Florido, Jose; Wang, He; Khan, Amirul; Jimack, Peter K; (2024) Investigating Guiding Information for Adaptive Collocation Point Sampling in PINNs. In: Franco, L and DeMulatier, C and Paszynski, M and Krzhizhanovskaya, VV and Dongarra, JJ and Sloot, PMA, (eds.) Computational Science – ICCS 2024. 24th International Conference, Malaga, Spain, July 2–4, 2024, Proceedings, Part III. (pp. 323-337). Springer: Cham, Switzerland.

Text 2409.18401v1.pdf - Accepted Version Access restricted to UCL open access staff Download (4MB)

Abstract

Physics-informed neural networks (PINNs) provide a means of obtaining approximate solutions of partial differential equations and systems through the minimisation of an objective function which includes the evaluation of a residual function at a set of collocation points within the domain. The quality of a PINNs solution depends upon numerous parameters, including the number and distribution of these collocation points. In this paper we consider a number of strategies for selecting these points and investigate their impact on the overall accuracy of the method. In particular, we suggest that no single approach is likely to be “optimal” but we show how a number of important metrics can have an impact in improving the quality of the results obtained when using a fixed number of residual evaluations. We illustrate these approaches through the use of two benchmark test problems: Burgers’ equation and the Allen-Cahn equation.

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as CSVJSONXML

Archive Staff Only

View Item