Using Artificial Intelligence To Forecast Water Oxidation Catalysts

Explainable machine-learning predictions for catalysts in CO2-assisted propane oxidative dehydrogenation

Propylene is an important raw material in the chemical industry that needs new routes for its production to meet the demand. The CO2-assisted oxidative dehydrogenation of propane (CO2-ODHP) represents an ideal way to produce propylene and uses the greenhouse gas CO2. The design of catalysts with high efficiency is crucial in CO2-ODHP research. Data-driven machine learning is currently of great interest and gaining popularity in the heterogeneous catalysis field for guiding catalyst development. In this study, the reaction results of CO2-ODHP reported in the literature are combined and analyzed with varied machine learning algorithms such as artificial neural network (ANN), k-nearest neighbors (KNN), support vector regression (SVR) and random forest regression (RF)and were used to predict the propylene space-time yield. Specifically, the RF method serves as a superior performing algorithm for propane conversion and propylene selectivity prediction, and SHapley Additive exPlanations (SHAP) based on the Shapley value performs fine model interpretation. Reaction conditions and chemical components show different impacts on catalytic performance. The work provides a valuable perspective for the machine learning in light alkane conversion, and helps us to design catalyst by catalytic performance hidden in the data of literatures.

The landscape of computational approaches for artificial photosynthesis

Artificial photosynthesis is an attractive strategy for converting solar energy into fuels, largely because the Earth receives enough solar energy in one hour to meet humanity's energy needs for an entire year. However, developing devices for artificial photosynthesis remains difficult and requires computational approaches to guide and assist the interpretation of experiments. In this Perspective, we discuss current and future computational approaches, as well as the challenges of designing and characterizing molecular assemblies that absorb solar light, transfer electrons between interfaces, and catalyze water-splitting and fuel-forming reactions.

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.

Interpretable design of Ir-free trimetallic electrocatalysts for ammonia oxidation with graph neural networks

The electrochemical ammonia oxidation to dinitrogen as a means for energy and environmental applications is a key technology toward the realization of a sustainable nitrogen cycle. The state-of-the-art metal catalysts including Pt and its bimetallics with Ir show promising activity, albeit suffering from high overpotentials for appreciable current densities and the soaring price of precious metals. Herein, the immense design space of ternary Pt alloy nanostructures is explored by graph neural networks trained on ab initio data for concurrently predicting site reactivity, surface stability, and catalyst synthesizability descriptors. Among a few Ir-free candidates that emerge from the active learning workflow, Pt₃Ru-M (M: Fe, Co, or Ni) alloys were successfully synthesized and experimentally verified to be more active toward ammonia oxidation than Pt, Pt₃Ir, and Pt₃Ru. More importantly, feature attribution analyses using the machine-learned representation of site motifs provide fundamental insights into chemical bonding at metal surfaces and shed light on design strategies for high-performance catalytic systems beyond the d-band center metric of binding sites.

Data-Centric Heterogeneous Catalysis: Identifying Rules and Materials Genes of Alkane Selective Oxidation

Artificial intelligence (AI) can accelerate catalyst design by identifying key physicochemical descriptive parameters correlated with the underlying processes triggering, favoring, or hindering the performance. In analogy to genes in biology, these parameters might be called "materials genes" of heterogeneous catalysis. However, widely used AI methods require big data, and only the smallest part of the available data meets the quality requirement for data-efficient AI. Here, we use rigorous experimental procedures, designed to consistently take into account the kinetics of the catalyst active states formation, to measure 55 physicochemical parameters as well as the reactivity of 12 catalysts toward ethane, propane, and n-butane oxidation reactions. These materials are based on vanadium or manganese redox-active elements and present diverse phase compositions, crystallinities, and catalytic behaviors. By applying the sure-independence-screening-and-sparsifying-operator symbolic-regression approach to the consistent data set, we identify nonlinear property-function relationships depending on several key parameters and reflecting the intricate interplay of processes that govern the formation of olefins and oxygenates: local transport, site isolation, surface redox activity, adsorption, and the material dynamical restructuring under reaction conditions. These processes are captured by parameters derived from N₂ adsorption, X-ray photoelectron spectroscopy (XPS), and near-ambient-pressure in situ XPS. The data-centric approach indicates the most relevant characterization techniques to be used for catalyst design and provides "rules" on how the catalyst properties may be tuned in order to achieve the desired performance.

