Search

The empirical aspect of descriptor design in catalyst informatics, particularly when confronted with limited data, necessitates adequate prior knowledge for delving into unknown territories, thus presenting a logical contradiction. This study introduces a technique for automatic feature engineering (AFE) that works on small catalyst datasets, without reliance on specific assumptions or pre-existing knowledge about the target catalysis when designing descriptors and building machine-learning models. This technique generates numerous features through mathematical operations on general physicochemical features of catalytic components and extracts relevant features for the desired catalysis, essentially screening numerous hypotheses on a machine. AFE yields reasonable regression results for three types of heterogeneous catalysis: oxidative coupling of methane (OCM), conversion of ethanol to butadiene, and three-way catalysis, where only the training set is swapped. Moreover, through the application of active learning that combines AFE and high-throughput experimentation for OCM, we successfully visualize the machine's process of acquiring precise recognition of the catalyst design. Thus, AFE is a versatile technique for data-driven catalysis research and a key step towards fully automated catalyst discoveries. Descriptor design in catalyst informatics necessitates adequate prior knowledge for delving into unknown territories, particularly when confronted with limited data, thus presenting a logical contradiction. Here, the authors report a technique for automatic feature engineering that works on small catalyst datasets without reliance on pre-existing knowledge about the target catalysis. [ABSTRACT FROM AUTHOR]

Unveiling the details of the mechanisms of a chemical reaction is a difficult task as reaction mechanisms are strongly coupled with reaction conditions. Here, catalysts informatics combined with high‐throughput experimental data is implemented to understand the oxidative coupling of methane (OCM) reaction. In particular, pairwise correlation and data visualization are performed to reveal the relation between reaction conditions and selectivity/conversion. In addition, machine learning is used to fill the gap between experimental data points; thus, a more detailed understanding of the OCM reaction against reaction conditions can be achieved. Therefore, catalysts informatics is proposed for understanding the details of the reaction mechanism, thereby aiding reaction design. [ABSTRACT FROM AUTHOR]

In the oxidative coupling of methane (OCM), the activation of methane and the suppression of deep oxidation are in a persistent trade‐off relationship, and a catalyst design strategy that balances the activity and the selectivity is desired. In this study, we analyzed a random catalyst dataset for OCM that was earlier obtained by high‐throughput experimentation, and extracted heuristics such as elements, supports, and their combinations related to methane activation at a low temperature and selective formation of C2 compounds at a high temperature. The obtained heuristics were used for catalyst development. The most effective was the use of a mixed support between La2O3 and BaO, which improved the low‐temperature activity, the high‐temperature selectivity, as well as the maximum C2 yield. It was considered that La2O3 acted as a heater and helped low‐temperature operation of BaO, which is highly selective but not active at a low temperature. [ABSTRACT FROM AUTHOR]

The combination of deep learning and high‐throughput experiments is proposed for the direct design of heterogeneous catalysts in the oxidative coupling of methane (OCM) reaction. Deep learning predicts 20 active catalysts from high‐throughput 12,708 OCM experimental data where 19 of the predicted 20 catalysts have not been previously reported. The predicted 20 catalysts are then evaluated through high‐throughput experiments where a highly active unreported catalyst Ti−Na2WO4/TiO2 is discovered. Ti−Na2WO4/TiO2 results in a high C2 yield of 18.8 % where the maximum C2 yield is reported to be approximately 20 % within the 12,708 OCM data. Furthermore, the experimental conditions predicted for Ti−Na2WO4/TiO2 are also reproduced by high‐throughput experiment. Thus, deep learning demonstrates that both catalysts and experimental conditions can be simultaneously explored for designing catalysts. More importantly, deep learning assisted catalysts search is found to dramatically increase the chances of finding active catalysts where 9 out of 20 predicted catalysts result in a C2 yield over 15 %. Therefore, the combination of deep learning with high‐throughput experiments is proposed to be an effective strategy for the direct design of catalysts. [ABSTRACT FROM AUTHOR]

