Inclusion of multiple cycling of potential in the deep neural network classification of voltammetric reaction mechanisms.

The use of deep neural networks (DNNs) for the classification of electrochemical mechanisms using simulated voltammograms with one cycle of potential for training has previously been reported. In this paper, it is shown how valuable additional patterns for mechanism distinction become available when a new DNN is trained simultaneously on images obtained from three cycles of potential using tensor inputs. Significant improvements, relative to the single cycle training, in achieving the correct classification of E, EC1st and EC2nd mechanisms (E = electron transfer step and C1st and C2nd are first and second order follow up chemical reactions, respectively) are demonstrated with noisy simulated data for conditions where all mechanisms are close to chemically reversible and hence difficult to distinguish, even by an experienced electrochemist. Challenges anticipated in applying the new DNN to the classification of experimental data are highlighted. Directions for future development are also discussed.

Recent advances and future perspectives for automated parameterisation, Bayesian inference and machine learning in voltammetry.

Advanced data analysis tools such as mathematical optimisation, Bayesian inference and machine learning have the capability to revolutionise the field of quantitative voltammetry. Nowadays such approaches can be implemented routinely with widely available, user-friendly modern computing languages, algorithms and high speed computing to provide accurate and robust methods for quantitative comparison of experimental data with extensive simulated data sets derived from models proposed to describe complex electrochemical reactions. While the methodology is generic to all forms of dynamic electrochemistry, including the widely used direct current cyclic voltammetry, this review highlights advances achievable in the parameterisation of large amplitude alternating current voltammetry. One significant advantage this technique offers in terms of data analysis is that Fourier transformation provides access to the higher order harmonics that are almost devoid of background current. Perspectives on the technical advances needed to develop intelligent data analysis strategies and make them generally available to users of voltammetry are provided.

Application of Bayesian Inference in Fourier-Transformed Alternating Current Voltammetry for Electrode Kinetic Mechanism Distinction.

Estimation of parameters of interest in dynamic electrochemical (voltammetric) studies is usually undertaken via heuristic or data optimization comparison of the experimental results with theory based on a model chosen to mimic the experiment. Typically, only single point parameter values are obtained via either of these strategies without error estimates. In this article, Bayesian inference is introduced to Fourier-transformed alternating current voltammetry (FTACV) data analysis to distinguish electrode kinetic mechanisms (reversible or quasi-reversible, Butler-Volmer or Marcus-Hush models) and quantify the errors. Comparisons between experimental and simulated data were conducted across all harmonics using public domain freeware (MECSim).