To explore the effects of hydration shell layer on the surface tension of electrolytes solution and to build an effective prediction model, a machine learning based model is proposed to accurately predict and explain the surface tension of electrolytes solution. The model combines machine learning (ML) algorithms, force filed parameters of molecular dynamics simulations and radial distribution function (RDF) to accurately capture the structure feature for electrolytes solution. The prediction performed an extremely low average relative deviation. SHapleyAdditive explanation (SHAP) method is used to indicate the features order of importance from strong to weak. It noted that the second hydration shell on the influence of surface tension may beyond the first hydration shell. This work provides a method for one-step acquisition of surface tension data that not only to accurately predict physical and chemical properties of materials, but also to extend the application of molecular dynamics simulations, providing enlightening insights for detecting underlying physical mechanisms.
Read full abstract