Target high‐efficiency ionic liquids to promote H2SO4‐catalyzed C4 alkylation by machine learning

Abstract To predict and rationally design high‐efficiency ionic liquids (ILs) additives for H 2 SO 4 ‐catalyzed alkylation, the quantitative structure–activity relationship between 11,000 ILs and interfacial properties of H 2 SO 4 alkylation was established by combination of molecular dynamics simulation, semi‐empirical density function theory, and machine learning. The results indicate that ILs additives with longer alkyl chain can significantly broaden interfacial thickness and decrease interfacial tension, in which the cation‐ and anion‐based descriptors play a synergistic prominent role. Based on the intensified interfacial properties, series of novel ILs additives with different alkyl chain length in both cations and anions are prepared, which present the ability to efficiently promote catalytic performance of H 2 SO 4 at trace addition amount and increase research octane number (RON) of alkylate up to 98.08 from 95.87 in pure H 2 SO 4 system. This work provides a strategy for prediction and rational design of high‐efficiency additives to enhance the liquid–liquid interfacial properties.