Machine Learning: A New Paradigm in Computational Electrocatalysis

Transfer learning guided discovery of efficient perovskite oxide for alkaline water oxidation

Perovskite oxides show promise for the oxygen evolution reaction. However, numerical chemical compositions remain unexplored due to inefficient trial-and-error methods for material discovery. Here, we develop a transfer learning paradigm incorporating a pre-trained model, ensemble learning, and active learning, enabling the prediction of undiscovered perovskite oxides with enhanced generalizability for this reaction. Screening 16,050 compositions leads to the identification and synthesis of 36 new perovskite oxides, including 13 pure perovskite structures. Pr0.1Sr0.9Co0.5Fe0.5O3 and Pr0.1Sr0.9Co0.5Fe0.3Mn0.2O3 exhibit low overpotentials of 327 mV and 315 mV at 10 mA cm-2, respectively. Electrochemical measurements reveal coexistence of absorbate evolution and lattice oxygen mechanisms for O-O coupling in both materials. Pr0.1Sr0.9Co0.5Fe0.3Mn0.2O3 demonstrates enhanced OH- affinity compared to Pr0.1Sr0.9Co0.5Fe0.5O3, with the emergence of oxo-bridged Mn-Co conjugate facilitating charge redistribution and dynamic reversibility of Olattice/VO, thereby slowing down Co dissolution. This work paves the way for accelerated discovery and development of high-performance perovskite oxide electrocatalysts for this reaction.

Structure and Dynamics of Aqueous 2-Aminothiazole/NaCl Electrolytes at Electrified Interfaces

A computational study was performed to investigate the dynamics of aqueous electrolytes containing organic corrosion inhibitors near electrified interfaces by using the constant-charge model in classical molecular dynamics simulations. The results showed that when inhibitors form films at the interface, the surface charge of the electrode causes displacement of the molecules, referred to as electroporation. The hydrophobicity of the inhibitor molecules affects both the stability of the films and their recovery time. This study highlights the value of computational investigations of the dynamics within inhibitor films as a complementary approach to the traditional focus on inhibitor-substrate interactions, leading to deeper insights into the mechanisms of corrosion inhibition mechanisms.

Interfacial Micro-Environment of Electrocatalysis and Its Applications for Organic Electro-Oxidation Reaction

Conventional designing principal of electrocatalyst is focused on the electronic structure tuning, on which effectively promotes the electrocatalysis. However, as a typical kind of electrode-electrolyte interface reaction, the electrocatalysis performance is also closely dependent on the electrocatalyst interfacial micro-environment (IME), including pH, reactant concentration, electric field, surface geometry structure, hydrophilicity/hydrophobicity, etc. Recently, organic electro-oxidation reaction (OEOR), which simultaneously reduces the anodic polarization potential and produces value-added chemicals, has emerged as a competitive alternative to oxygen evolution reaction, and the role IME played in OEOR is receiving great interest. Thus, this article provides a timely review on IME and its applications toward OEOR. In this review, the IME for conventional gas-involving reactions, as a contrast, is first presented, and then the recent progresses of IME toward diverse typical OEOR are summarized; especially, some representative works are thoroughly discussed. Additionally, cutting-edge analytical methods and characterization techniques are introduced to comprehensively understand the role IME played in OEOR. In the last section, perspectives and challenges of IME regulation for OEOR are shared.

High-entropy alloys in electrocatalysis: from fundamentals to applications

High-entropy alloys (HEAs) comprising five or more elements in near-equiatomic proportions have attracted ever increasing attention for their distinctive properties, such as exceptional strength, corrosion resistance, high hardness, and excellent ductility. The presence of multiple adjacent elements in HEAs provides unique opportunities for novel and adaptable active sites. By carefully selecting the element configuration and composition, these active sites can be optimized for specific purposes. Recently, HEAs have been shown to exhibit remarkable performance in electrocatalytic reactions. Further activity improvement of HEAs is necessary to determine their active sites, investigate the interactions between constituent elements, and understand the reaction mechanisms. Accordingly, a comprehensive review is imperative to capture the advancements in this burgeoning field. In this review, we provide a detailed account of the recent advances in synthetic methods, design principles, and characterization technologies for HEA-based electrocatalysts. Moreover, we discuss the diverse applications of HEAs in electrocatalytic energy conversion reactions, including the hydrogen evolution reaction, hydrogen oxidation reaction, oxygen reduction reaction, oxygen evolution reaction, carbon dioxide reduction reaction, nitrogen reduction reaction, and alcohol oxidation reaction. By comprehensively covering these topics, we aim to elucidate the intricacies of active sites, constituent element interactions, and reaction mechanisms associated with HEAs. Finally, we underscore the imminent challenges and emphasize the significance of both experimental and theoretical perspectives, as well as the potential applications of HEAs in catalysis. We anticipate that this review will encourage further exploration and development of HEAs in electrochemistry-related applications.

