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

Abstract

The detection and classification of heavy metals is a growing need to guarantee the quality of process water in different industries. However, the official methodologies to evaluate the presence of these contaminants require samples pre-processing, making them time-consuming and expensive; these elements do not allow online monitoring. For this reason, new technologies are required for online monitoring and evaluation. In this work, a new methodology is presented for the detection and classification of different heavy metal ions such as: As, Pb and Cd. Commercial graphite sensors modified with 2D molybdenite were used applying an electroanalytical technique of square wave voltammetry. Subsequently, signal processing based on pattern recognition and machine learning methods was carried out. This classification methodology includes the following steps: data display and arrangement, dimensionality reduction through the t-distributed stochastic neighbor embedding (t-SNE) method, which serves as feature extraction, and the support vector machines (SVM) method as a classifier. The validation is carried out with a data set of 118 aqueous samples. Leave one out cross-validation (LOOCV) was used to obtain classification accuracy. The results showed a classification accuracy of 98.31% with only two errors of the experimental validation with this data set. It is concluded that this methodology is a useful tool for detecting the presence of these ions in aqueous samples with MoS2-2D.

Machine learning toward high-performance electrochemical sensors

“…When bio/sensors lead to the generation of chemically diversified outputs, i.e., fingerprints, with pattern responses being attained to the samples, the use of ML becomes an effective strategy to assure accurate detection and/or classification tasks [13][14][15][16][17][18][19][20][21]. Impedimetric devices are attractive tools to provide diversified features as the variation of impedance (Z) with frequency depends on a set of distinguishable parameters, including resistive, capacitive, interface, and mass-transport phenomena [22].…”

Leveraging graphical models to enhance in situ analyte identification via multiple voltammetric techniques

“…These methods have been developed for a variety of purposes, including analyte detection (e.g., biomarkers, explosive compounds) and property quantification (e.g., estimating transport and electrochemical features). [35][36][37][38][39][40][41][42][43][44][45][46][47][48] However, these computational approaches often leverage physics-agnostic methods (e.g., support-vector machines, partial least squares regression) that are difficult to extrapolate to conditions not directly examined in the training data. [46][47][48][49] In this vein, the integration of physical models into computational voltammetry algorithms may build upon the demonstrations already present in the field to enable more powerful algorithms.…”

“…[35][36][37][38][39][40][41][42][43][44][45][46][47][48] However, these computational approaches often leverage physics-agnostic methods (e.g., support-vector machines, partial least squares regression) that are difficult to extrapolate to conditions not directly examined in the training data. [46][47][48][49] In this vein, the integration of physical models into computational voltammetry algorithms may build upon the demonstrations already present in the field to enable more powerful algorithms. Efforts towards physics-augmented machine learning algorithms for voltammetry are already underway; inferential algorithms, combined with a physics-based voltammetry simulator (e.g., MECSim 50 ), can estimate parameter values and can even discriminate between candidate electron transfer mechanisms (e.g., Butler-Volmer, Marcus-Hush).…”

Leveraging graphical models to enhance in situ analyte identification via multiple voltammetric techniques

“…These methods have been developed for a variety of purposes, including analyte detection (e.g., biomarkers, explosive compounds) and property quantification (estimating transport and electrochemical features). [35][36][37][38][39][40][41][42][43][44][45][46][47][48] However, these computational approaches often leverage physics-agnostic methods (e.g., support-vector machines, partial least squares regression) that are difficult to extrapolate to conditions not directly examined in the training data. [46][47][48][49] In this vein, the integration of physical models into computational voltammetry algorithms may build upon the demonstrations already present in the field to enable more powerful algorithms.…”

“…[35][36][37][38][39][40][41][42][43][44][45][46][47][48] However, these computational approaches often leverage physics-agnostic methods (e.g., support-vector machines, partial least squares regression) that are difficult to extrapolate to conditions not directly examined in the training data. [46][47][48][49] In this vein, the integration of physical models into computational voltammetry algorithms may build upon the demonstrations already present in the field to enable more powerful algorithms. Efforts towards physics-augmented machine learning algorithms for voltammetry are already underway; indeed, inferential algorithms, combined with a physics-based voltammetry simulator (e.g., MECSim), can estimate parameter values and can even discriminate between candidate electron transfer mechanisms (e.g., Butler-Volmer, Marcus-Hush).…”