Reproduce “Long-time integration of parametric evolution equations with physics-informed DeepONets” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Sifan Wang, Paris Perdikaris

The authors present a physics-informed DeepONet that predicts short intervals and is repeatedly reused to simulate long trajectories from different initial states. It combines initial-state and coordinate inputs, with governing-equation, initial, and boundary-condition penalties during training. In a KdV example through T=100, relative L2 errors were 1.24% versus 6.84% for a data-only DeepONet; these are single-example results, and stability guarantees remain open.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.