A Review of Transition Metal Boride, Carbide, Pnictide, and Chalcogenide Water Oxidation Electrocatalysts

Transition metal borides, carbides, pnictides, and chalcogenides (X-ides) have emerged as a class of materials for the oxygen evolution reaction (OER). Because of their high earth abundance, electrical conductivity, and OER performance, these electrocatalysts have the potential to enable the practical application of green energy conversion and storage. Under OER potentials, X-ide electrocatalysts demonstrate various degrees of oxidation resistance due to their differences in chemical composition, crystal structure, and morphology. Depending on their resistance to oxidation, these catalysts will fall into one of three post-OER electrocatalyst categories: fully oxidized oxide/(oxy)hydroxide material, partially oxidized core@shell structure, and unoxidized material. In the past ten years (from 2013 to 2022), over 890 peer-reviewed research papers have focused on X-ide OER electrocatalysts. Previous review papers have provided limited conclusions and have omitted the significance of "catalytically active sites/species/phases" in X-ide OER electrocatalysts. In this review, a comprehensive summary of (i) experimental parameters (e.g., substrates, electrocatalyst loading amounts, geometric overpotentials, Tafel slopes, etc.) and (ii) electrochemical stability tests and post-analyses in X-ide OER electrocatalyst publications from 2013 to 2022 is provided. Both mono and polyanion X-ides are discussed and classified with respect to their material transformation during the OER. Special analytical techniques employed to study X-ide reconstruction are also evaluated. Additionally, future challenges and questions yet to be answered are provided in each section. This review aims to provide researchers with a toolkit to approach X-ide OER electrocatalyst research and to showcase necessary avenues for future investigation.

Machine learning-assisted optimization of multi-metal hydroxide electrocatalysts for overall water splitting

Green hydrogen produced via electrochemical water splitting is a suitable candidate to replace emission-intensive fuels. However, the successful widespread adoption of green hydrogen is contingent on the development of low-cost, earth-abundant catalysts. Herein, machine learning models built on experimental data were used to optimize the precursor ratios of hydroxide-based electrocatalysts, with the objective of improving the product's electrocatalytic performance for overall water splitting. The Neural Network-based models were found to be the most effective in predicting and minimizing the overpotentials of the catalysts, reaching a minimum in two iterations. The relatively mild reaction conditions of the synthesis procedure, coupled with its scalability demonstrated herein, renders the optimized catalyst relevant for industrial implementation in the future. The optimized catalyst, characterized to be a molybdate-intercalated CoFe LDH, demonstrated overpotentials of 266 and 272 mV at 10 mA cm-2 for oxygen and hydrogen evolution reactions respectively in alkaline electrolyte, alongside unwavering stability for overall water splitting over 50 h. Overall, our results reflect the efficacy and advantages of machine learning strategies to alleviate the time and labour-intensive nature of experimental optimizations, which can greatly accelerate electrocatalysts research.

Machine Learning-Assisted Low-Dimensional Electrocatalysts Design for Hydrogen Evolution Reaction

Efficient electrocatalysts are crucial for hydrogen generation from electrolyzing water. Nevertheless, the conventional "trial and error" method for producing advanced electrocatalysts is not only cost-ineffective but also time-consuming and labor-intensive. Fortunately, the advancement of machine learning brings new opportunities for electrocatalysts discovery and design. By analyzing experimental and theoretical data, machine learning can effectively predict their hydrogen evolution reaction (HER) performance. This review summarizes recent developments in machine learning for low-dimensional electrocatalysts, including zero-dimension nanoparticles and nanoclusters, one-dimensional nanotubes and nanowires, two-dimensional nanosheets, as well as other electrocatalysts. In particular, the effects of descriptors and algorithms on screening low-dimensional electrocatalysts and investigating their HER performance are highlighted. Finally, the future directions and perspectives for machine learning in electrocatalysis are discussed, emphasizing the potential for machine learning to accelerate electrocatalyst discovery, optimize their performance, and provide new insights into electrocatalytic mechanisms. Overall, this work offers an in-depth understanding of the current state of machine learning in electrocatalysis and its potential for future research.

