Machine learning-based techno-econo-environmental analysis of CO2-to-olefins process for screening the optimal catalyst and hydrogen color

CO2 to light olefins (CTLO) is an attractive strategy for CO2 fixation to obtain high-value-added chemical products. Selecting the optimal catalyst and hydrogen source for the process has become increasingly challenging due to the wide range of developed catalysts and diverse hydrogen sources available. Herein, this study proposes a machine learning-based techno-econo-environmental analysis framework for screening catalysts and hydrogen colors for the CTLO process. The preferred machine learning model is employed to screen the most promising catalyst for the CTLO process, which is then applied to accomplish the conceptual design of the entire process to obtain essential material and energy balance results by process modeling and simulation. Finally, the techno-econo-environmental performance of the CTLO processes using various colored hydrogen are compared to provide more informed choices. The results indicate the extreme gradient boosting model exhibits superior predictive accuracy, making it suitable for integrating with the genetic algorithm to screen the optimal catalyst for the CTLO process. After multi-objective optimization, an optimal Fe-based catalyst is screened and used for the modeling and simulation of the CTLO process due to its highest light olefins yield (36.43 %). The carbon, hydrogen, and exergy utilization efficiencies of the CTLO process considering solely the target light olefins are 59.58 %, 21.71 %, and 40.41 %, respectively. After evaluating the impact of different H2 colors on the total operating cost, unit production cost, and minimum selling price of the CTLO process, it was found the CTLO process using gray H2 generated by coke oven gas and coal gasification technologies exhibits the most favorable cost-effectiveness and optimal market price compared to alternative production scenarios. However, using green H2 proves highly advantageous for the CTLO process in attaining comprehensive negative carbon emissions throughout its lifecycle. Moreover, it anticipates the influence of technological advancements and market fluctuations on the market competitiveness of CTLO processes with diverse hydrogen colors.