High-throughput screening and literature data-driven machine learning-assisted investigation of multi-component La₂O₃-based catalysts for the oxidative coupling of methane

Abstract

Multi-component La2O3-based catalysts for oxidative coupling of methane (OCM) were designed based on high-throughput screening (HTS) and literature datasets with multi-output machine learning (ML) approaches including random forest regression (RFR),...

Catalysts informatics: paradigm shift towards data-driven catalyst design

“…This is a successful study on how to receive knowledge from the ML regression field based on the collected data made by different areas and researchers to design the target subject. 28 The systematic HTEs supply a lot of datasets, which is helpful for understanding the trends of the data. Thus, identification of the next subject and determining the method to resolve the target would be possible from analyzing the HTE data characteristics.…”

Leveraging machine learning engineering to uncover insights into heterogeneous catalyst design for oxidative coupling of methane

“…The amounts of the target gases H 2 , O 2 , N 2 , CH 4 , CO, CO 2 , C 2 H 4 , and C 2 H 6 were estimated according to our earlier reports using N 2 as an internal standard. 39,40…”

“…† Multicomponent M1-M2-M3 supported catalysts were prepared with co-impregnation using a parallel synthesis method. 39,40 All elemental resources (0.20 mmol for each) and support materials (1.0 g) were placed in a glass tube (φ18) with 6 mL of highly purified water (18.2 MΩ × cm), and were mixed at 50 °C for 6 h under vigorous stirring with a magnetic stirrer. The slurry was centrifuged under vacuum at 80 °C and was dried overnight at 110 °C.…”

Machine Learning-Aided Catalyst Modification in Oxidative Coupling of Methane via Manganese Promoter

“…Conventional NaMnW/SiO 2 was prepared with typical coimpregnation as a standard catalyst, which can afford nice C 2 yield at OCM under not only O 2 -rich conditions ,, but also O 2 -lean conditions − in a conventional fixed-bed reactor. , Both 0.269 g of Mn­(NO 3 ) 2 ·6H 2 O and 0.155 g of Na 2 WO 4 ·2H 2 O were resolved in 300 mL of deionized water in a round bottle-necked flask. Then, 2.5 g of SiO 2 was added with vigorous stirring.…”

“…Because of progress in the development of data science analytical techniques and machine learning (ML) engineering, there remains an ever-increasing interest in reaching new findings related to catalyst materials , and catalysis mechanisms − based on data science-aided approaches at catalyst investigations of prediction and elucidation. Particularly, literature-driven and high-throughput screening (HTS) experiment-driven ML approaches have received much attention. − The former is based on conventional knowledge of different scientists from various data fields obtained using different reactor concepts and catalyst preparation methodologies. This mode of inquiry provides a wider scope of data than independently accumulated experiment data.…”