Machine Learning Study on Microwave-Assisted Batch Preparation and Oxygen Reduction Performance of Fe-N-C Catalysts

The Fe-N-C catalyst represents one of the most promising candidates for replacing platinum-based catalysts toward the oxygen reduction reaction. The pivotal factor in the successful integration of Fe-N-C catalysts within applications is the attainment of a large-scale production capability. Microwave-assisted pyrolysis offers various advantages, including enhanced energy and time efficiency, uniform heating, and high yield in single-batch processes. These characteristics render it exceptionally suitable for the mass production of catalysts. Through a synergistic approach involving machine learning techniques and microscopic characterization, we discerned performance trends and underlying mechanisms within batch-synthesized Fe-N-C catalysts under microwave-assisted preparation conditions. Machine learning analysis revealed that the precursor mass exerts the most substantial influence on product performance. Furthermore, microscopic characterization unveiled that these influencing factors impact catalyst performance by modulating the degree of agglomeration. Our research introduces an efficacious machine learning model for prognosticating performance and dissecting the influencing factors pertinent to Fe-N-C catalyst synthesis within a microwave system.

Thermodynamic and kinetic modeling of electrocatalytic reactions using a first-principles approach

The computational modeling of electrochemical interfaces and their applications in electrocatalysis has attracted great attention in recent years. While tremendous progress has been made in this area, however, the accurate atomistic descriptions at the electrode/electrolyte interfaces remain a great challenge. The Computational Hydrogen Electrode (CHE) method and continuum modeling of the solvent and electrolyte interactions form the basis for most of these methodological developments. Several posterior corrections have been added to the CHE method to improve its accuracy and widen its applications. The most recently developed grand canonical potential approaches with the embedded diffuse layer models have shown considerable improvement in defining interfacial interactions at electrode/electrolyte interfaces over the state-of-the-art computational models for electrocatalysis. In this Review, we present an overview of these different computational models developed over the years to quantitatively probe the thermodynamics and kinetics of electrochemical reactions in the presence of an electrified catalyst surface under various electrochemical environments. We begin our discussion by giving a brief picture of the different continuum solvation approaches, implemented within the ab initio method to effectively model the solvent and electrolyte interactions. Next, we present the thermodynamic and kinetic modeling approaches to determine the activity and stability of the electrocatalysts. A few applications to these approaches are also discussed. We conclude by giving an outlook on the different machine learning models that have been integrated with the thermodynamic approaches to improve their efficiency and widen their applicability.

Metal-Doped C3B Monolayer as the Promising Electrocatalyst for Hydrogen/Oxygen Evolution Reaction: A Combined Density Functional Theory and Machine Learning Study

The development of high-efficiency electrocatalysts for hydrogen evolution reduction (HER)/oxygen evolution reduction (OER) is highly desirable. In particular, metal borides have attracted much attention because of their excellent performances. In this study, we designed a series of metal borides by doping of a transition metal (TM) in a C3B monolayer and further explored their potential applications for HER/OER via density functional theory (DFT) calculations and machine learning (ML) analysis. Our results revealed that the |ΔG*H| values of Fe-, Ag-, Re-, and Ir-doped C3B are approximately 0.00 eV, indicating their excellent HER performances. On the other hand, among all the considered TM atoms, the Ni- and Pt-doped C3B exhibit excellent OER activities with the overpotentials smaller than 0.44 V. Together with their low overpotentials for HER (<0.16 V), we proposed that Ni/C3B and Pt/C3B could be the potential bifunctional electrocatalysts for water splitting. In addition, the ML method was employed to identify the important factors to affect the performance of the TM/C3B electrocatalyst. Interestingly, the results showed that the OER performance is closely related to the inherent properties of TM atoms, i.e., the number of d electrons, electronegativity, atomic radius, and first ionization energy; all these values could be directly obtained without DFT calculations. Our results not only proposed several promising electrocatalysts for HER/OER but also suggested a guidance to design the potential TM-boron (TM-B)-based electrocatalysts.

Unveiling the Hidden Energy Profiles of the Oxygen Evolution Reaction via Machine Learning Analyses

The oxygen evolution reaction (OER) is a crucial electrochemical process for hydrogen production in water electrolysis. However, due to the involvement of multiple proton-coupled electron transfer steps, it is challenging to identify the specific elementary reaction that limits the rate of the OER. Here we employed a machine-learning-based approach to extract the reaction pathway exhaustively from experimental data. Genetic algorithms were applied to search for thermodynamic and kinetic parameters using the current-electrochemical potential relationship of the OER. Interestingly, analysis of the datasets revealed the energy state distributions of reaction intermediates, which likely originated in the interactions among intermediates or the distribution of multiple sites. Through our exhaustive analyses, we successfully uncovered the hidden energy profiles of the OER. This approach can reveal the reaction pathway to activate for efficient hydrogen production, which facilitates the design of catalysts.

