Engineering Papers⌕ Search
Home/Archive/NASA NTRS

NASA NTRS · 20240009298

Analyzing EOSDIS Dataset Research Outputs using Knowledge Graphs and Large Language Models

Irina Gerasimov·Armin Mehrabian·Jerome Alfred·Kendall Gilbert·James Acker·Binita KC·Andrey Savtchenko·Jennifer Wei
View original source ↗Export metadata ↓

Abstract

Datasets, unlike publications, can be updated over time, with each new version receiving a DOI but not always being linked to previous ones. This complicates tracking citations across a dataset’s lifecycle. We address this by integrating dataset versions and citations into a knowledge graph (KG), which helps trace dataset citations and analyze dataset usage in applied research. To categorize publications from various journals, we fine-tuned NASA IMPACT INDUS Large Language Model (LLM) on a labeled publication set, assigning publications to one of twenty applied research areas. By linking datasets to these research areas, we improved dataset searchability and discovery through these domains.

Explore related subjects

open-sourcedata provenancedata usagedata publicationdataset citationdataset DOIcitation management

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Irina Gerasimov, Armin Mehrabian, Jerome Alfred, Kendall Gilbert, James Acker, Binita KC, Andrey Savtchenko, Jennifer Wei. 2024-07-22. Analyzing EOSDIS Dataset Research Outputs using Knowledge Graphs and Large Language Models. https://ntrs.nasa.gov/citations/20240009298

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

NASA NTRS2024

Bridging the Gap: Enhancing Prominence and Provenance of NASA Datasets in Research Publications

Attribution of datasets that were used to generate research results described in peer-reviewed publications to the original source of these datasets (which are often archived at NASA Earth Science data centers) has been very challenging. Even though the data citation standard of citing datasets as research artifacts and citing them with Digital Object Identifiers (DOIs) was introduced over a decade ago, most authors do not properly reference the data used in their studies and merely mention them in the text. The lack of proper citations of datasets makes the peer-reviewed publication less transparent, imperils reproducibility, and impedes open science. We offer an open-source publication management methodology and a tool that can help to enhance usage-based data discovery, prominence, and provenance of the data; reproducibility of the research results; and potentially increase the return on investment on NASA-funded research.

open-source↗
NASA NTRSDate not supplied

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

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. We present an innovative approach that links datasets and collected 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-Base Retriever 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. The classified publications linked to datasets are used to discover datasets by users interested in specific applied research and by dataset providers to determine dataset usage for applications.

open-source↗