Machine Learning-Based CO2 Hydrogenation to High-Value Green Fuels: A Comprehensive Review for Computational Assessment

Ahmed, Muhammad
Latif, Rukhsar
Seher, Shabaz
Sajjad, Rida
Hussain, Tariq
Islam, Muhammad Raza
Waleed, Abdul

ASEAN Journal for Science and Engineering in Materials
Vol 3, No 2 (2024): AJSEM: Volume 3, Issue 2, September 2024

The biggest candidate for climate change is the emission of CO2 during the burning of fossil fuels and researchers are trying to capture this CO2 efficiently and utilization effectively. This review highlights the parametric effects on conversion, utilization, and selectivity in CO2 hydrogenation via the Fischer-Tropsch method using various catalysts. Collecting the data from reported studies as datasets for quantum mechanical-based simulation software such as DFT and Monte Carlo were employed to probe the characteristics of catalysts, the discovery of novel catalysts, theoretical models for utilization of catalysts and parameters for CO2 hydrogenation such as operational, catalyst information, and mass transfer. Two syntheses such as methanol and methane were studied extensively via machine learning techniques. How artificial intelligence can help experimentalists for finding new catalysts has been discussed and how one can understand the catalytic features in a better way. Furthermore, the key challenges in CO2 hydrogenation technology and future directions based on artificial intelligence have been discussed thoroughly.