Machine learning (ML) predictions for the oxidative coupling of methane (OCM) are evaluated under experiment situation. The ML protocol has sparked new motivation for trial runs of 96 kinds of metal‐supported catalysts based not only on scientists' experiences but also on data presented in earlier reports of the literatures and obtained during verification. Our protocol discovers unreported catalyst combinations for OCM reactions from data expanding upon three decades of research, where various numbers of catalysts are predicted and confirmed to perform better than blank data. Nevertheless, the target on C2 yield for the OCM reaction remains as a challenging subject: i. e. higher than 30 %. Revisiting data reported in the literature reveals that different reactor systems and/or specific methods are used in the original data for achieving higher than 30 % C2 yield. Such specialties are attributed to the inadequacy of a literature‐data‐driven ML approach at the present situation. Furthermore, classification of experimental data has indicated target C2 yield values and trends toward CH4 and O2 conversion and product selectivity in high dimensions can improve future ML prediction. These findings are greatly beneficial for the next stage of development to find a global descriptor to improve ML prediction accuracy beyond interpolation filling. [ABSTRACT FROM AUTHOR]

The challenge in catalytic reactions lies within its complexity coming from high dimensional experimental factors. In order to solve such complexity, machine learning is implemented to treat experimental conditions in high dimensions. Oxidative coupling of methane, methane to C2 compounds (ethylene and ethane), is chosen as the prototype reaction where 156 data consisting of various experimental conditions is prepared. Machine learning reveals that the relationship between experimental conditions and C2 yield is non‐linear matter. In particular, extreme tree regression is found to accurately reproduce the experimental data. In addition, machine learning predictions can be a good indicator for designing experiments. Thus, machine learning can be a powerful approach towards understanding and determining experimental conditions in high dimension. [ABSTRACT FROM AUTHOR]

Abstract: Catalysts for oxidative coupling of methane (OCM) are explored using data science and 1868 OCM catalysts from literature data. Machine learning reveals the descriptors responsible for determining the C2 yield produced during the OCM reaction. Trained machine predicts 56 undiscovered catalysts with corresponding conditions for OCM reactions achieving a C2 yield over 30 %. First principle calculations are implemented to evaluate the predicted catalysts where the activation of CH4, CH3, and O2 are confirmed with the predicted catalysts for the OCM reaction. Thus, machine learning is proven to be an effective approach for discovering hidden catalysts and should accelerate the catalyst design process in general. [ABSTRACT FROM AUTHOR]

Keywords: Machine learning prediction; Oxidative coupling of methane; Literature data; C2 yield; Verification EN Machine learning prediction Oxidative coupling of methane Literature data C2 yield Verification 5836 5836 1 12/07/20 20201204 NES 201204 B The Cover Feature b illustrates collaborations of data scientists and catalyst scientists to break through the C2 yield higher than 30% for the oxidative coupling of methane (OCM) based on machine learning (ML) predictions with literature data. Machine learning prediction, Oxidative coupling of methane, Literature data, C2 yield, Verification. [Extracted from the article]

• A variety of Mn–Na 2 WO 4 catalysts were prepared using different support materials. • The OCM performance was evaluated via high-throughput experimentation. • The supports affect the formation and dispersion of Na 2 WO 4. • The dispersion is important for low-temperature activation of methane. The oxidative coupling of methane is an effective approach for directly upgrading methane to valuable products. Among known OCM catalysts, Mn–Na 2 WO 4 /SiO 2 is a promising candidate for an industrial application with superior catalytic performance and high stability, where the performance of Mn–Na 2 WO 4 significantly depends on the choice of support materials. Here, a variety of Mn–Na 2 WO 4 catalysts were prepared using different Si-based materials as supports. The OCM performance of these catalysts was evaluated by using a high-throughput screening instrument that we had previously developed. The relationship between the catalyst performance and the choice of support materials was studied in detail on the basis of characterization using Raman spectroscopy, X-ray diffraction, elemental mapping, and X-ray photoelectron spectroscopy. [Display omitted] [ABSTRACT FROM AUTHOR]