Reproduce “Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions” 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
Rodrigo Almeida, Noelia Otero, Jost Arndt, Simon Baur, Wojciech Samek, Jackie Ma
The authors make Aardvark Weather an ensemble by adding noise to its observation encoder and Monte Carlo dropout to its forecast processor, separating variance across encoder draws from within-draw processor variance. Withholding IASI sounder increases encoder-attributed variance while total variance changes little. The ensemble mean lowers RMSE by 11.0% versus Aardvark, but remains worse than IFS ENS in probabilistic CRPS.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.