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

Abstract

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.

Selective Valorization of CO2 towards Valuable Hydrocarbons through Methanol‐mediated Tandem Catalysis

“…As discussed earlier, the selection of the components and structure of a tandem catalyst can significantly impact the hydrocarbon product distribution. Given the vast number of possible configurations for such catalysts, incorporating data‐driven machine learning (ML) techniques can be a valuable approach for exploring the entire chemical space and expediting the identification of the optimal catalyst for efficient tandem CO 2 hydrogenation [172–173] . However, this requires the availability of high‐quality data that accurately captures the variability in catalyst structure and product yield.…”

“…Given the vast number of possible configurations for such catalysts, incorporating datadriven machine learning (ML) techniques can be a valuable approach for exploring the entire chemical space and expediting the identification of the optimal catalyst for efficient tandem CO 2 hydrogenation. [172][173] However, this requires the availability of high-quality data that accurately captures the variability in catalyst structure and product yield. Once a suitable dataset has been established, ML algorithms such as artificial neural networks (ANNs) or decision trees can be utilized to model the complex, highdimensional relationships between catalyst structure and product yield.…”

Interpretable Machine Learning Models for Practical Antimonate Electrocatalyst Performance

“…The complexity of real oxide electrocatalysts in terms of the electrochemical interface, surface structure, oxygen vacancies, and support effects render a purely atomistic‐based first‐principles prediction of catalyst performance (i. e., catalytic activity, selectivity, and stability) challenging. Empirical models [11–14] aim to predict catalyst performance under such experimental or realistic conditions as well as to potentially allow for an optimization of e. g. synthesis conditions or catalyst composition. Stochastic techniques such as design of experiments and Bayesian optimization machine‐learning approaches can be applied for optimization of such catalyst parameters [15–17] .…”