Reproduce “Towards Causal Representations of Climate Model Data” 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
Julien Boussard, Chandni Nagda, Julia Kaltenborn, Charlotte Emilie Elektra Lange, Philippe Brouillard, Yaniv Gurwicz, Peer Nowack, David Rolnick
CDSD groups climate-map locations by shared hidden drivers while learning lagged links among them. Authors apply it to Nor-ESM2 temperature and precipitation maps from one model and scenario. After month-by-month seasonal adjustment, the temperature grouping includes a mid-Pacific region associated with ENSO; this pattern does not validate causal links, which are not found between temperature clusters.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.