Bringing Agentic Search to Earth Observation Data Discovery
NASA and its data centers hold thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony. Finding the right one is hard even for domain experts. We present an agentic search system, deployed as a public service for the geoscience community, that takes a natural-language research query and returns the matching datasets and tools. We demonstrate that, in the era of large language models, the latent value of knowledge graphs (KGs) can be substantially amplified through agentic search. From the NASA Earth Observation Knowledge Graph (NASA EO-KG)
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Agentic Resource Discovery: Let agents search →
- PossiblePossibly related (embedding) · 52%Build a protein research copilot with Amazon Bedrock AgentCore →
- PossiblePossibly related (embedding) · 51%gefsikatsinelou/MetaSearchMCP →
- PossiblePossibly related (embedding) · 50%Hussein-Furaty/NeuraFind →
- PossiblePossibly related (embedding) · 50%Embed the world: Multimodal AI for searchable aerial imagery at scale →
- LinkedLinked via arxiv author · 85%Minghan Yu →
“Bringing Agentic Search to Earth Observation Data Discovery”
- LinkedLinked via arxiv author · 85%Youran Sun →
“Bringing Agentic Search to Earth Observation Data Discovery”
- LinkedLinked via arxiv author · 85%Chugang Yi →
“Bringing Agentic Search to Earth Observation Data Discovery”