Modeling the emitted carbon dioxide and monoxide gases in the gasification process using optimized hybrid machine learning models

Abstract The machine learning methods are hereby proposed to predict the amount of Carbon Monoxide (CO) and Carbon Dioxide (CO₂) emissions in a gasification process, which is one of the most important enabling technologies for carbon-containing materials, such as coal, biomass, and waste toward producing end products of worth, such as syngas, hydrogen, and synthetic fuels. In an attempt to support efforts for improving the emission prediction-a key criterion for enhancing efficiency and further, the environmental performance of gasification-two new advanced algorithms are being applied for the optimization of the model of a random forest: the Jellyfish Search Optimizer (JSO) and Sooty Tern Optimization Algorithm (STOA). The tuned RFJS (RF+JSO) was the best of these configurations, providing the least RMSE of 0.593 on test data and the highest R 2 on validation of 0.983, proving to be most effective for the prediction of emissions. This goes to attest that the model RFJS would be a strong tool in real-time-based carbon emissions reduction due to its effectiveness in dealing with major implications from environmental monitoring to regulation and further into sustainable energy production.