31 May 2021 in ChemCatChem
We have constructed and analyzed an updated dataset consisting of 4759 experimental datapoints for the oxidative coupling of methane (OCM) reaction based on literature data reported before 2020 (∼2019) using machine learning (ML) methods. Several ML methods, including random forest regression (RFR), extra trees regression (ETR), and gradient boosting regression with XGBoost (XGB), were used in conjunction with our proposed approach, in which elemental features are used as input representations rather than inputting the catalyst compositions directly. A recent research trend, namely, the extensive exploration of Mn/Na2WO4/SiO2 catalyst systems in recent years due to their high activity and durability, was clearly reflected in the dataset analysis. An ML model for the prediction of the reaction outcome (C2 yield) was successfully developed, and feature importance scores and SHapley Additive exPlanations (SHAP) values were calculated based on ETR and XGB, respectively, to identify the input variables with the greatest influence on the catalyst performance and observe how these important variables affect the C2 yield in the OCM. The discovery and optimization of catalytic processes using ML as a “surrogate” model were explored, and promising catalytic system candidates for the OCM reaction were identified. Notably, the developed ML model predicted catalysts containing elements that do not appear in the OCM dataset. This clearly demonstrates desirably high potential of our ML model to enable extrapolative predictions for ML‐aided future catalysis research.
21 September 2023 in Nature Communications
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.
10 May 2021 in Catalysis Science & Technology
Pt/MoOx/TiO2 shows excellent catalytic performance for the reverse water-gas shift reaction at 250 °C via reverse Mars–van Krevelen mechanism.
2 August 2022 in ACS Catalysis
20 October 2023 in Environmental Science & Technology
1 August 2023 in ACS Catalysis
Low temperature and high pressure are thermodynamically more favorable conditions to achieve high conversion and high methanol selectivity in CO2 hydrogenation. However, low-temperature activity is generally very poor due to the sluggish kinetics, and thus, designing highly selective catalysts active below 200 °C is a great challenge in CO2-to-methanol conversion. Recently, Re/TiO2 has been reported as a promising catalyst. We show that Re/TiO2 is indeed more active in continuous and high-pressure (56 and 331 bar) operations at 125-200 °C compared to an industrial Cu/ZnO/Al2O3 catalyst, which suffers from the formation of methyl formate and its decomposition to carbon monoxide. At lower temperatures, precise understanding and control over the active surface intermediates are crucial to boosting conversion kinetics. This work aims at elucidating the nature of active sites and active species by means of in situ/operando X-ray absorption spectroscopy, Raman spectroscopy, ambient-pressure X-ray photoelectron spectroscopy (AP-XPS), and diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS). Transient operando DRIFTS studies uncover the activation of CO2 to form active formate intermediates leading to methanol formation and also active rhenium carbonyl intermediates leading to methane over cationic Re single atoms characterized by rhenium tricarbonyl complexes. The transient techniques enable us to differentiate the active species from the spectator one on TiO2 support, such as less reactive formate originating from spillover and methoxy from methanol adsorption. The AP-XPS supports the fact that metallic Re species act as H2 activators, leading to H-spillover and importantly to hydrogenation of the active formate intermediate present over cationic Re species. The origin of the unique reactivity of Re/TiO2 was suggested as the coexistence of cationic highly dispersed Re including single atoms, driving the formation of monodentate formate, and metallic Re clusters in the vicinity, activating the hydrogenation of the formate to methanol.