Coupling Square Wave Anodic Stripping Voltammetry with Support Vector Regression to Detect the Concentration of Lead in Soil under the Interference of Copper Accurately

Abstract

In this study, an effective method for accurately detecting Pb(II) concentration was developed by coupling square wave anodic stripping voltammetry (SWASV) with support vector regression (SVR) based on a bismuth-film modified electrode. The interference of different Cu2+ contents on the SWASV signals of Pb2+ was investigated, and a nonlinear relationship between Pb2+ concentration and the peak currents of Pb2+ and Cu2+ was determined. Thus, an SVR model with two inputs (i.e., peak currents of Pb2+ and Cu2+) and one output (i.e., Pb2+ concentration) was trained to quantify the above nonlinear relationship. The SWASV measurement conditions and the SVR parameters were optimized. In addition, the SVR mode, multiple linear regression model, and direct calibration mode were compared to verify the detection performance by using the determination coefficient (R2) and root-mean-square error (RMSE). Results showed that the SVR model with R2 and RMSE of the test dataset of 0.9942 and 1.1204 μg/L, respectively, had better detection accuracy than other models. Lastly, real soil samples were applied to validate the practicality and accuracy of the developed method for the detection of Pb2+ with approximately equal detection results to the atomic absorption spectroscopy method and a satisfactory average recovery rate of 98.70%. This paper provided a new method for accurately detecting the concentration of heavy metals (HMs) under the interference of non-target HMs for environmental monitoring.

Spatiotemporal Variability Assessment of Trace Metals Based on Subsurface Water Quality Impact Integrated with Artificial Intelligence-Based Modeling

“…in several studies, such as [46][47][48][49][50][51]. In the literature, it has been reported that SVR models have been utilized by several researchers to estimate the concentration of trace and heavy metals in soil [52][53][54]. Equation (1) represents the SVR function with notations x k and m as the support vectors and their numbers, while the bias term (b) and the Lagrange coefficient α k need to be determined analytically for optimal SVR network identification.…”

Electrochemical stripping analysis

“…This method of adding a third element can be successfully used to minimize several other intermetallic interferences 233 . Finally, the application of neural networks 234,235 and support vector regression methods 236 have been reported to address the effect of intermetallic compounds.…”

Classification of As, Pb and Cd Heavy Metal Ions Using Square Wave Voltammetry, Dimensionality Reduction and Machine Learning

“…The catalytic properties of nanoparticles depend on the particle size. Gold is a nanoparticle that can improve heavy metal detection, but it has a high cost, which is a limitation for its use as an electrode modifier [15].…”