Heterogeneous catalysis mediated by light, electricity and enzyme via machine learning: Paradigms, applications and prospects

Energy crisis and environmental pollution have become the bottleneck of human sustainable development. Therefore, there is an urgent need to develop new catalysts for energy production and environmental remediation. Due to the high cost caused by blind screening and limited valuable computing resources, the traditional experimental methods and theoretical calculations are difficult to meet with the requirements. In the past decades, computer science has made great progress, especially in the field of machine learning (ML). As a new research paradigm, ML greatly accelerates the theoretical calculation methods represented by first principal calculation and molecular dynamics, and establish the physical picture of heterogeneous catalytic processes for energy and environment. This review firstly summarized the general research paradigms of ML in the discovery of catalysts. Then, the latest progresses of ML in light-, electricity- and enzyme-mediated heterogeneous catalysis were reviewed from the perspective of catalytic performance, operating conditions and reaction mechanism. The general guidelines of ML for heterogeneous catalysis were proposed. Finally, the existing problems and future development trend of ML in heterogeneous catalysis mediated by light, electricity and enzyme were summarized. We highly expect that this review will facilitate the interaction between ML and heterogeneous catalysis, and illuminate the development prospect of heterogeneous catalysis.

Using Machine Learning to Predict Oxygen Evolution Activity for Transition Metal Hydroxide Electrocatalysts

Electrocatalytic water splitting is an attractive way to generate hydrogen and oxygen for obtaining clean energy. Oxygen evolution reaction (OER), as one of the half reactions of oxygen evolution, is kinetically unfavorable involving the transfer of four electrons. Hydroxides are promising candidates for efficient OER electrocatalysts toward water splitting because of their high intrinsic activity and active surface area. However, quantitative prediction of hydroxide electrocatalytic performances from high-dimensional component spaces remains a challenge, severely hindering the performance-oriented precise composition and process design. Herein, we introduce a machine learning-based OER activity prediction method for hydroxide catalysts under extensive doping space for the first time. The relationship among composition, morphology, phase, pH value of the electrolyte, type of the working electrode, and overpotential was successfully fitted by the random forest algorithm. The model shows a good precision on the forecast of new experiments with a mean relative error of 4.74%. Furthermore, a new high-activity hydroxide catalyst Ni_0.77Fe_0.13La_0.1 was rationally designed and experimentally prepared, showing an ultra-low OP of 226 mV for a current density of 10 mA cm^-2. This work provides an effective and novel way for hydroxide electrocatalyst prediction, which can further enhance the electrocatalyst design toward high catalytic performance.

Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery

Electrocatalysts and photocatalysts are key to a sustainable future, generating clean fuels, reducing the impact of global warming, and providing solutions to environmental pollution. Improved processes for catalyst design and a better understanding of electro/photocatalytic processes are essential for improving catalyst effectiveness. Recent advances in data science and artificial intelligence have great potential to accelerate electrocatalysis and photocatalysis research, particularly the rapid exploration of large materials chemistry spaces through machine learning. Here a comprehensive introduction to, and critical review of, machine learning techniques used in electrocatalysis and photocatalysis research are provided. Sources of electro/photocatalyst data and current approaches to representing these materials by mathematical features are described, the most commonly used machine learning methods summarized, and the quality and utility of electro/photocatalyst models evaluated. Illustrations of how machine learning models are applied to novel electro/photocatalyst discovery and used to elucidate electrocatalytic or photocatalytic reaction mechanisms are provided. The review offers a guide for materials scientists on the selection of machine learning methods for electrocatalysis and photocatalysis research. The application of machine learning to catalysis science represents a paradigm shift in the way advanced, next-generation catalysts will be designed and synthesized.

