15R2O Enhancing Dataset Discovery and Usage Tracking in Earth Sciences: Integrating Knowledge Graphs and Large Language Models

Tracing dataset usage in published research has become increasingly feasible due to the growing trend of citing datasets in peer-reviewed journal publications. This empirical evidence of dataset usage allows dataset archivers and providers to enhance their offerings by including use cases from peer-reviewed literature. These use cases provide future researchers with valuable examples of how datasets have been utilized in specific applied research areas, helping them select the most appropriate datasets for their applications.

NASA's Data Active Archive Centers (DAACs) have played a crucial role in supporting a wide range of applied research in Earth and Environmental sciences. To date, over 20,000 publications have been collected, citing more than 3,000 NASA Earth science datasets. Our presentation addresses the development of tools that assist users in navigating these publications to identify the most relevant datasets and their research applications.

We present an innovative approach that links datasets and publications through a knowledge graph (KG). This KG enables the tracking of dataset citations throughout the dataset's lifecycle, revealing patterns of dataset usage across various applied research areas. We fine-tuned the pre-trained NASA IMPACT INDUS Large Language Model (LLM) using a set of labeled publication abstracts. Our results indicate that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were categorized into non-applied research areas.

By linking datasets to applied research areas via the KG and utilizing the Global Change Master Directory (GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a more transparent and advanced search and discovery mechanism for datasets within the Earth data ecosystem. The integrated KG and LLM approach is now operational in managing dataset publications at one of NASA's Earth science data archival centers.