In electromagnetic (EM) society, the propagation of EM waves and the interaction with matters are governed by Maxwell's equations. In the past half-century, the Maxwell's equations are usually solved by different numerical methods such as FEM, MoM, FDTD, etc. As an emerging discipline, scientific machine learning (SciML) has been applied to solve and model a variety of physical and engineering sciences, which could play an important role in addressing EM problems. Thus, this session will focus on advanced SciML methods in solving Maxwell's equations in forward and inverse problems, as well as its extensions to EM related multiphysics issues.