Prediction of Oxygen Evolution Activity for NiCoFe Oxide Catalysts via Machine Learning

Transition metal (such as Fe, Co, and Ni) oxides are excellent systems in the oxygen evolution reaction (OER) for the development of non-noble-metal-based catalysts. However, direct experimental evidence and the physical mechanism of a quantitative relationship between physical factors and oxygen evolution activity are still lacking, which makes it difficult to theoretically and accurately predict the oxygen evolution activity. In this work, a data-driven method for the prediction of overpotential (OP) for (Ni-Fe-Co)O x catalysts is proposed via machine learning. The physical features that are more related to the OP for the OER have been constructed and analyzed. The random forest regression model works exceedingly well on OP prediction with a mean relative error of 1.20%. The features based on first ionization energies (FIEs) and outermost d-orbital electron numbers (DEs) are the principal factors and their variances (δFIE and δDE) exhibit a linearly decreasing correlation with OP, which gives direct guidance for an OP-oriented component design. This method provides novel and promising insights for the prediction of oxygen evolution activity and physical factor analysis in (Ni-Fe-Co)O x catalysts.

A Heuristic Approach to Linking Experimental Descriptors with Product Selectivity in Electrochemical CO2 Reduction

An important challenge in electrochemical CO2 reduction (ECR) is relating experimental conditions to their consequences, particularly in terms of product selectivity. The problem lies in the lack of descriptors which adequately describe the experimental protocols and their associated results. In this study, a machine learning approach is applied to correlate the molar composition of 21 single metals and 23 bimetallic particles, as well as operating parameters, from a large collection of synthetic records compiled from the literature with product selectivity. The decision tree obtained shows the conditions that lead to high desired product selectivity and provides a heuristic insight into its electrochemistry. As such, the data does not provide details. However, machine learning algorithms are capable of identifying hidden patterns in the data, providing a deeper insight into the chemistry involved in product formation in the ECR.

Effectively Increasing Pt Utilization Efficiency of the Membrane Electrode Assembly in Proton Exchange Membrane Fuel Cells through Multiparameter Optimization Guided by Machine Learning

Although proton exchange membrane fuel cells have received attention, the high costs associated with Pt-based catalysts in membrane electrode assemblies (MEAs) remain a huge obstacle for large-scale applications. To solve this urgent problem, the utilization efficiency of Pt in MEAs must be increased. Facing numerous interacting parameters in an attempt to keep experimental costs as low as possible, we innovatively introduce machine learning (ML) to achieve this goal. Nine different ML algorithms are trained on the experimental dataset from our laboratory to precisely predict the performance and Pt utilization (maximum R² = 0.973/0.968). To determine the best synthesis conditions, black-box interpretation methods are applied to provide reliable insights from both qualitative and quantitative perspectives. The optimized choices of ionomer/catalyst ratio, water content, organic solvent, catalyst loading, stirring method, solid content, and ultrasonic spraying flow rate are properly made with few experimental attempts under ML results' guidance. Promising Pt utilization of 0.147 gPt kW^-1 and a power density of 1.02 W cm^-2 are achieved at 0.6 V in a single cell (H₂/air) at an ultralow total loading of 0.15 mg Pt cm^-2. Therefore, this work contributes to the economy of hydrogen energy by paving the way for MEA optimization with complex parameters by ML.

Prospects and challenges for autonomous catalyst discovery viewed from an experimental perspective

Autonomous catalysis research requires elaborate integration of operando experiments into automated workflows. Suitable experimental data for analysis by artificial intelligence can be measured more readily according to standard operating procedures.

