We present ClimateBench v2, a standardized protocol for evaluating climate models on diagnostics expected to be informative for their skill in projecting mid-century regional temperature and precipitation changes. The protocol is designed to evaluate any physics-based, data-driven, or hybrid climate model on equal foot...
Duncan Watson-Parris, Willa Tobin, Aytaç Paçal et al.· 0 citations
This evaluation framework provides a reproducible benchmark for quantifying parametric climate knowledge in LLMs, and shows that LLMs reproduce broad geographic regularities in climatological temperature fields, capturing latitudinal and topographic patterns.
Ivan S. Kuznetsov, Jacopo Grassi, Dmitrii Pantiukhin et al.· Artificial Intelligence for...· 0 citations
HlimRep-Ocean is presented, an ocean emulator that operates directly on the native unstructured mesh of FESOM2, and achieves the lowest RMSE against GLORYS reanalysis among all assessed systems, confirming the competitiveness of the native-mesh approach.
K. Nowak, A. Koldunov, Nikolay Koldunov et al.· 0 citations
Abstract. The increasing availability of kilometer-scale climate simulations presents major challenges for data access, processing, and analysis due to the unprecedented volume and heterogeneity of the outputs. Different data formats, structures, and metadata conventions, require dedicated solutions to ensure interoper...
Matteo Nurisso, Jost von Hardenberg, Marco Cadau et al.· Geoscientific Model Developm...· 0 citations
To the authors' knowledge, FESOM2-JAX is the first global ocean-sea-ice model of CMIP-class complexity written natively in a differentiable framework, and the first on an unstructured mesh.
Nikolay Koldunov, S. Danilov, S. Cheedela et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.