Indirect design of OCM catalysts through machine learning of catalyst surface oxygen species

Catalysts for oxidative coupling of methane (OCM) were designed through machine learning of a property of surface oxygen species on the basis of the knowledge that catalytic performance for the OCM is affected by catalyst surface oxygen species. To select the property of the surface oxygen species used as a guide of catalyst design via machine learning, the relationships between the total yield of ethylene and ethane (C-2 yield) and the O1s X-ray photoelectron spectral (XPS) features of the 51 catalysts prepared in our previous study were evaluated. Since a weak correlation was seen between the C-2 yield and the O1s XPS peak energy of CO32- species on the catalyst surface, the CO32- peak energy was chosen as the guiding parameter of catalyst design in this work. Machine learning was then performed on the dataset consisting of the CO32- peak energy (objective variable) and the physical quantities of elements in the catalysts (descriptor) to find the important physical quantities determining the CO32- peak energy. According to the important physical quantities, catalyst compositions were predicted. Based on the predicted compositions, 28 catalysts were synthesized to verify that their CO32- peak energies were in the range where high catalytic performance can be expected. Furthermore, the catalysts are tested for the OCM reaction. As a result, Ba-In-Rb/La2O3 was found as a new highly active OCM catalyst having compatible activity to the conventional Mn-Na2WO4/SiO2 catalyst. Therefore, it was demonstrated that the indirect catalyst through machine learning of the catalyst surface property is effective for development of catalysts.

Automated summary

Catalysts for oxidative coupling of methane (OCM) were designed through machine learning of the property of surface oxygen species. The CO32- peak energy was chosen as the guiding parameter and important physical quantities determining the CO32- peak energy were identified through machine learning. Synthesized catalysts were found to have high catalytic performance based on their predicted compositions, and a new highly active OCM catalyst was discovered.