Accelerated discovery of multi-elemental reverse water-gas shift catalysts using extrapolative machine learning approach

Designing novel catalysts is key to solving many energy and environmental challenges. Despite the promise that data science approaches, including machine learning (ML), can accelerate the development of catalysts, truly novel catalysts have rarely been discovered through ML approaches because of one of its most common limitations and criticisms-the assumed inability to extrapolate and identify extraordinary materials. Herein, we demonstrate an extrapolative ML approach to develop new multi-elemental reverse water-gas shift catalysts. Using 45 catalysts as the initial data points and performing 44 cycles of the closed loop discovery system (ML prediction + experiment), we experimentally tested a total of 300 catalysts and identified more than 100 catalysts with superior activity compared to those of the previously reported high-performance catalysts. The composition of the optimal catalyst discovered was Pt(3)/Rb(1)-Ba(1)-Mo(0.6)-Nb(0.2)/TiO2. Notably, niobium (Nb) was not included in the original dataset, and the catalyst composition identified was not predictable even by human experts.

NiFe2O4@SiO2-Cu as a novel and efficient magnetically recoverable nanocatalyst for regioselective synthesis of β-thiol-1,2,3-triazoles under benign conditions

A green, mild and eco-friendly approach for the three component one-pot regioselective synthesis of 1,2,3-triazoles from thiiranes has been introduced in the presence of NiFe2O4@SiO2-Cu as a new and recoverable nanocatalyst. First, the NiFe2O4 nanoparticles have been produced through a solid-state reaction of hydrated nickel sulfate, hydrated iron(iii) nitrate, NaOH and NaCl salts, and then calcined at 700 °C. Next, in order to protect the ferrite particles from oxidation and aggregation, the NiFe2O4 was core-shelled using tetraethyl orthosilicate (TEOS) and converted to NiFe2O4@SiO2. Finally, the novel NiFe2O4@SiO2-Cu nanocomposite was successfully prepared by adding copper(ii) chloride solution and solid potassium borohydride. The catalyst has been characterized by FT-IR, SEM, EDX, VSM, ICP-OES, TEM and XRD techniques. The 1,3-dipolar cyclization of 1,2,3-triazoles was performed successfully in water at room temperature in high yields. The recoverability and reusability of the heterogeneous NiFe2O4@SiO2-Cu have also been investigated using VSM, SEM and FT-IR analyses. The catalyst was used four times in consecutive runs without considerable loss of activity. The presented procedure provides significant benefits such as using water as a green solvent, absence of hazardous organic solvents, high yields, benign conditions and recyclability of the magnetic catalyst.

Mesokinetics as a Tool Bridging the Microscopic-to-Macroscopic Transition to Rationalize Catalyst Design

Heterogeneous catalysis is the workhorse of the chemical industry, and a heterogeneous catalyst possesses numerous active sites working together to drive the conversion of reactants to desirable products. Over the decades, much focus has been placed on identifying the factors affecting the active sites to gain deep insights into the structure-performance relationship, which in turn guides the design and preparation of more active, selective, and stable catalysts. However, the molecular-level interplay between active sites and catalytic function still remains qualitative or semiquantitative, ascribed to the difficulty and uncertainty in elucidating the nature of active sites for its controllable manipulation. Hence, bridging the microscopic properties of active sites and the macroscopic catalytic performance, that is, microscopic-to-macroscopic transition, to afford a quantitative description is intriguing yet challenging, and progress toward this promises to revolutionize catalyst design and preparation.In this Account, we propose mesokinetics modeling, for the first time enabling a quantitative description of active site characteristics and the related mechanistic information, as a versatile tool to guide rational catalyst design. Exemplified by a pseudo-zero-order reaction, the kinetics derivation from the Pt particle size-sensitive catalytic activity and size-insensitive activation energy suggests only one type of surface site as the dominant active site, in which the Pt(111) with almost unchanged turnover frequency (TOF₁₁₁) is further identified as the dominating active site. Such a method has been extended to identify and quantify the number (N_i) of active sites for various thermo-, electro-, and photocatalysts in chemical synthesis, hydrogen generation, environment application, etc. Then, the kinetics derivation from the kinetic compensation effects suggests a thermodynamic balance between the activation entropy and enthalpy, which exhibit linear dependences on Pt charge. Accordingly, the Pt charge can serve as a catalytic descriptor for its quantitative determination of TOF_i. This strategy has been further applied to Pt-catalyzed CO oxidation with nonzero-order reaction characteristic by taking the site coverages of surface species into consideration.Hence, substituting the above statistical correlations of N_i and TOF_i into the rate equation R = ∑N_i × TOF_i offers the mesokinetics model, which can precisely predict catalytic function and screen catalysts. Finally, based on the disentanglement of the factors underlying Pt electronic structures, a de novo strategy, from the interfacial charge distribution to reaction mechanism, kinetics, and thermodynamics parameters of the rate-determining step, and ultimately catalytic performance, is developed to map the unified mechanistic and kinetics picture of reaction. Overall, the mesokinetics not only demonstrates much potential to elucidate the quantitative interplay between active sites and catalytic activity but also provides a new research direction in kinetics analysis to rationalize catalyst design.

