Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 6, 2026Open Access

Enhancing Spatial Data Discovery in Spatial Data Infrastructures (SDIs) using AI

View Full Paper
Ask AI
Bookmark
Share

Authors

JOJames OndiekiMRMatthes RiekeSJSimon Jirka

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved dataset discovery in Spatial Data Infrastructures, suggesting effective use of AI.

Key Points

  • The aim is to enhance dataset discovery in Spatial Data Infrastructures by using AI technologies in a hybrid workflow.
  • Integrated Retrieval-Augmented Generation with geocoding and spatial indexing.
  • Used an LLM parser to extract terms and locations from user queries.
  • Filtered datasets via spatial index in a PostGIS database before conducting semantic search.
  • Significantly reduced barriers for non-expert users by enabling queries based on natural language and place names.
  • Effectively mitigated hallucinations in LLM responses when grounded with actual metadata.
  • Facilitated cross-lingual dataset discovery without the need for explicit translation.

Cite This Study

Ondieki et al. (2026) studied this question.

synapsesocial.com/papers/6a23ba3c71a5da9775e75f9fhttps://doi.org/10.5281/zenodo.20540881
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Intent-Driven Hybrid Semantic–Spatial Retrieval–Augmented Generation for Intelligent Prospecting with GIS Visualization2026
  2. 2Retrieval Augmented Generation for Relative Distance-based Spatial Reasoning2026
  3. 3Mapping with Words: Integrating Large Language Models into Geospatial Practice2026
  4. 4Text‐to‐SpatialSQL: A LLM Based Method for Generating Spatial SQL Queries With Geo‐Knowledge Extracted From Software User Manual2026
  5. 5An Automated Framework for Natural Language-Based Spatial Query Using Large Language Models2026 · 2 citations