Machine learning-driven optimization for sustainable CO2-to-methanol conversion through catalytic hydrogenation

Abstract

Growing concerns about greenhouse gas emissions have accelerated research into converting CO₂ into valuable products like methanol. Catalytic hydrogenation, utilizing a catalyst in a thermochemical process, offers a promising solution for reducing atmospheric CO₂ and combating climate change. However, optimizing operating conditions and selecting suitable catalysts for CO₂ to methanol conversion remains challenging due to the complex interplay between catalyst properties and reaction performance. This research leveraged machine learning (ML) to model CO₂ to methanol conversion using a comprehensive experimental database. ML models were developed to predict CO₂ conversion efficiency, methanol selectivity, and CO selectivity, facilitating process optimization, techno-economic analysis, and life cycle assessment (LCA). The gradient boosting regression model emerged as the most accurate, with coefficients of determination (R² > 0.86) and low error metrics (RMSE < 9.99, MAE < 5.99). De novo predictions demonstrated an acceptable linear relationship with the completely unseen dataset. Feature importance analysis identified temperature and gas hourly space velocity (GHSV) as the most significant descriptors. The optimal conditions for maximum CO₂ conversion efficiency and methanol selectivity were identified as temperatures between 330 and 370 °C, a pressure of 50 bar, and a GHSV of 6,500–14,000 mL/g.h. The techno-economic analysis highlighted H₂ purchase price, methanol selling price, and CO₂ feedstock costs as critical economic factors, with a payback period of 4.6 years. The LCA demonstrated a 270 % reduction in carbon emissions through catalytic hydrogenation of CO₂ to methanol. This study underscored the importance of using sustainable H₂ and electricity sources to enhance the economic and environmental benefits of the process.