In a recent webinar co-hosted by the Geospatial Data Commmunity of Practice and Radiant Earth on the topic of collecting and sharing ground-referenced data for ML applications, CGIAR researcher Dr. Kai Sonders revealed that approximately 20 percent of data collected by their research centers are georeferenced. If researchers were equipped with GPS devices and trained on the methodology to make survey data compatible, these data could be an excellent source for ground-referenced EO training data.