FRAME – A FAIR Protocol for Hybrid Models and Data in Hydrology
Hybrid models, which combine physics and machine learning (ML) based models, are becoming increasingly popular in hydrology and the broader Earth Science community due to their potential for improved prediction and process representation. However, hybrid models pose unique challenges to open research practices, including the widely accepted FAIR (Findable, Accessible, Interoperable, Reusable) principles. Unlike physics-based models, the reusability of hybrid models is hindered by the integration of ML models which dynamically change with training data. Furthermore, existing model and data repositories are not designed to host hybrid models which contain code, ML models, and associated training data. To address these challenges, FRAME will collaboratively design, implement, and test a standardised FAIR protocol tailored for hydrological hybrid models. The protocol will consist of coding standards for interoperability between different model components, a unified metadata specification accounting for different types of physics and ML-based models, and a python package leveraging existing model and data repositories widely used in the hydrology (HydroShare) and ML (DLHub) communities to share and retrieve hybrid models. To ensure wider and long-term impact of the project beyond its lifetime, the developed protocol will be actively used and improved by participating groups in the ETH Domain and Europe and will ultimately be transitioned to a community-driven protocol, inviting participation from the wider scientific community.
TRANSCODE – Towards community-driven, open and FAIR ecohydrological modeling
Mechanistic ecohydrological models are essential tools to accurately simulate the impacts of climate change on the water, carbon, and nutrient cycles. However, there are very few models available to the community which can holistically simulate such a wide range of processes and most of them are written in low-level programming languages (e.g., C++ or FORTRAN), hindering model accessibility to new users. In this regard, Tethys and Chloris (T&C), a state-of-the-art ecohydrological model written in MATLAB, offers a strong foundation for creating an accessible community-driven model. TRANSCODE aims to transform T&C into a FAIR model by redesigning its architecture for modularity and re-implementing it in Julia, an open-source language which marries the computational efficiency of low-level programming languages such as FORTRAN and the accessibility of high-level languages such as MATLAB. This translation will improve computational efficiency, foster open code contributions from the community, and facilitate interoperability with other models. Specifically, the project will create a modular, comprehensively tested, highly efficient, and easily accessible version of T&C, termed T&C-Julia. TRANSCODE has the potential to significantly benefit the Earth science community and advance the field of ecohydrological modelling by providing a versatile, state-of-the-art, and open-source modelling platform.
Projects duration | FRAME (Sep. 2024 – Feb. 2026) – TRANSCODE (Oct. 2024 – Sep. 2025)
People | Akash Koppa
Funding | Open Research Data (ORD) Program of the ETH Board