UrbanTrace: LLM-Assisted Discovery and Semantics-Aware Integration of Spatial Data

2026-07-27

AI Summary

This study addresses the challenges urban decision-making faces due to highly heterogeneous spatial data and the limited semantic reasoning capabilities of existing GIS tools, which often lead to error-prone manual processing. To overcome these limitations, this work proposes UrbanTrace, a novel visual analytics system that integrates semantic-aware large language model (LLM) agents into the spatial data integration pipeline for the first time. UrbanTrace employs an offline parser to extract semantic and geometric metadata, combines domain-customized LLM agents with a nodal workflow architecture, and enables goal-driven data discovery and legally compliant spatial aggregation. The system innovatively transforms spatial aggregation sensitivity into explorable visual assets and transparently reveals the integration process and outcomes through a tri-view interface. Evaluations across 28 urban scenarios and 112 datasets demonstrate 100% semantic validity in data discovery and 87% geometric validity in spatial mapping, with expert assessments confirming significant improvements in analytical reliability and exploratory efficiency.

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.

Problem

• spatial data integration
• semantic reasoning
• spatial aggregation
• urban decision-making
• heterogeneous data

Innovation

• LLM-assisted spatial data integration
• semantic-aware GIS
• spatial aggregation validity
• visual analytics for urban data
• context-aware AI agents