Theory-Guided Construction of the Unsaturated V-N2 Site with Carbon Defects for Highly Selective Electrocatalytic Nitrogen Reduction

Renewable energy-driven, electrocatalytic nitrogen reduction reaction (NRR) is a promising strategy for ammonia synthesis. However, improving catalyst activity and selectivity under ambient conditions has long been challenging. In this work, we obtained the potential active V-N center through theoretical prediction and successfully constructed the associated V-N₂/N₃ structure on N-doped carbon materials. Surprisingly, such a catalyst exhibits excellent electrocatalytic NRR performance. The V-N₂ catalyst affords a remarkably high faradaic efficiency of 76.53% and an NH₃ yield rate of 31.41 μg_NH3 h^-1 mg_Cat.^-1 at -0.3 V vs RHE. The structural characterization and density functional theory (DFT) calculations verified that the high performance of the catalyst originates from the tuned d-band upon coordination with nitrogen, in line with the original design intention as derived theoretically. Indeed, the V-N₂ center with carbon defects enhances dinitrogen adsorption and charge transfer, thereby lowering the energy barriers to form the *NNH intermediates. Such a strategy as a rational design─controllable synthesis─theoretical verification may prove effective as well for other chemical processes.

Machine Learning Descriptors for Data-Driven Catalysis Study

Traditional trial-and-error experiments and theoretical simulations have difficulty optimizing catalytic processes and developing new, better-performing catalysts. Machine learning (ML) provides a promising approach for accelerating catalysis research due to its powerful learning and predictive abilities. The selection of appropriate input features (descriptors) plays a decisive role in improving the predictive accuracy of ML models and uncovering the key factors that influence catalytic activity and selectivity. This review introduces tactics for the utilization and extraction of catalytic descriptors in ML-assisted experimental and theoretical research. In addition to the effectiveness and advantages of various descriptors, their limitations are also discussed. Highlighted are both 1) newly developed spectral descriptors for catalytic performance prediction and 2) a novel research paradigm combining computational and experimental ML models through suitable intermediate descriptors. Current challenges and future perspectives on the application of descriptors and ML techniques to catalysis are also presented.

Analysis of the oxygen evolution activity of layered double hydroxides (LDHs) using machine learning guidance

Layered double hydroxides (LDHs) are excellent catalysts for the oxygen evolution reaction (OER) because of their tunable properties, including chemical composition and structural morphology. An interplay between these adjustable properties and other (including external) factors might not always benefit the OER catalytic activity of LDHs. Therefore, we applied machine learning algorithms to simulate the double-layer capacitance to understand how to design/tune LDHs with targeted catalytic properties. The key factors of solving this task were identified using the Shapley Additive explanation and cerium was identified as an effective element to modify the double-layer capacitance. We also compared different modelling methods to identify the most promising one and the results revealed that binary representation is better than directly applying atom numbers as inputs for chemical compositions. Overpotentials of LDH-based materials as predicted targets were also carefully examined and evaluated, and it turns out that overpotentials can be predicted when measurement conditions about overpotentials are added as features. Finally, to confirm our findings, we reviewed additional experimental literature data and used them to test our machine algorithms to predict LDH properties. This analysis confirmed the very credible and robust generalization ability of our final model capable of achieving accurate results even with a relatively small dataset.

Active Learning Accelerating to Screen Dual-Metal-Site Catalysts for Electrochemical Carbon Dioxide Reduction Reaction

Dual-metal-site catalysts (DMSCs) are increasingly important catalysts in the field of electrochemical carbon dioxide reduction reaction (CO₂RR) in recent years. However, rapid screening of suitable metal combinations of DMSCs remains a huge challenge. Herein, we constructed an active learning (AL) framework to study CO₂RR to HCOOH. This AL framework turned out a success in the accurate prediction of 282 DMSCs for CO₂RR through interactive learning between users and machine learning (ML) models. Among the 42 DMSCs calculated in three iteration loops of AL, 29 DMSCs were obtained, where the screening success rate was as high as 70%. Furthermore, we found five experimentally unexplored DMSCs that exhibited better CO₂RR activity and selectivity than pure Bi. Low prediction errors on other DMSCs show that the AL model possessed outstanding universality. The results prove the excellent potential of the AL method and provide guidance on the design of high-performance electrocatalysts for CO₂RR.

Machine Learning Assisted Simulations of Electrochemical Interfaces: Recent Progress and Challenges

The electrochemical interface, where the adsorption of reactants and electrocatalytic reactions take place, has long been a focus of attention. Some of the important processes on it tend to possess relatively slow kinetic characteristics, which are usually beyond the scope of ab initio molecular dynamics. The newly emerging technique, machine learning methods, provides an alternative approach to achieve thousands of atoms and nanosecond time scale while ensuring precision and efficiency. In this Perspective, we summarize in detail the recent progress and achievements made by the introduction of machine learning to simulate electrochemical interfaces, and focus on the limitations of current machine learning models, such as accurate descriptions of long-range electrostatic interactions and the kinetics of the electrochemical reactions occurring at the interface. Finally, we further point out the future directions for machine learning to expand in the field of electrochemical interfaces.