Data-Driven Identification of the Reaction Network in Oxidative Coupling of the Methane Reaction via Experimental Data
Data-Driven Identification of the Reaction Network in Oxidative Coupling of the Methane Reaction via Experimental Data
复制标题
DOI：
10.1021/acs.jpclett.9b03678
复制
发表时间：
2020-02-06
影响因子：
5.7
通讯作者：
Takahashi, Keisuke
中科院分区：
文献类型：
--
作者：
Miyazato, Itsuki;Nishimura, Shun;Takahashi, Keisuke
对于实验和计算来说，识别化学反应的细节都是一件具有挑战性的事情。本文利用一系列实验数据和数据科学技术对甲烷氧化偶联(OCM)的反应途径进行了研究，其中数据使用了各种可视化技术进行分析。数据可视化、成对关联和机器学习揭示了实验条件与OCM反应中CO、CO2、C2H4、C2H6和H-2选择性之间的关系。更重要的是，OCM反应的反应网络是基于机器学习提供的分数和实验数据构建的。特别是，提出的反应图不仅包含化合物，还包含实验条件。因此，原则上可以通过一系列实验数据来实现对化学反应的数据驱动识别，从而导致更高效的实验设计和催化剂开发。
Identifying details of chemical reactions is a challenging matter for both experiments and computations. Here, the reaction pathway in oxidative coupling of methane (OCM) is investigated using a series of experimental data and data science techniques in which data are analyzed using a variety of visualization techniques. Data visualization, pairwise correlation, and machine learning unveil the relationships between experimental conditions and the selectivities of CO, CO2, C2H4, C2H6, and H-2 in the OCM reaction. More importantly, the reaction network for the OCM reaction is constructed on the basis of the scores provided by machine learning and experimental data. In particular, the proposed reaction map not only contains the chemical compound but also contains experimental conditions. Thus, data-driven identification of chemical reactions can be achieved in principle via a series of experimental data, leading to more efficient experimental design and catalyst development.