UrbanTrace: LLM-Assisted Discovery and Semantics-Aware Integration of Spatial Data
Authors
Sonia Castelo (New York University), Eden Wu (New York University), João Rulff (New York University), Harish Doraiswamy (Microsoft Research India), Juliana Freire (New York University), Claudio Silva (New York University)
Presentation
- Session
- Places and spaces
- Time
- Thursday, Nov 12, 13:12 – 13:24 (US/Eastern) · session 13:00 – 14:30
- Location
- Hall America center
Links
Sign in to access the preprint PDF.
Sign in- Download Supplemental Material
Keywords
Multivariate spatial harmonization, intent-driven data discovery, agentic spatial analytics
Abstract
Urban decision-making requires integrating heterogeneous spatial data. While current GIS tools handle geometric computation efficiently, they lack the semantic reasoning to guide complex workflows. Analysts manually manage data discovery, spatial boundaries, and measurement semantics, risking aggregation errors. We present UrbanTrace, a visual analytics system that transforms manual spatial data-wrangling into a transparent, node-based collaborative workflow with context-aware AI agents. Using an offline profiler to extract semantic and geometric metadata, UrbanTrace grounds LLMs in real-world data distributions. This enables specialized agents to retrieve datasets based on high-level goals and automatically enforce valid spatial aggregations. To make harmonization explicit, three interactive views: an Integration Provenance Graph, Multivariate Priority Map, and Spatial Delta Map, allow users to explore how conclusions shift across spatial configurations. We evaluate UrbanTrace on 28 urban scenarios spanning 112 datasets. Quantitative ablations show our profiling significantly outperforms baseline LLMs in data discovery, achieving 100% semantic and 87% geometric validity in spatial mapping. Through real-world case studies and expert interviews, we demonstrate that UrbanTrace turns spatial aggregation sensitivity from a methodological burden into an exploratory visual asset.
For Practitioners
Practitioners such as urban planners, GIS analysts, civic data scientists, and policy analysts who work with heterogeneous spatial datasets would benefit from this work. They can apply the insights from UrbanTrace to streamline geospatial data discovery and integration, better understand the impact of spatial boundaries and aggregation choices, and create more transparent, interpretable, and objective-driven analyses for urban decision-making.