Reproduce “PARDIG: Global Precipitation Estimates Learned from Sparse Satellite Observations” 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
Guy Shalev, Stephan Rasp, Boris Babenko, Andrew El-Kadi, Mohammed Alewi Hassen, Samier Merchant, Fred Zyda, Dominic Masters and 9 more
PARDIG estimates precipitation fields from sparse GPM radar observations, using atmospheric analyses and geostationary imagery as context. It trains at observed locations and times, then applies a spherical mesh and coordinate queries to produce maps at 0.1° resolution every 15 minutes. In 2016–2023 US radar comparisons, CSI at 1 mm/h was 0.48 versus 0.43 for the strongest baseline; evaluation remains geographically limited.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.