Machine learning-aided catalyst screening and multi-objective optimization for the indirect CO₂ hydrogenation to methanol and ethylene glycol process

Abstract

Indirect CO2 hydrogenation to methanol and ethylene glycol is a green, efficient, and economical technology for converting CO2 into high-value chemicals to address the intractable environmental crisis caused by CO2...

Ensemble learning to predict solar-to-hydrogen energy conversion based on photocatalytic water splitting over doped TiO2

“…In recent years, ML methods have been successfully applied in various interdisciplines, including natural language processing, 16,17 image processing, 18 medical diagnostics, 19,20 and materials informatics. 21,22 Yang et al 23 used random forest regression, support vector machine regression, and neural network models to predict the conversion ratio of ethylene carbonate and the yield of methanol and ethylene glycol from indirect CO 2 hydrogenation technology. Catalytic modeling through ML technology can avoid the complex catalytic mechanism and find the hidden relationship between the experimental conditions, which helps researchers reduce the blindness of experiments and accelerate the development of new catalysts.…”

An auto‐configurable machine learning framework to optimize and predict catalysts for CO2 to light olefins process

“…For example, Ye et al 12 believed that machine learning is a promising and effective option for developing new heterogeneous catalysis for CO 2 hydrogenation to high‐value products. Roy et al 13 and our previous work have successfully screened and optimized the catalysts for the direct and indirect CO 2 hydrogenation to methanol processes 14 . In addition, Yan et al 15 proposed a novel catalytic performance prediction method of transition metal phosphide based on ML to guide the design and development of new catalysts.…”