Main Descriptors To Correlate Structures with the Performances of Electrocatalysts

Traditional trial and error approaches to search for hydrogen/oxygen redox catalysts with high activity and stability are typically tedious and inefficient. There is an urgent need to identify the most important parameters that determine the catalytic performance and so enable the development of design strategies for catalysts. In the past decades, several descriptors have been developed to unravel structure-performance relationships. This Minireview summarizes reactivity descriptors in electrocatalysis including adsorption energy descriptors involving reaction intermediates, electronic descriptors represented by a d-band center, structural descriptors, and universal descriptors, and discusses their merits/limitations. Understanding the trends in electrocatalytic performance and predicting promising catalytic materials using reactivity descriptors should enable the rational construction of catalysts. Artificial intelligence and machine learning have also been adopted to discover new and advanced descriptors. Finally, linear scaling relationships are analyzed and several strategies proposed to circumvent the established scaling relationships and overcome the constraints imposed on the catalytic performance.

Preparation, Characterization of Graphitic Carbon Nitride Photo-Catalytic Nanocomposites and Their Application in Wastewater Remediation: A Review

Energy crisis and environmental pollution are the major problems of human survival and development. Photocatalytic technology can effectively use solar energy and is prospective to solve the above-mentioned problems. Carbon nitride is a two-dimensional polymer material with a graphite-like structure. It has good physical and chemical stabilities, unique chemical and electronic energy band structures, and is widely used in the field of photocatalysis. Graphitic carbon nitride has a conjugated large π bond structure, which is easier to be modified with other compounds. thereby the surface area and visible light absorption range of carbon nitride-based photocatalytic composites can be insignificantly increased, and interface electron transmission and corresponding photogenerated carriers separation of streams are simultaneously promoted. Therefore, the present study systematically introduced the basic catalytic principles, preparation and modification methods, characterization and calculation simulation of carbon nitride-based photocatalytic composite materials, and their application in wastewater treatment. We also summarized their application in wastewater treatment with the aid of artificial intelligence tools. This review summarized the frontier technology and future development prospects of graphite phase carbon nitride photocatalytic composites, which provide a theoretical reference for wastewater purification.

Principles of Water Electrolysis and Recent Progress in Cobalt-, Nickel-, and Iron-Based Oxides for the Oxygen Evolution Reaction

Water electrolysis that results in green hydrogen is the key process towards a circular economy. The supply of sustainable electricity and availability of oxygen evolution reaction (OER) electrocatalysts are the main bottlenecks of the process for large‐scale production of green hydrogen. A broad range of OER electrocatalysts have been explored to decrease the overpotential and boost the kinetics of this sluggish half‐reaction. Co‐, Ni‐, and Fe‐based catalysts have been considered to be potential candidates to replace noble metals due to their tunable 3d electron configuration and spin state, versatility in terms of crystal and electronic structures, as well as abundance in nature. This Review provides some basic principles of water electrolysis, key aspects of OER, and significant criteria for the development of the catalysts. It provides also some insights on recent advances of Co‐, Ni‐, and Fe‐based oxides and a brief perspective on green hydrogen production and the challenges of water electrolysis.

Molecular and heterogeneous water oxidation catalysts: recent progress and joint perspectives

The recent synthetic and mechanistic progress in molecular and heterogeneous water oxidation catalysts highlights the new, overarching strategies for knowledge transfer and unifying design concepts.

