Abstract
Hydrological models are essential in water resources management, but the expertise required to operate them often exceeds that of potential stakeholders. We present an approach that facilitates the dissemination of hydrological models, and its implementation in the Model INTegration (MINT) framework. Our approach follows principles from software engineering to create software components that reveal only selected functionality of models which is of interest to users while abstracting from implementation complexity, and to generate metadata for the model components. This methodology makes the models more findable, accessible, interoperable, and reusable in support of FAIR principles. We showcase our methodology and its implementation in MINT using two case studies. We illustrate how the models SWAT and MODFLOW are turned into software components by hydrology experts, and how users without hydrology expertise can find, adapt, and execute them. The two models differ in terms of represented processes and in model design and structure. Our approach also benefits expert modelers, by simplifying model sharing and the execution of model ensembles. MINT is a general modeling framework that uses artificial intelligence techniques to assist users, and is released as open-source software.
Daniel Garijo
Collaborator
Maximiliano Osorio
Research Engineer
I’m a software engineer who is passionate about making AI researchers possible, creating technologies to integrate information and models across disciplines.
Suzanne Pierce
Collaborator
Yolanda Gil
Senior Director for Major Strategic AI and Data Science Initiatives
I have broad research interests in AI and data science. As Principal Scientist I lead the Interactive Knowledge Capture research group, which is part of AI@ISI.