Machine Learning Descriptors for Data-Driven Catalysis Study

Leveraging Machine Learning Potentials for In-Situ Searching of Active sites in Heterogeneous Catalysis

This Perspective explores the integration of machine learning potentials (MLPs) in the research of heterogeneous catalysis, focusing on their role in identifying in situ active sites and enhancing the understanding of catalytic processes. MLPs utilize extensive databases from high-throughput density functional theory (DFT) calculations to train models that predict atomic configurations, energies, and forces with near-DFT accuracy. These capabilities allow MLPs to handle significantly larger systems and extend simulation times beyond the limitations of traditional ab initio methods. Coupled with global optimization algorithms, MLPs enable systematic investigations across vast structural spaces, making substantial contributions to the modeling of catalyst surface structures under reactive conditions. The review aims to provide a broad introduction to recent advancements and practical guidance on employing MLPs and also showcases several exemplary cases of MLP-driven discoveries related to surface structure changes under reactive conditions and the nature of active sites in heterogeneous catalysis. The prevailing challenges faced by this approach are also discussed.

Application of graph neural network in computational heterogeneous catalysis

Heterogeneous catalysis, as a key technology in modern chemical industries, plays a vital role in social progress and economic development. However, its complex reaction process poses challenges to theoretical research. Graph neural networks (GNNs) are gradually becoming a key tool in this field as they can intrinsically learn atomic representation and consider connection relationship, making them naturally applicable to atomic and molecular systems. This article introduces the basic principles, current network architectures, and datasets of GNNs and reviews the application of GNN in heterogeneous catalysis from accelerating the materials screening and exploring the potential energy surface. In the end, we summarize the main challenges and potential application prospects of GNNs in future research endeavors.

A Data-Driven Approach for Enhanced CO2 Capture with Ruthenium Complexes

To attain carbon neutrality, significant efforts have been made to capture and utilize CO2. The homogeneous hydrogenation of CO2 catalyzed by transition metal complexes, particularly the ruthenium complexes, has demonstrated significant advantages and is regarded as a viable approach for practical application. Insertion of CO2 into the Ru-H bond, producing the Ru-formate product, is the key step in the hydrogenation of CO2. In order to parameterize the catalytic activities in the CO2 insertion into the Ru-H bond, the concept of simplified mechanism-based approach with data-driven practice (SMADP) has been introduced in this paper. The results showed that the hydricity of the Ru-H complex (ΔGH-) might serve as a single active descriptor in the process of CO2 insertion, and that a novel ruthenium complex in CO2 catalysis may not be easily obtained by mere modification of the auxiliary ligand at the ruthenium metal site.

Predicting and understanding photocatalytic CO2 reduction reaction with IR spectroscopy-based interpretable machine learning framework

The highly selective conversion of carbon dioxide into value-added products is extremely valuable. However, even with the aid of in situ characterization techniques, it remains challenging to directly correlate extensive spectral data carrying microscopic information with macroscopic performance. Herein, we adopted advanced machine learning (ML) approaches to establish an accurate and interpretable relationship between vibrational spectral signals and catalytic performances to uncover hidden physical insights. Focusing on photocatalytic CO2 reduction, our model is shown to effectively and accurately predict the CO production activity and selectivity based solely on the infrared (IR) spectral signals, the generalizability of which is additionally demonstrated with a new Bi5O7I photocatalytic system. More importantly, further model analysis has revealed a novel strategy to steer CO selectivity, the physical sanity of which is verified by a detailed reaction mechanism analysis. This work demonstrates the tremendous potential of machine-learned spectroscopy to efficiently identify reaction control factors, which can further lay the foundation for targeted optimization and reverse design.

