Discovering Electrochemistry with an Electrochemistry‐Informed Neural Network (ECINN)

Abstract

Machine learning is increasingly integrated into chemistry research by guiding experimental procedures, correlating structure, and function, interpreting large experimental datasets, to distill scientific insights that might be challenging with traditional methods. Such applications, however, largely focus on gaining insights via big data and/or big computation, while neglecting the valuable chemical prior knowledge dwelling in chemists’ minds. In this paper, we introduce an Electrochemistry‐Informed Neural Network (ECINN) by explicitly embedding electrochemistry priors including the Butler‐Volmer (BV), Nernst and diffusion equations on the backbone of neural networks for multi‐task discovery of electrochemistry parameters. We applied the ECINN to voltammetry experiments of and redox couples to discover electrode kinetics and mass transport parameters. Notably, ECINN seamlessly integrated mass transport with BV to analyze the entire voltammogram to infer transfer coefficients directly, so offering a new approach to Tafel analysis by outdating various mass transport correction methods. In addition, ECINN can help discover the nature of electron transfer and is shown to refute incorrect physics if imposed. This work encourages chemists to embed their domain knowledge into machine learning models to start a new paradigm of chemistry‐informed machine learning for better accountability, interpretability, and generalization.

Removing 65 Years of Approximation in Rotating Ring Disk Electrode Theory with Physics-Informed Neural Networks

“…The recent introduction of PINN, as a novel discretization-free partial differential equation (PDE) solver, has proven effective and accurate, to solve complicated PDEs in various domains, from modeling and reconstructing fluid mechanics flow fields, , to material fatigue prediction and solid mechanics, , and to blood pressure and hemodynamics estimation in healthcare. , In the field of electrochemistry, PINN has re-educated hydrodynamic electrochemistry simulation in areas ranging from single and double microband channel electrodes to the rotating disk electrode with analytical levels of accuracy. , In 2024, PINN is no longer at its infancy, or is complementary to traditional finite difference and finite element methods . The Electrochemistry-Informed Neural Netwok (ECINN) embedded electrochemical kinetic laws with mass transport equations, achieving simultaneous discovery of electrochemical rate constants, transfer coefficients, and diffusion coefficients . PINN stands ready to solve electrochemical problems for the community, offering freedom from previously essential approximations both physical and mathematical.…”

“… 28 The Electrochemistry-Informed Neural Netwok (ECINN) embedded electrochemical kinetic laws with mass transport equations, achieving simultaneous discovery of electrochemical rate constants, transfer coefficients, and diffusion coefficients. 29 PINN stands ready to solve electrochemical problems for the community, offering freedom from previously essential approximations both physical and mathematical. All simulation programmers used below are available on with neural network weights for users’ convenience.…”