The Hubbard-U correction and optical properties of d0 metal oxide photocatalysts

We report a systematic investigation of individual and multisite Hubbard-U corrections for the electronic, structural, and optical properties of the metal titanate oxide d⁰ photocatalysts SrTiO₃ and rutile/anatase TiO₂. Accurate bandgaps for these materials can be reproduced with local density approximation and generalized gradient approximation exchange-correlation density functionals via a continuous series of empirically derived U^d and U^p combinations, which are relatively insensitive to the choice of functional. On the other hand, lattice parameters are much more sensitive to the choice of U^d and U^p, but in a systematic way that enables the U^d and U^p corrections to be used to qualitatively gauge the extent of self-interaction error in the electron density. Modest U^d corrections (e.g., 4 eV-5 eV) yield the most reliable dielectric response functions for SrTiO₃ and are comparable to the range of U^d values derived via linear response approaches. For r-TiO₂ and a-TiO₂, however, the U^d,p corrections that yield accurate bandgaps fail to accurately describe both the parallel and perpendicular components of the dielectric response function. Analysis of individual U^d and U^p corrections on the optical properties of SrTiO₃ suggests that the most consequential of the two individual corrections is U^d, as it predominately determines the accuracy of the dominant excitation from O-2p to the Ti-3d t_2g/e_g orbitals. U^p, on the other hand, can be used to shift the entire optical response uniformly to higher frequencies. These results will assist high-throughput and machine learning approaches to screening photoactive materials based on d⁰ photocatalysts.

Towards Experimental Handbooks in Catalysis

The “Seven Pillars” of oxidation catalysis proposed by Robert K. Grasselli represent an early example of phenomenological descriptors in the field of heterogeneous catalysis. Major advances in the theoretical description of catalytic reactions have been achieved in recent years and new catalysts are predicted today by using computational methods. To tackle the immense complexity of high-performance systems in reactions where selectivity is a major issue, analysis of scientific data by artificial intelligence and data science provides new opportunities for achieving improved understanding. Modern data analytics require data of highest quality and sufficient diversity. Existing data, however, frequently do not comply with these constraints. Therefore, new concepts of data generation and management are needed. Herein we present a basic approach in defining best practice procedures of measuring consistent data sets in heterogeneous catalysis using “handbooks”. Selective oxidation of short-chain alkanes over mixed metal oxide catalysts was selected as an example.

Quantum-mechanical transition-state model combined with machine learning provides catalyst design features for selective Cr olefin oligomerization

The use of data science tools to provide the emergence of non-trivial chemical features for catalyst design is an important goal in catalysis science. Additionally, there is currently no general strategy for computational homogeneous, molecular catalyst design. Here, we report the unique combination of an experimentally verified DFT-transition-state model with a random forest machine learning model in a campaign to design new molecular Cr phosphine imine (Cr(P,N)) catalysts for selective ethylene oligomerization, specifically to increase 1-octene selectivity. This involved the calculation of 1-hexene : 1-octene transition-state selectivity for 105 (P,N) ligands and the harvesting of 14 descriptors, which were then used to build a random forest regression model. This model showed the emergence of several key design features, such as Cr-N distance, Cr-α distance, and Cr distance out of pocket, which were then used to rapidly design a new generation of Cr(P,N) catalyst ligands that are predicted to give >95% selectivity for 1-octene.

Machine-Learning-Enabled Exploration of Morphology Influence on Wire-Array Electrodes for Electrochemical Nitrogen Fixation

Neural networks, trained on data generated by a microkinetic model and finite-element simulations, expand explorable parameter space by significantly accelerating the predictions of electrocatalytic performance. In addition to modeling electrode reactivity, we use micro/nanowire arrays as a well-defined, easily tuned, and experimentally relevant exemplary morphology for electrochemical nitrogen fixation. This model system provides the data necessary for training neural networks which are subsequently exploited for electrocatalytic material morphology optimizations and explorations into the influence of geometry on nitrogen fixation electrodes, feats untenable without large-scale simulations, on both a global and a local basis.

Non-precious-metal catalysts for alkaline water electrolysis: operando characterizations, theoretical calculations, and recent advances

Advances of non-precious-metal catalysts for alkaline water electrolysis are reviewed, highlighting operando techniques and theoretical calculations in their development.

Artificial-Intelligence-Driven Organic Synthesis-En Route towards Autonomous Synthesis?

AI for chemistry: Automated synthesis can now be performed using an artificial intelligence algorithm to propose the synthetic route and a robotic microfluidic platform to execute the synthesis. This Highlight describes this approach towards small-molecule synthesis and reflects on the significance of this milestone in chemistry.