Progress and challenges in nitrous oxide decomposition and valorization

Nitrous oxide (N2O) decomposition is increasingly acknowledged as a viable strategy for mitigating greenhouse gas emissions and addressing ozone depletion, aligning significantly with the UN's sustainable development goals (SDGs) and carbon neutrality objectives. To enhance efficiency in treatment and explore potential valorization, recent developments have introduced novel N2O reduction catalysts and pathways. Despite these advancements, a comprehensive and comparative review is absent. In this review, we undertake a thorough evaluation of N2O treatment technologies from a holistic perspective. First, we summarize and update the recent progress in thermal decomposition, direct catalytic decomposition (deN2O), and selective catalytic reduction of N2O. The scope extends to the catalytic activity of emerging catalysts, including nanostructured materials and single-atom catalysts. Furthermore, we present a detailed account of the mechanisms and applications of room-temperature techniques characterized by low energy consumption and sustainable merits, including photocatalytic and electrocatalytic N2O reduction. This article also underscores the extensive and effective utilization of N2O resources in chemical synthesis scenarios, providing potential avenues for future resource reuse. This review provides an accessible theoretical foundation and a panoramic vision for practical N2O emission controls.

Automation and machine learning augmented by large language models in a catalysis study

Recent advancements in artificial intelligence and automation are transforming catalyst discovery and design from traditional trial-and-error manual mode into intelligent, high-throughput digital methodologies. This transformation is driven by four key components, including high-throughput information extraction, automated robotic experimentation, real-time feedback for iterative optimization, and interpretable machine learning for generating new knowledge. These innovations have given rise to the development of self-driving labs and significantly accelerated materials research. Over the past two years, the emergence of large language models (LLMs) has added a new dimension to this field, providing unprecedented flexibility in information integration, decision-making, and interacting with human researchers. This review explores how LLMs are reshaping catalyst design, heralding a revolutionary change in the fields.

A systematic theoretical study of CO2 hydrogenation towards methanol on Cu-based bimetallic catalysts: role of the CHO&CH3OH descriptor in thermodynamic analysis

The application of density functional theory (DFT) has enriched our understanding of methanol synthesis through CO2 hydrogenation on Cu-based catalysts. However, variations in catalytic performance under different metal doping conditions have hindered the development of universal catalytic principles. To address these challenges, we systematically investigated the scaling relationships of adsorption energy among different reaction intermediates on pure Cu, Au-Cu, Ni-Cu, Pt-Cu, Pd-Cu and Zn-Cu models. Additionally, by summing the respective adsorption energies of two separate species, we have developed a dual intermediate descriptor of CHO&CH3OH, capable of achieving computational accuracy on par with DFT results using the multiple linear regression method, all the while enabling the rapid prediction of thermodynamic properties at various stages of methanol synthesis. This method facilitates a better understanding of the coupling mechanisms between energy and linear expressions on copper-based substrates, and the universal linear criterion can be applied to other catalytic systems, with the aim of pursuing potential catalysts having both high efficiency and low cost.

CatEmbed: A Machine-Learned Representation Obtained via Categorical Entity Embedding for Predicting Adsorption and Reaction Energies on Bimetallic Alloy Surfaces

Machine-learning models for predicting adsorption energies on metallic surfaces often rely on basic elemental properties and electronic and geometric descriptors. Here, we apply categorical entity embedding, a featurization method inspired by natural language processing techniques, to predict adsorption energies on bimetallic alloy surfaces using categorical descriptors. Using this method, we develop a machine-learned representation from categorical descriptors (e.g., surface composition, adsorbate type, and site type) of the slab/adsorbate complex. By combining this representation with numerical features (e.g., slab metal stoichiometric ratios), we create the CatEmbed representation. Remarkably, decision tree models trained using CatEmbed, which includes no explicit geometric information, achieve a Mean Absolute Error (MAE) of 0.12 eV. Additionally, we extend this technique to predict reaction energies on bimetallic surfaces, creating the CatEmbed-React representation, which achieves an MAE of 0.08 eV. These findings highlight the effectiveness of categorical entity embedding for predicting adsorption and reaction energies on bimetallic alloy surfaces.