Systematic Data-Driven Modeling of Bimetallic Catalyst Performance for the Hydrogenation of 5-Ethoxymethylfurfural with Variable Selection and Regularization

Catalyst development for biorefining applications involves many challenges. Mathematical modeling can be seen as an essential tool in assisting to explain catalyst performance. This paper presents studies on several machine learning (ML) methods that can model the performance of heterogeneous catalysts with relevant descriptors. A systematic approach for selecting the most appropriate ML method is taken with focus on the variable selection. Regularization algorithms were applied to variable selection. Several different candidate model structures were compared in modeling with interpretation of results. The systematic modeling approach presented aims to highlight the necessary tools and aspects to unexperienced users of ML. Literature datasets for the hydrogenation of 5-ethoxymethylfurfural with simple bimetal catalysts, including main metals and promoters, were studied with the addition of catalyst descriptors found in the literature. Good results were obtained with the best models for estimating conversion, selectivity, and yield with correlations between 0.90 and 0.98. The best identified model structures were support vector regression, Gaussian process regression, and decision tree methods. In general, the use of variable selection procedures was found to improve the performance of models. The modeling methods applied thus seem to exhibit a strong potential in aiding catalyst development based mainly on the information content of descriptor datasets.

Applications of Machine Learning in Alloy Catalysts: Rational Selection and Future Development of Descriptors

At present, alloys have broad application prospects in heterogeneous catalysis, due to their various catalytic active sites produced by their vast element combinations and complex geometric structures. However, it is the diverse variables of alloys that lead to the difficulty in understanding the structure-property relationship for conventional experimental and theoretical methods. Fortunately, machine learning methods are helpful to address the issue. Machine learning can not only deal with a large number of data rapidly, but also help establish the physical picture of reactions in multidimensional heterogeneous catalysis. The key challenge in machine learning is the exploration of suitable general descriptors to accurately describe various types of alloy catalysts, which help reasonably design catalysts and efficiently screen candidates. In this review, several kinds of machine learning methods commonly used in the design of alloy catalysts is introduced, and the applications of various reactivity descriptors corresponding to different alloy systems is summarized. Importantly, this work clarifies the existing understanding of physical picture of heterogeneous catalysis, and emphasize the significance of rational selection of universal descriptors. Finally, the development of heterogeneous catalytic descriptors for machine learning are presented.

Functional and Material Properties in Nanocatalyst Design: A Data Handling and Sharing Problem

(1) Background: Properties and descriptors are two forms of molecular in silico representations. Properties can be further divided into functional, e.g., catalyst or drug activity, and material, e.g., X-ray crystal data. Millions of real measured functional property records are available for drugs or drug candidates in online databases. In contrast, there is not a single database that registers a real conversion, TON or TOF data for catalysts. All of the data are molecular descriptors or material properties, which are mainly of a calculation origin. (2) Results: Here, we explain the reason for this. We reviewed the data handling and sharing problems in the design and discovery of catalyst candidates particularly, material informatics and catalyst design, structural coding, data collection and validation, infrastructure for catalyst design and the online databases for catalyst design. (3) Conclusions: Material design requires a property prediction step. This can only be achieved based on the registered real property measurement. In reality, in catalyst design and discovery, we can observe either a severe functional property deficit or even property famine.

Site-dependent selectivity in oxidation reactions on single Pt nanoparticles

Site-dependent selectivity in oxidation reactions on Pt nanoparticles was identified by conducting IR nanospectroscopy measurements while using allyl-functionalized N-heterocyclic carbenes (allyl-NHCs) as probe molecules.

