09-10, 15:00–15:30 (America/Chicago), Grand F
An implementation of a discrete global grid system (DGGS) for accelerating geospatial data analysis is discussed. EASE-DGGS forms the backbone of a suite of RESTful APIs designed for addressing important agricultural and environmental challenges.
Advocates for discrete global grid systems (DGGS) posit the technology as overcoming the limitations of traditional geographic information systems (GIS), which can accelerate discovery and information generation. In 2020 we developed EASE-DGGS, a hybrid DGGS based on EASE-GRID v2, to address limitations of DGGS, specifically the issue of integration of remotely sensed imagery and vector data within spatial analysis frameworks. As part of the University of Minnesota's GEMS Informatics initiative, the EASE-DGGS library was released into the open source domain in 2024 under an Apache 2.0 license. In this presentation, we will present the information scaling motivation for DGGS. We will also examine GEMS Exchange - a RESTful application programming interface (REST API) built on top of EASE-DGGS. GEMS Exchange is explicitly designed to accelerate knowledge discovery in the agricultural and environmental sectors. The presentation will also discuss the API portfolio, with particular emphasis on a key new dataset developed by the UMN GEMS team for the conterminous United States: advanced prediction of the USDA’s Cropland Data Layer. Our CDL-prediction engine, and the whole of GEMS Exchange was built using free, and open source packages and libraries.The presentation will conclude by examining the potential for data integration and interoperability provided by GEMS Exchange in the era of machine learning.
