随后采用确定独立性筛选和稀疏化算子(SISSO)方法提取解释d₃₃的基本描述符。最终获得一个易懂且直接的描述符：，仅由四个易获得的参数组成，可以快速对一系列高d₃₃的KNN基陶瓷进行评估，展现出较强的理论可解释性。这项工作不仅为快速发现高压电性能KNN基陶瓷提供了一种方法，而且为提高钙钛矿的性能提供了一种高度直观和指导性的途径，克服了传统机器学习模型低可信度和难解释的问题。