Hyperparameter optimization in the estimation of PDE and delay-PDE models from data

Mai, Oliver; Kroll, Tim W.; Thiele, Uwe; Kamps, Oliver

Abstract

We propose an improved method for estimating partial differential equations (PDEs) and delay PDEs from data, using Bayesian optimization and the Bayesian information criterion to automatically find suitable hyperparameters for the method itself and also for the equations (such as a time-delay). We show that combining time integration into an established model estimation method increases robustness and yields predictive models. Allowing hyperparameters to be optimized as part of the model estimation results in a wider modeling scope. We demonstrate the method’s performance for a number of synthetic benchmark problems of different complexity, representing different classes of physical behavior. This includes the Allen–Cahn and Cahn–Hilliard models, as well as different reaction-diffusion systems without and with time-delay.