Atomistic learning in the electronically grand-canonical ensemble

Abstract

A strategy is presented for the machine-learning emulation of electronic structure calculations carried out in the electronically grand-canonical ensemble. The approach relies upon a dual-learning scheme, where both the system charge and the system energy are predicted for each image. The scheme is shown to be capable of emulating basic electrochemical reactions at a range of potentials, and coupling it with a bootstrap-ensemble approach gives reasonable estimates of the prediction uncertainty. The method is also demonstrated to accelerate saddle-point searches, and to extrapolate to systems with one to five water layers. We anticipate that this method will allow for larger length- and time-scale simulations necessary for electrochemical simulations.

Electrochemical Degradation of Pt3Co Nanoparticles Investigated by Off-Lattice Kinetic Monte Carlo Simulations with Machine-Learned Potentials

“…The ab initio computation of the activation barriers in electrochemical reactions is a formidable task due to the intricate nature of atomic environments and the hurdles faced when incorporating electrode potentials in the first-principles calculations (i.e., grand-canonical calculations). We note that considerable efforts are being made to tackle each of these challenges. − Additionally, advancements are also being made in directly simulating solvent environments and electrochemical reactions using MLPs. − …”

Recent Advances and Fundamental Challenges in Computational Modeling of Electrocatalytic Ammonia Oxidation

“…One requirement for the accuracy and efficiency of such enhanced sampling methods is an accurate potential energy surface, which can potentially be provided by well-trained machine learning potentials. 59,60 The development of highly accurate and efficient machine learning potentials by learning from ab initio data for describing electrocatalytic processes is promising. 60 Improvements to algorithms 61,62 and computational data ecosystems 63,64 will help to discover more about the phenomena buried at the solid−electrolyte interfaces.…”

“…59,60 The development of highly accurate and efficient machine learning potentials by learning from ab initio data for describing electrocatalytic processes is promising. 60 Improvements to algorithms 61,62 and computational data ecosystems 63,64 will help to discover more about the phenomena buried at the solid−electrolyte interfaces. Finally, the complexity of electrochemical systems, such as the presence of multiple reaction pathways and the coupling of physical processes at different scales, e.g., mass transport, can also pose challenges for computational modeling.…”

“…To model rare events like chemical reactions, advanced sampling methods, such as replica-exchange molecular dynamics, metadynamics, and blue moon ensemble, are required to capture the dynamics of catalytic processes within an acceptable simulation time frame. One requirement for the accuracy and efficiency of such enhanced sampling methods is an accurate potential energy surface, which can potentially be provided by well-trained machine learning potentials. , The development of highly accurate and efficient machine learning potentials by learning from ab initio data for describing electrocatalytic processes is promising . Improvements to algorithms , and computational data ecosystems , will help to discover more about the phenomena buried at the solid–electrolyte interfaces.…”

A Simple Evaluation of Adiabatic Proton Tunneling across the Electrified Double Layer

“…Identifying and reducing rate-limiting steps for processes involving CPET steps remains a key challenge toward improving existing chemical transformation technologies. ,− Recent advancements in electrocatalysis theory and developments in methods for density functional theory (DFT) have revolutionized our understanding of CPET reactions at the atomic level. ,− These developments have not only provided fundamental insights into reaction dynamics but also improved our ability to predict trends in their rates more accurately, a crucial step toward optimizing the use of such processes in energy conversion and storage. Ultimately the goal of such approaches is to identify pathways to improve the efficiency of electrocatalytic processes, thereby improving their economic competitiveness and enabling their broader integration in the global transition to a sustainable energy system. − …”