“Recently, a research team led by Li Jinjin from School of Electronic Information and Electrical Engineering, SJTU published their latest research findings in Energy Storage Materials (IF=16.28), a top journal in energy study. They proposed a machine learning method to rapidly and accurately predict the binding energies towards lithium polysulfides (LiPS), which greatly facilitated the screening and discovery of cathode materials for lithium-sulfur batteries. Their research greatly enhances the application of transfer learning in the area of complex materials by demonstrating that transfer learning can overcome the obstacle caused by a lack in material property data, which is of great importance to providing a general predicting model for research on the binding energies between two-dimensional layered materials and LiPS.”