Journal of Advanced Dielectrics, Volume. 12, Issue 3, 2250005(2022)
Experimental search for high-performance ferroelectric tunnel junctions guided by machine learning
Jingjing Rao1,2, Zhen Fan1,2、*, Qicheng Huang1, Yongjian Luo1, Xingmin Zhang3, Haizhong Guo4, Xiaobing Yan5, Guo Tian1, Deyang Chen1, Zhipeng Hou1, Minghui Qin1, Min Zeng1, Xubing Lu1, Guofu Zhou1,2, Xingsen Gao1, and Jun-Ming Liu6
Author Affiliations
1Institute for Advanced Materials, South China Normal University, Guangzhou 510006, P. R. China2Guangdong Provincial Key Laboratory of Optical Information Materials and Technology, South China Normal University, Guangzhou 510006, P. R. China3Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201204, P. R. China4School of Physics and Microelectronics, Zhengzhou University, Zhengzhou 450001, P. R. China5Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province, Hebei University, Baoding 071002, P. R. China6Laboratory of Solid State Microstructures and Innovation Center of Advanced, Nanjing 210093, P. R. Chinashow less
Ferroelectric tunnel junction (FTJ) has attracted considerable attention for its potential applications in nonvolatile memory and neuromorphic computing. However, the experimental exploration of FTJs with high ON/OFF ratios is a challenging task due to the vast search space comprising of ferroelectric and electrode materials, fabrication methods and conditions and so on. Here, machine learning (ML) is demonstrated to be an effective tool to guide the experimental search of FTJs with high ON/OFF ratios. A dataset consisting of 152 FTJ samples with nine features and one target attribute (i.e., ON/OFF ratio) is established for ML modeling. Among various ML models, the gradient boosting classification model achieves the highest prediction accuracy. Combining the feature importance analysis based on this model with the association rule mining, it is extracted that the utilizations of {graphene/graphite (Gra) (top), LaNiO3 (LNO) (bottom)} and {Gra (top), CaCeMnO3 (CCMO) (bottom)} electrode pairs are likely to result in high ON/OFF ratios in FTJs. Moreover, two previously unexplored FTJs: Gra/BaTiO3 (BTO)/LNO and Gra/BTO/CCMO, are predicted to achieve ON/OFF ratios higher than 1000. Guided by the ML predictions, the Gra/BTO/LNO and Gra/BTO/CCMO FTJs are experimentally fabricated, which unsurprisingly exhibit 1000 ON/OFF ratios (8540 and 7890, respectively). This study demonstrates a new paradigm of developing high-performance FTJs by using ML.Ferroelectric tunnel junction (FTJ) has attracted considerable attention for its potential applications in nonvolatile memory and neuromorphic computing. However, the experimental exploration of FTJs with high ON/OFF ratios is a challenging task due to the vast search space comprising of ferroelectric and electrode materials, fabrication methods and conditions and so on. Here, machine learning (ML) is demonstrated to be an effective tool to guide the experimental search of FTJs with high ON/OFF ratios. A dataset consisting of 152 FTJ samples with nine features and one target attribute (i.e., ON/OFF ratio) is established for ML modeling. Among various ML models, the gradient boosting classification model achieves the highest prediction accuracy. Combining the feature importance analysis based on this model with the association rule mining, it is extracted that the utilizations of {graphene/graphite (Gra) (top), LaNiO3 (LNO) (bottom)} and {Gra (top), CaCeMnO3 (CCMO) (bottom)} electrode pairs are likely to result in high ON/OFF ratios in FTJs. Moreover, two previously unexplored FTJs: Gra/BaTiO3 (BTO)/LNO and Gra/BTO/CCMO, are predicted to achieve ON/OFF ratios higher than 1000. Guided by the ML predictions, the Gra/BTO/LNO and Gra/BTO/CCMO FTJs are experimentally fabricated, which unsurprisingly exhibit 1000 ON/OFF ratios (8540 and 7890, respectively). This study demonstrates a new paradigm of developing high-performance FTJs by using ML.