Keynote Speaker:Guo Ling

Abstract:

Physics-informed neural networks (PINNs) have recently emerged as an effective way of numerically solving partial differential equations. However it is lacking uncertainty quantification of the solution due to the inherent randomness in the data. In this talk, we will review some recent developments on using PINNs to quantify uncertainty propagation in a unified framework forward, inverse and mixed stochastic problems based on scattered measurements. We will introduce the NN-aPC approach for steady PDEs with random inputs. We will also demonstrate the capability of the stochastic version of PINNs with the applications for the long-time integration of time-dependent stochastic partial differential equations.

Speaker Introduction:

Guo Ling is the Professor and Doctoral Supervisor of the Mathematic College of Shanghai Normal University. Her main research area is uncertainty quantification and machine learning. She has presided over many projects such as the National Natural Science Foundation of China successively and published many papers in high-level journals such asSIAM. J. Sci. Comp. She has won the Shanghai Education Award and granted the titles of the Bearer of Red Flag March 8 of the Shanghai Education System and Shanghai Teaching Expert.

Inviter:

Zhao Weidong ProfessorofSchool of Mathematics

Time:

10:00-11:00 on December 22 (Tuesday)

Location:

Tencent Meeting, ID: 585 798 369

https://meeting.tencent.com/s/HMGBsrd6HrFT

Hosted by: School of Mathematics, Shandong University