基于不同机器学习算法的钙钛矿材料性能预测  

Performance prediction of perovskite materials based on different machine learning algorithms

作　　者：郑伟达 张惠然 胡红青[3] 刘尧 李盛洲 丁广太 张金仓 ZHENG Wei-da;ZHANG Hui-ran;HU Hong-qing;LIU Yao;LI Sheng-zhou;DING Guang-tai;ZHANG Jin-cang(College of Sciences, Shanghai University, Shanghai 200444, China;School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;School of Materials Science and Engineering, Shanghai University, Shanghai 200444, China)

机构地区：[1]上海大学材料基因组工程研究院,上海200444 [2]上海大学理学院,上海200444 [3]上海大学计算工程与科学学院,上海200444

出　　处：《中国有色金属学报》2019年第4期803-809,共7页The Chinese Journal of Nonferrous Metals

基　　金：国家重点研发计划资助项目(2016YFB0700502)~~

摘　　要：钙钛矿材料由于在各领域具有广泛的应用前景而备受材料学家的关注,对其各种物理化学性能的研究一直是材料领域研究的热点。本文建立随机森林(Randomforest,RF)、岭回归(Ridgeregression,RR)、以及基于径向基核函数和线性核函数的支持向量回归(Support vector regression,SVR)等4种机器学习算法的预测模型,对钙钛矿材料数据集中的密度、形成能、带隙、晶体体积等4种性能参数进行预测。结果表明:RF方法可以对钙钛矿材料的密度、带隙性能进行有效预测;RR方法可以实现对密度性能的预测;线性核函数的SVR方法可以实现对形成能性能的预测。该研究表明,不同的机器学习算法对数据样本分布的敏感程度不同,因此针对不同的性能参数预测需要选择不同方法。Due to the potential application in various fields, there is great opportunity for further research into the basic physics and chemistry around perovskites. In this work, four machine learning algorithms prediction models have been built. They are random forest(RF), ridge regression(RR), and support vector regression(SVR) based on the radial basis kernel function and linear kernel function. They are used to predict the density, formation energy, band gap, and the crystal volume of the perovskite materials. The experimental results show that the RF method can effectively predict the density and band gap of perovskite materials. The RR method can realize the prediction of density performance. The SVR method of linear kernel function can realize the prediction of the performance. This study shows that different machine learning algorithms have different sensitivity to the distribution of data set samples, so different methods should be selected to predict different performance parameters.

关 键 词：钙钛矿材料 机器学习 性能预测 算法选择 

分 类 号：TB34[一般工业技术—材料科学与工程]