Hybrid machine learning and genetic algorithm approach for catalyst and process optimization in Fischer–Tropsch synthesis toward sustainable fuel production

Abstract This study presents a data‐driven approach for predicting the relationships between catalyst design, process conditions, and product selectivity in Fischer–Tropsch synthesis (FTS). A dataset of 400 entries was compiled from peer‐reviewed literature, incorporating 24 input variables covering catalyst composition (including base metals, supports, and promoters), physical properties (including BET surface area and pore diameter), and key reaction conditions (including temperature, pressure, TOS, GHSV, and the gas ratio). The five target responses included CO conversion and selectivity for CO 2 , CH 4 , C 2 –C 4 hydrocarbons, and C 5 –C 12 hydrocarbons. Random forest (RF) regression models were developed for each target variable (i.e., conversions and selectivity). High accuracy was consistently achieved in the model training; the training R 2 values ranged from 0.95 to 0.98, with the RMSEC falling between 1.7 and 5.3, which is in line with or an improvement over previously reported results. The performance of the models was evaluated using k‐fold cross‐validation, yielding robust R 2 values ranging from 0.75 to 0.91, with RMSEV values between 3 and 7 for all predicted FTS responses. These results are superior to those reported in the literature, especially regarding CO conversion and C 5 –C 12 product selectivity.To extend beyond prediction and provide actionable insights toward sustainable fuel production, a genetic algorithm (GA) was combined with the RF models to optimize the catalyst composition and process conditions. Using this RF–GA approach, an optimal catalyst was identified. This led to a notable C 5 –C 12 selectivity of 90.75%, one of the highest reported values.