Experimental search for high-performance ferroelectric tunnel junctions guided by machine learning

Abstract

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), Ca[Formula: see text]Ce[Formula: see text]MnO3 (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 [Formula: see text]1000 ON/OFF ratios ([Formula: see text]8540 and [Formula: see text]7890, respectively). This study demonstrates a new paradigm of developing high-performance FTJs by using ML.

Keywords

• Machine learning
• ferroelectric tunnel junctions
• ON/OFF ratio
• nonvolatile memory