PhICNet: Physics-Incorporated Convolutional Recurrent Neural Networks for Modeling Dynamical Systems

04/14/2020
by   Priyabrata Saha, et al.
13

Dynamical systems involving partial differential equations (PDEs) and ordinary differential equations (ODEs) arise in many fields of science and engineering. In this paper, we present a physics-incorporated deep learning framework to model and predict the spatiotemporal evolution of dynamical systems governed by partially-known inhomogenous PDEs with unobservable source dynamics. We formulate our model PhICNet as a convolutional recurrent neural network which is end-to-end trainable for spatiotemporal evolution prediction of dynamical systems. Experimental results show the long-term prediction capability of our model.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset