»ã±¨±êÌâ (Title)£º»ùÓÚÎïÀíѧ֪ʶµÄÉñ¾­ÍøÂç»ìºÏѵÁ·×·Çó·ÇÏßÐÔѦ¶¨ÚÌ·½³Ì¹Ö²¨½â£¨Mix-training physics-informed neural networks for the rogue waves of nonlinear Schrodinger equation£©

»ã±¨ÈË (Speaker)£º Àî±ë ½ÌÊÚ£¨Äþ²¨´óѧ£©

»ã±¨¹¦·ò (Time)£º2023Äê5ÔÂ12ÈÕ(ÖÜÎå) 16:00

»ã±¨µØÖ· (Place)£ºÌÚѶ»áÒ飺586 592 749

Ô¼ÇëÈË(Inviter)£ºÏÄÌú³É

Ö÷°ì²¿ÃÅ£ºÀíѧԺÊýѧϵ

»ã±¨ÌáÒª£ºIn this work, we propose Mix-training physics-informed neural networks (PINNs), a deep learning model with more approximation ability based on PINNs, combined with mixed training and prior information. We demonstrate the advantages of this model by exploring rogue waves with rich dynamic behavior in the nonlinear Schrodinger (NLS) equation. Numerical results show that compared with the original PINNs, this model can not only quickly recover the dynamical behavior of the rogue waves of NLS equation, but also significantly improve its approximation ability and absolute error accuracy, the prediction accuracy improved by two to three orders of magnitude. In particular, when the space-time domain of the solution expands or the solution has a local sharp region, the proposed model still has high prediction accuracy.