Heterogeneous Graph Importance Scoring and Clustering with Automated LLM-based Interpretation

TL;DR

This paper introduces a comprehensive open-data pipeline for assessing urban bridge importance using heterogeneous graph analysis, clustering, and LLM-based automated interpretation, applicable across multiple cities.

Contribution

It presents a novel methodology combining multi-dimensional importance scoring, clustering, and automated interpretation with LLMs, validated on multi-city data.

Findings

Developed an open-data pipeline from OSM to bridge importance rankings.

Created a five-indicator scoring system with significant computational efficiency.

Validated clustering framework across different cities with transferability.

Abstract

Urban bridge networks are critical infrastructure whose disruption can cascade into severe impacts on transportation, emergency services, and economic activity. This paper presents a comprehensive methodology for assessing bridge importance through heterogeneous graph analysis, unsupervised clustering, and automated interpretation via large language models (LLMs). Our approach addresses three fundamental challenges: (1) quantifying multi-dimensional bridge importance using only open data sources, (2) discovering functional bridge archetypes across different cities, and (3) generating policy-relevant interpretations automatically. We construct heterogeneous graphs from OpenStreetMap (OSM) data incorporating bridges, road networks, buildings, and public facilities. Five social impact indicators are computed: transit desert score, hospital access score, isolation risk score, supply chain impact score, and green space access score. These 52-dimensional feature vectors undergo dimensionality reduction via UMAP and density-based clustering via HDBSCAN. Discovered clusters are interpreted using temperature-optimized LLMs (Elyza8b, trained on construction domain corpus). (1) A complete open-data pipeline from OSM to actionable bridge importance rankings, (2) a five-indicator scoring methodology with 40$\times$ computational optimization, (3) a UMAP+HDBSCAN clustering framework validated on multi-city data, (4) an LLM interpretation methodology including temperature optimization and model selection rationale, and (5) transferability demonstration across cities via configuration-only adaptation.