5 papers
FESOM2-JAX v1.0: a differentiable shadow of the ocean-sea-ice model FESOM2, cast onto GPUs
Nikolay V. Koldunov, Sergey Danilov, Suvarchal Cheedela +9
We present FESOM2-JAX, a Python re-implementation of the Finite-volumE Sea ice-Ocean Model (FESOM2) in JAX. The model retains the unstructured-mesh, cell-vertex finite-volume formu…
CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science
Dmitrii Pantiukhin, Boris Shapkin, Ivan Kuznetsov +2
The Coupled Model Intercomparison Project Phase 6 (CMIP6) has generated thousands of peer-reviewed publications documenting model configurations, evaluation procedures, emergent co…
An Ocean Model Ported by a Large Language Model: Experience and Lessons from FESOM2 (Fortran to C to C++/Kokkos)
Nikolay V. Koldunov, Suvarchal K. Cheedela, Sergey Danilov +3
Large language models (LLMs) can translate and modify source code, and have been shown to do so for codes of different complexity. Whether they can port a complete, production geop…
A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives
Dmitrii Pantiukhin, Ivan Kuznetsov, Boris Shapkin +3
The rapid accumulation of Earth science data has created a significant scalability challenge; while repositories like PANGAEA host vast collections of datasets, citation metrics in…
Climate Knowledge in Large Language Models
Ivan Kuznetsov, Jacopo Grassi, Dmitrii Pantiukhin +3
Large language models (LLMs) are increasingly deployed for climate-related applications, where understanding internal climatological knowledge is crucial for reliability and misinf…