Geospatial metadata boosts dataset links across scientific fields
Geospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines
Digital LibrariesArtificial Intelligence
Summary
Many scientific datasets miss important location information, making it harder to find and connect related data. The authors found that adding detailed geospatial metadata helps datasets from different fields link together more often than just using keywords. This means geographic information is a better way to connect research across subjects. They improved a computer model that increases how many datasets from various disciplines link through shared location data.
What this means in practice
- •For data repository managers: Improve dataset discoverability and cross-discipline links by enhancing geospatial metadata completeness and incorporating it into metadata knowledge graphs.
- •For data platform developers: Create tools that use geospatial metadata and fine-tuned language models to automatically enrich dataset records and increase interdisciplinary connections.
Authors
Daniel Ebanks, Devika Jain
Abstract
Research data repositories are essential infrastructure for scientific inquiry and for ensuring that datasets follow FAIR (Findable, Accessible, Interoperable, and Reusable) principles. However, repository reuse depends on the quality and completeness of geospatial and thematic metadata, which researchers generally provide voluntarily. Given limited curation resources, it is unsurprising that even Harvard Dataverse, the world's largest general-purpose research repository, contains many incomplete metadata records. Missing fields represent lost information and reduce interoperability. We find that datasets with more missing metadata receive fewer downstream citations and have fewer resolvable connections to other datasets. The implications are particularly important for geospatial datasets: only 0.3% of research datasets include a bounding box, and most represent archival points rather than complete geographic shapes. Our analysis shows that geospatial metadata helps connect concepts across disciplines. After embedding Harvard Dataverse datasets in a metadata knowledge graph, we find that datasets are twice as likely to connect across scientific disciplines through shared geospatial metadata as through keywords. This suggests that geographic metadata is a more reliable basis for cross-disciplinary interoperability than keyword vocabularies, which often remain discipline-specific. We train and fine-tune a small language model using datasets from Harvard Dataverse. Through geospatial metadata enrichment, we increase the share of datasets from different disciplines connected through metadata elements from 58.5% to 63.2%.