A machine learning strategy-incorporated BiFeO3/Ti3C2 MXene electrochemical platform for simple, rapid detection of Pb2+ with high sensitivity

Abstract

The electrochemical technique has been increasingly used for the detection of heavy metal ions in the water system. However, the process for determining the optimum experimental conditions was cumbersome, time-consuming, and unsynchronized, resulting in unsatisfactory detection efficiency. Herein, a new machine learning (ML) strategy combined with BiFeO3/Ti3C2 MXene (BiFeO3/MXene) was used to fabricate a simple but efficient electrochemical Pb2+ sensor. The interconnected BiFeO3/MXene composites prepared by a hydrothermal method possessed an interconnected conductive framework, abundant active sites, and a large surface area, which gave them excellent electronic conductivity and high accumulation of Pb2+. Meanwhile, ML methods such as back-propagation artificial neural network (BPANN) and genetic algorithm (GA) combined with orthogonal experimental design (OED) were used to optimize sensor parameters such as the pH of the supporting electrolyte, the BiFeO3/MXene content, deposition potential, and deposition time. Compared with OED and the one factor at a time (OFAT) methods, the OED-ML method greatly simplified the experimental procedures and improved the electrochemical detection performance. The developed sensor showed superior detection performance for Pb2+ with a detection limit of 0.0001 μg L−1 using the OED-ML method, which was much lower than that of the OED and OFAT methods (0.0003 μg L−1). In addition, the sensor showed good repeatability, reproducibility, stability, and interference capability. The feasibility of the method was verified by detecting Pb2+ in lake samples with recoveries ranging from 98.79% to 101.3%. To our knowledge, the ML strategy was introduced for the first time in an electrochemical sensor for Pb2+ detection, which proved the feasibility and practicality of ML.