Reproduce “Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events” 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
Isabella S. Thiel, Juan Bello-Rivas, Yannis G. Kevrekidis, Themistoklis P. Sapsis
The paper conditions a fixed temporal corrector on spread from an ensemble around a nudged coarse simulation, using a small FiLM module to convey local-instability cues. Under small-noise and local-linearization conditions, covariance summarizes finite-time deformation. In a two-layer QG test, 50-unit FiLM-STORN lowers average event-frequency error to 0.07199, but has worse global KL divergence and log-density error than 1,000-unit STORN.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.