Reproduce “An Interpretable Model of Climate Change Using Correlative 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
Charles Anderson, Jason Stock
The authors train a neural network on CMIP6 annual temperature and precipitation maps to predict year, then use Alopex, a gradient-free search, to find map patterns that drive selected year predictions. The resulting patterns differ for target years 1900, 2000, and 2100. These are optimized inputs to a predictor, not validated evidence of observed or human-caused climate change.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.