Machine learning (ML) algorithms are playing increasingly important roles in exploring solvents for wide industrial applications. However, most ML strategies for solvent screening neglect the contributions of intermolecular interactions among solvent components, resulting in reduced prediction accuracy for the solubilities of solvent mixtures. In this study, we propose an efficient method combining feature-based transfer learning and a hybrid Henry's law constant (HLC) calculation method to assist the exploration of promising solvent mixtures to remove organic sulfides. The incorporation of predicted HLC values from established models as features significantly enhances the prediction accuracy for various organic sulfides. In the case of 2-propanethiol, the prediction shows a R_test² of 0.91, RMSE of 0.0166, and MAE of 0.0118. The hybrid HLC calculation method, which incorporates non-ideal interactions between two solvent components, outperforms both the conductor-like screening models for real solvents (COSMO-RS) and ideal solution methods in predicting experimental HLC values. The present method successfully predicts a hybrid solvent for methanethiol (MeSH) removal. Both static and dynamic absorption experiments confirm that this designed solvent mixture has the lowest HLC of 370.48 kPa and the highest removal rate of 80.38% for MeSH.

Porous heterogeneous lyophobic systems (HLSs) find potential applications in energy restoring, dissipating, and absorbing. However, the development of controllable HLSs still lacks rational structure design of nanoporous materials matching the molecular sizes of adopted liquids. Besides that, thoroughly understanding the underlying transportation mechanism in the confined nano channels is greatly challenging. In this work, a series of Co/Zn bimetallic zeolitic imidazolate frameworks (ZIFs) with tunable structures were synthesized via regulating the Co to Zn ratios and employed to investigate the intrusion–extrusion of liquid water in confined nanopores. Structural characterizations confirm the heterometallic coordination in the Co/Zn-doped frameworks. Water intrusion–extrusion experiments unlock the relationship between the intrusion pressure and the nanopore size and realize the evolution of the HLSs between molecular spring and shock-absorber. In addition, cycling tests indicate the reversible structure change of Co/Zn ZIFs encountering pressure-induced water intrusion. In combination with molecular dynamics simulations, we present that the water multimers intrude into nanopores of ZIFs in chain-like forms along with dissociation of hydrogen bonds (HBs). Water molecules in the pre-intrusion state exhibit reduced HBs in response to the increase of pressure and linear structure with 1.6–3.0 HBs on average. After transition to the post-intrusion situation, the associative configuration of water tends to exhibit the tetrahedral structure. Herein, we highlight the roles of pore size and HB in synergically dominating the pressure-induced intrusion–extrusion of liquid water in hydrophobic nanopores. Furthermore, the present work can also guide the development of functional guest–host systems based on porous architectures.