Reproduce “Regional climate risk assessment from climate models using probabilistic machine learning” 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
Zhong Yi Wan, Ignacio Lopez-Gomez, Robert Carver, Tapio Schneider, John Anderson, Fei Sha, Leonardo Zepeda-Núñez
GenFocal downscales coarse climate projections into fine-scale weather. It debiases distributions without matching events, then uses conditional diffusion trained on paired ERA5 data to generate detail. For 2010–2019, its North Atlantic cyclone statistics resemble ERA5, and its CONUS 99th-percentile heat-index error is 0.68 K versus 1.01 K for QMSR. These historical evaluations concern statistics, not event-level predictions or verified future outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.