Unveiling gas‐phase oxidative coupling of methane via data analysis

Abstract

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.

Sulfur oxidative coupling of methane process development and its modeling via machine learning

“…This protocol treats the elemental features of a catalyst as inputs, without the need of directly inputting the catalyst, resulting in high prediction accuracy. Over the last lustrum , the group of Takahashi have published several papers on ML applied to OCM 24,28–31 . For example, they used different ML techniques to predict the effect of the OCM reaction conditions on the C 2 yield, revealing the nonlinearity between experimental conditions and C 2 yield 31 .…”

“…In 2019, this group reported the use of a random forest regression model to describe the dependence of the C 2 yield on reaction conditions using a OCM dataset, constructed by high‐throughput experimental screening of the performance of 20 catalysts in 216 reaction conditions 30 . More recently instead, Ishioka et al used support vector regression to fill the gap between experimental data points by interpolation to obtain a better understanding of the relation between the selectivity and CH 4 conversion against the OCM reaction conditions 29 . An approach similar to the one here reported has been recently applied by Siritanaratkul to determine the limitation of ML for yield prediction of OCM 32 …”

“…Over the last lustrum, the group of Takahashi have published several papers on ML applied to OCM. 24,[28][29][30][31] For example, they used different ML techniques to predict the effect of the OCM reaction conditions on the C 2 yield, revealing the nonlinearity between experimental conditions and C 2 yield. 31 In particular, the authors found that extreme tree regression models accurately reproduced the experimental data.…”

Noncatalytic Oxidative Coupling of Methane (OCM): Gas-Phase Reactions in a Jet Stirred Reactor (JSR)

“…Luo et al ( 35 ) analyzed the gas-phase reaction network over the Li/MgO catalyst with the detection of gas-phase intermediate species. Ishioka et al ( 36 ) also used a machine learning technique to better understand the gas-phase performances against operating conditions from the high-throughput experimental data. In fact, since surface species are difficult to observe or identify, OCM surface kinetics are indirectly investigated experimentally by extrapolating conversion rates and selectivity at zero methane conversion for initiation steps 8 , 12 , 37 − 39 or by applying isotopic techniques to identify the pathways of products.…”

“…Luo et al analyzed the gas-phase reaction network over the Li/MgO catalyst with the detection of gas-phase intermediate species. Ishioka et al also used a machine learning technique to better understand the gas-phase performances against operating conditions from the high-throughput experimental data. In fact, since surface species are difficult to observe or identify, OCM surface kinetics are indirectly investigated experimentally by extrapolating conversion rates and selectivity at zero methane conversion for initiation steps ,,− or by applying isotopic techniques to identify the pathways of products. ,,− Other than these, the parameters of surface elementary reactions (sticking coefficient and activation energy) are estimated mostly via density functional theory (DFT) calculations − or Polanyi relationships. ,,,, It is challenging to precisely predict the entire surface reaction mechanism for OCM, which indicates the critical role of an accurate and reliable gas-phase model over the entire mechanism.…”