A FAIR Protocol for Hybrid Models and Data in Hydrology

Hybrid modeling, which integrates physics-based and machine learning (ML) components, is a growing research area in hydrology and the broader Earth Science community. By combining the interpretability of process-based models with the predictive power of data-driven algorithms, these hybrid architectures offer improved accuracy and representation of complex environmental processes. However, their adoption is currently constrained by significant challenges regarding FAIR principles (Findable, Accessible, Interoperable, Reusable) . Unlike traditional physics-based models, the reusability of hybrid systems is frequently hindered by the dynamic nature of ML components, which are inextricably linked to specific training datasets and hyperparameter configurations. Furthermore, existing data data and model repositories are rarely designed to host such models.To address these systemic barriers, we collaboratively designed and implemented a standardized FAIR protocol specifically tailored for hydrological hybrid models. This framework, termed as FRAME, consists of three critical components: (a) a set of interoperability coding standards for the physics and ML modules, (b) a unified metadata specification that captures the disparate requirements of both physics-based parameters and ML architectures, and (c) a specialized online repository designed for the persistent hosting and sharing of integrated hybrid assets. To facilitate user adoption, we developed an associated command line interface (CLI) for automated retrieval and setup of these models. To ensure the long-term impact and scalability of this protocol, we are actively soliciting participation from the global hydrologic modeling community. By establishing a community-driven standard, this protocol aims to provide a robust foundation for the transparent, reproducible, and collaborative advancement of hybrid modeling in hydrology.