BIMSA >
数据分析与问题求解讨论班
数据分析与问题求解讨论班
Solving and Discovering PDEs with Physics-Informed Neural Networks
Solving and Discovering PDEs with Physics-Informed Neural Networks
组织者
演讲者
赵卓阳
时间
2026年08月07日 15:00 至 16:00
地点
A3-3-301
线上
Zoom 204 323 0165
(BIMSA)
摘要
This presentation introduces physics-informed neural networks (PINNs) for solving forward and inverse problems involving nonlinear partial differential equations. PINNs approximate the unknown solution with a neural network and include the governing equation in the loss function through automatic differentiation. Both continuous-time and discrete-time formulations are discussed, with emphasis on how Runge-Kutta methods connect different time snapshots. Several examples, including Burgers, Schrodinger, Allen-Cahn, Navier-Stokes, and KdV equations, are used to show how PINNs recover solutions and identify unknown parameters from limited data.
演讲者介绍
Zhao Zhuoyang is a first-year Ph.D. student in a joint Program between BIMSA and Renmin University of China, majoring in Mathematics, under the supervision of Professor Zhang Xiaoming.