Oblique CO2 hydrogenation to methanol and ethylene glycol is a inexperienced, environment friendly, and economical know-how for changing CO2 into high-value chemical substances to deal with the intractable environmental disaster brought on by CO2 emissions. Nevertheless, conventional strategies for screening and optimizing catalysts on this course of primarily rely upon expertise and repeated ‘trial-and-error’ experiments, that are resource-, time- and cost-consuming duties. Due to this fact, this examine developed a machine studying framework for predicting the conversion ratio of ethylene carbonate, and the yield of methanol and ethylene glycol of oblique CO2 hydrogenation know-how to speed up its catalyst screening and optimization progress. The preliminary dataset is visualized by conducting principal part evaluation and improved to make sure ample data variables for the machine studying mannequin to tell apart catalyst varieties. After evaluating the optimized outcomes of three algorithms, the neural community with two hidden layers is the core of the machine studying mannequin of the oblique CO2 hydrogenation course of. It’s then additional optimized by a characteristic engineering technique coupled with characteristic significance evaluation and Pearson correlation matrix. It signifies that the optimized neural community mannequin has greater efficiency, particularly in predicting ethylene carbonate conversion and product yields. In contrast with different enter options, the area velocity and hydrogen/ester ratio are the 2 most vital components affecting the conversion ratio of ethylene carbonate and the yield of methanol and ethylene glycol. In keeping with the outcomes of the characteristic significance evaluation, a multi-objective optimization mannequin with a genetic algorithm is employed to display screen probably the most appropriate catalyst. In contrast with different catalysts, extra efforts ought to be paid to the optimized xMoOx-Cu/SiO2 catalyst for the industrialization of CO2 oblique hydrogenation know-how after experimental verification.