Machine Learning to Promote Efficient Screening of Low-Contact Electrode for 2D Semiconductor Transistor Under Limited Data

Low-barrier and high-injection electrodes are crucial for high-performance (HP) 2D semiconductor devices. Conventional trial-and-error methodologies for electrode material screening are impractical because of their low efficiency and arbitrary specificity. Although machine learning has emerged as a promising alternative to tackle this problem, its practical application in semiconductor devices is hindered by its substantial data requirements. In this paper, a comprehensive scheme combining an autoencoding regularized adversarial neural network and a feature-adaptive variational active learning algorithm for screening low-contact electrode materials for 2D semiconductor transistors with limited data is proposed. The proposed scheme exhibits exceptional performance by training with only 15% of the total data points, where the mean square errors are 0.17 and 0.27 eV for the vertical and lateral Schottky barrier, respectively, and 2.88% for tunneling probability. Further, it exhibits an optimal predictive performance for 100 randomly sampled training datasets, reveals the underlying physical insight based on the identified features, and realizes continual improvement by employing detailed density-of-states descriptors. Finally, the empirical evaluations of the transport characteristics are conducted and verified by constructing MOSFET devices. These findings demonstrate the considerable potential of machine-learning techniques for screening high-efficiency electrode materials and constructing HP 2D semiconductor devices.

Single-atom and cluster catalysts for thermocatalytic ammonia synthesis at mild conditions

Ammonia (NH3) is closely related to the fields of food and energy that humans depend on. The exploitation of advanced catalysts for NH3 synthesis has been a research hotspot for more than one hundred years. Previous studies have shown that the Ru B5 sites (step sites on the Ru (0001) surface uniquely arranged with five Ru atoms) and Fe C7 sites (iron atoms with seven nearest neighbors) over nanoparticle catalysts are highly reactive for N2-to-NH3 conversion. In recent years, single-atom and cluster catalysts, where the B5 sites and C7 sites are absent, have emerged as promising catalysts for efficient NH3 synthesis. In this review, we focus on the recent advances in single-atom and cluster catalysts, including single-atom catalysts (SACs), single-cluster catalysts (SCCs), and bimetallic-cluster catalysts (BCCs), for thermocatalytic NH3 synthesis at mild conditions. In addition, we discussed and summarized the unique structural properties and reaction performance as well as reaction mechanisms over single-atom and cluster catalysts in comparison with traditional nanoparticle catalysts. Finally, the challenges and prospects in the rational design of efficient single-atom and cluster catalysts for NH3 synthesis were provided.

Computational chemistry for water-splitting electrocatalysis

Electrocatalytic water splitting driven by renewable electricity has attracted great interest in recent years for producing hydrogen with high-purity. However, the practical applications of this technology are limited by the development of electrocatalysts with high activity, low cost, and long durability. In the search for new electrocatalysts, computational chemistry has made outstanding contributions by providing fundamental laws that govern the electron behavior and enabling predictions of electrocatalyst performance. This review delves into theoretical studies on electrochemical water-splitting processes. Firstly, we introduce the fundamentals of electrochemical water electrolysis and subsequently discuss the current advancements in computational methods and models for electrocatalytic water splitting. Additionally, a comprehensive overview of benchmark descriptors is provided to aid in understanding intrinsic catalytic performance for water-splitting electrocatalysts. Finally, we critically evaluate the remaining challenges within this field.

Perspectives on development of optoelectronic materials in artificial intelligence age

Optoelectronic devices, such as light-emitting diodes, have been demonstrated as one of the most demanded forthcoming display and lighting technologies because of their low cost, low power consumption, high brightness, and high contrast. The improvement of device performance relies on advances in precisely designing novelty functional materials, including light-emitting materials, hosts, hole/electron transport materials, and yet which is a time-consuming, laborious and resource-intensive task. Recently, machine learning (ML) has shown great prospects to accelerate material discovery and property enhancement. This review will summarize the workflow of ML in optoelectronic materials discovery, including data collection, feature engineering, model selection, model evaluation and model application. We highlight multiple recent applications of machine-learned potentials in various optoelectronic functional materials, ranging from semiconductor quantum dots (QDs) or perovskite QDs, organic molecules to carbon-based nanomaterials. We furthermore discuss the current challenges to fully realize the potential of ML-assisted materials design for optoelectronics applications. It is anticipated that this review will provide critical insights to inspire new exciting discoveries on ML-guided of high-performance optoelectronic devices with a combined effort from different disciplines.