Reproduce “SMORE: Stability-Promoting Mesh-Agnostic Model Reduction for Time-Dependent PDEs” 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
Yangyuan Li, Weichao Li, Shaowu Pan
SMORE predicts PDE fields beyond training snapshots by encoding fields as compact latent states, advancing them with linear or linear–quadratic dynamics, and decoding at queried coordinates. Stability-motivated penalties encourage theoretically sufficient conditions, but do not guarantee them. Across three tested benchmarks, a variant has the lowest extrapolation MSE; on Wave, SMORE-Koopman reduces MSE 97.7% versus DINo.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.