Cover Feature: Revisiting Machine Learning Predictions for Oxidative Coupling of Methane (OCM) based on Literature Data (ChemCatChem 23/2020). Issue 23 (9th November 2020)

• Record Type: Journal Article
• Authors: Nishimura, Shun; Ohyama, Junya; Kinoshita, Takaaki; Dinh Le, Son; Takahashi, Keisuke
• Is Part Of: ChemCatChem. Volume 12:Issue 23(2020)
• Page Start: 5836
• Page End: 5836
• Publication Date: 2020-11-09
• Subjects: Machine learning prediction -- Oxidative coupling of methane -- Literature data -- C2 yield -- Verification; Catalysis -- Periodicals; 541.39505
• DOI: 10.1002/cctc.202001722
• Languages: English
• ISSNs: 1867-3880

Abstract

Abstract : The Cover Feature 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. In their Communication, S. Nishimura et al. explain that the ML protocol has sparked new interest for trial experiments based on scientists' experiences and literature data to discover unreported catalyst combinations for OCM reactions. Nevertheless, the target C2 yield remains a challenging subject. Revision of the ML protocols based on literature data reveals that the characteristics of the original data lead to inadequacy of the literature‐data‐driven ML approach, and proposed the improvement for future ML predictions beyond interpolation filling. More information can be found in the Communication by S. Nishimura et al.