Multiscale Modelling with Physics-informed Neural Network: from Large-scale Dynamics to Small-scale Predictions in Complex Systems

Multiscale phenomena manifest across various scientific domains, presenting a ubiquitous challenge in accurately and effectively predicting multiscale dynamics in complex systems. In this paper, a novel solving mode is proposed for characterizing multiscale dynamics through a decoupling method. By modelling large-scale dynamics independently and treating small-scale dynamics as a slaved system, a Spectral PINN is developed to approach the small-scale system in an orthogonal basis functional space. The effectiveness of the method is demonstrated through extensive numerical experiments, including one-dimensional …

challenge complex systems cs.lg domains dynamics manifest modelling network neural network novel paper physics physics.comp-ph physics.flu-dyn physics-informed predictions presenting scale small systems through