Because of the shortcomings of classical PINN (Physical-informed Neural Networks) for discontinuous problems of shallow water equation, a regularized PINN algorithm based on viscous dissipative mechanism was proposed. In the network framework, the viscous regularized shallow water equation is used as the physical constraint and the penalty term in the loss function. Training network makes the smooth solution of the regularized equation approximate the discontinuous solution of the original equation. Finally, for one-dimensional and two-dimensional shallow water problems with different initial conditions, the numerical results show that the new algorithm has strong generalization ability, can predict the solution at any time, and has high resolution, without the phenomenon of spurious oscillation.

Light absorption of Au nanoparticles@carbon sphere (AuNPs@CS) composite structure is investigated with finite difference time domain (FDTD) method. It shows that light absorption of AuNPs@CS composite structure is effectively controlled by position of Au nanoparticle.Two Au nanoparticles are selected and embedded on the surface of the carbon sphere at an optimal depth (0 nm). As the angle between the particle center of Au and the spheroid core of carbon sphere is 22.5° and 45°, light absorption is enhanced than that of a single carbon sphere; As the angles between them are 315°, 270°, 180° and 90°, the increment of light absorption decreases gradually; At an angle of 337.5° between them, the optical absorption is significantly lower than that of a single carbon sphere. It may be attributed to the change of Au nanoparticles position, which causes the change of light intensity and scattering direction of the surface plasmon. The light absorption of AuNPs@CS composite structure can be adjusted by varying the number and position of Au nanoparticle on the surface of carbon sphere.