Comparing intrusive and non-intrusive polynomial chaos for a class of exponential time differencing schemes

We consider the numerical approximation of different ordinary differential equations (ODEs) and partial differential equations (PDEs) with periodic boundary conditions involving a one-dimensional random parameter, comparing the intrusive and non-intrusive polynomial chaos expansion (PCE) method. We demonstrate how to modify two schemes for intrusive PCE (iPCE) which are highly efficient in solving nonlinear reaction-diffusion equations: A second-order exponential time differencing scheme (ETD-RDP-IF) as well as a spectral exponential time differencing fourth-order Runge-Kutta scheme (ETDRK4). In numerical experiments, we show that these schemes show superior accuracy to simpler schemes such as the EE scheme for a range of model equations and we investigate whether they are competitive with non-intrusive PCE (niPCE) methods. We observe that the iPCE schemes are competitive with niPCE for some model equations, but that iPCE breaks down for complex pattern formation models such as the Gray-Scott system.