Noah-Agent: A Multi-Expert AI Agent Framework for Automated Parameterization and Validation of Large-Scale Fortran Climate Models (v0.1)
Published in Preprint (Zenodo); in preparation, 2025
Status: Preprint, version 0.1, in preparation.
Noah-Agent is a multi-expert AI agent framework for automated parameterization and validation of large-scale Fortran climate models.
Approach
- Multiple specialized agents coordinate to parameterize and validate large Fortran model codebases.
- The framework automates steps that are otherwise done by hand, such as parameter selection and validation against reference behavior.
Relation to Other Work
Noah-Agent connects to the broader Noah-MP land surface modeling effort and to ESM-bench, which evaluates whether AI agents understand Earth System Model physics and code.
Links
- Preprint (Zenodo): https://zenodo.org/records/17862049
- Blog post: Noah-Agent: a multi-expert agent framework for Fortran climate models
Recommended citation: Wu, K. (2025). "Noah-Agent: A Multi-Expert AI Agent Framework for Automated Parameterization and Validation of Large-Scale Fortran Climate Models (v0.1)." Preprint, Zenodo. https://zenodo.org/records/17862049
Download Paper