A meta-analysis of catalytic literature data reveals property-performance correlations for the OCM reaction

Decades of catalysis research have created vast amounts of experimental data. Within these data, new insights into property-performance correlations are hidden. However, the incomplete nature and undefined structure of the data has so far prevented comprehensive knowledge extraction. We propose a meta-analysis method that identifies correlations between a catalyst’s physico-chemical properties and its performance in a particular reaction. The method unites literature data with textbook knowledge and statistical tools. Starting from a researcher’s chemical intuition, a hypothesis is formulated and tested against the data for statistical significance. Iterative hypothesis refinement yields simple, robust and interpretable chemical models. The derived insights can guide new fundamental research and the discovery of improved catalysts. We demonstrate and validate the method for the oxidative coupling of methane (OCM). The final model indicates that only well-performing catalysts provide under reaction conditions two independent functionalities, i.e. a thermodynamically stable carbonate and a thermally stable oxide support.

The incomplete nature and undefined structure of the existing catalysis research data has prevented comprehensive knowledge extraction. Here, the authors report a novel meta-analysis method that identifies correlations between a catalyst’s physico-chemical properties and its performance in a particular reaction.

Descriptor–property relationships in heterogeneous catalysis: exploiting synergies between statistics and fundamental kinetic modelling

Combined kinetic and statistical approach to shed light on the link between kinetically-relevant descriptors and easily tuneable catalyst properties.

Machine learning meets volcano plots: computational discovery of cross-coupling catalysts

The application of modern machine learning to challenges in atomistic simulation is gaining attraction. We present new machine learning models that can predict the energy of the oxidative addition process between a transition metal complex and a substrate for C-C cross-coupling reactions. In turn, this quantity can be used as a descriptor to estimate the activity of homogeneous catalysts using molecular volcano plots. The versatility of this approach is illustrated for vast libraries of organometallic catalysts based on Pt, Pd, Ni, Cu, Ag, and Au combined with 91 ligands. Out-of-sample machine learning predictions were made on a total of 18 062 compounds leading to 557 catalyst candidates falling into the ideal thermodynamic window. This number was further refined by searching for candidates with an estimated price lower than 10 US$ per mmol. The 37 catalyst finalists are dominated by palladium phosphine ligand combinations but also include the earth abundant transition metal (Cu) with less common ligands. Our results indicate that modern statistical learning techniques can be applied to the computational discovery of readily available and promising catalyst candidates.

Facile Synthesis of a Novel Hierarchical ZSM-5 Zeolite: A Stable Acid Catalyst for Dehydrating Glycerol to Acrolein

Catalytic biomass conversion is often hindered by coking. Carbon compounds cover active surface and plug pores, causing catalyst deactivation. Material design at the nanoscale allows tailoring of the catalytic activity and stability. Here, we report a simple synthesis of nanosized ZSM‐5 materials by using a silicalite‐1 seeding suspension. ZSM‐5 crystals were grown from a deionized silica source in the presence of ammonia. By using silicalite‐1 seeds, crystalline ZSM‐5 is synthesized without any structure‐directing agent. This method allows parallel preparation of a range of ZSM‐5 samples, eliminating time‐consuming ion‐exchange steps. Mesoporosity is introduced by formation of intercrystallite voids, owing to nanocrystal agglomeration. The effects of crystal sizes and morphologies are then evaluated in the catalytic dehydration of glycerol to acrolein, with results compared against commercial ZSM‐5. The most active nanosized ZSM‐5 catalysts were five times more stable compared with commercial ZSM‐5, giving quantitative conversion and twice the acrolein yield compared with the commercial catalyst. The influence of the catalyst structure on the chemical diffusion and the resistance to coking are discussed.

Predicting the performance of oxidation catalysts using descriptor models

Mix & match: we show that combining simple heuristic models with experimental validation is an effective method for optimising supported mixed oxide catalysts.

Machine-learning prediction of the d-band center for metals and bimetals

The d-band centers for eleven metals and their pairwise bimetals for two different structures (1% metal doped- or overlayer-covered metal surfaces) are statistically predicted using machine learning methods from readily available values as descriptors for the target metals.

Catalytic acetoxylation of lactic acid to 2-acetoxypropionic acid, en route to acrylic acid

We present an alternative synthetic route to acrylic acid, starting from the platform chemical lactic acid and using heterogeneous catalysis.

Heterogeneous biomimetic aerobic synthesis of 3-iodoimidazo[1,2-a]pyridines via CuOx/OMS-2-catalyzed tandem cyclization/iodination and their late-stage functionalization

Heterogeneous catalysis performs well in biomimetic oxidation to generate a low-energy pathway for the synthesis of 3-iodoimidazo[1,2-a]pyridines.