Lessons learned designing the HydroGEN machine learning platform for hydrologic exploration: a story of collaboration between hydrologic scientists, software developers, machine learning researchers and water managers
Abstract
Today, water and resource managers face a huge challenge operating systems that are rapidly evolving in a warming climate, and where historical observations are no longer a reliable guide. Existing water management tools significantly lag the state of the science and are often ill-equipped to provide reliable forecasts under these conditions. Similarly, historical observations are of limited use on their own, without additional modeling and analysis. Our team is building a web-based platform called HydroGEN to help address this challenge. HydroGEN will train machine learning emulators to generate user customized seasonal to annual hydrologic scenarios of both groundwater and surface water systems using observations and sophisticated physics-based hydrologic models. We have taken a user-centered design approach to our platform development, working with water managers directly to better understand the gaps in current workflows and major barriers to adoption of new models. Our initial prototype focused on the Upper Colorado River Basin, an imperiled watershed of great importance serving almost 40 million people and chosen by our early adopters. Here, we present lessons learned from this process and how this has informed the HydroGEN design. We will also describe the path forward for this platform and ongoing work to develop inclusive and diverse pilot studies.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2021
- Bibcode:
- 2021AGUFMSY24A..04C