A Multi-Agent System for Building-Age Cohort Mapping to Support Urban Energy Planning

TL;DR

This paper introduces a multi-agent system that fuses heterogeneous data sources to accurately map building ages for urban energy planning, utilizing a novel satellite-based classifier with high overall accuracy.

Contribution

The work presents a multi-agent LLM framework for data fusion and a new satellite-only classifier, BuildingAgeCNN, for building age estimation with improved accuracy and confidence calibration.

Findings

BuildingAgeCNN achieves 90.69% overall accuracy.

The classifier has a macro-F1 score of 67.25%, indicating class imbalance challenges.

The system supports urban energy planning by providing structured building age data.

Abstract

Determining the age distribution of the urban building stock is crucial for sustainable municipal heat planning and upgrade prioritization. However, existing approaches often rely on datasets gathered via sensors or remote sensing techniques, leaving inconsistencies and gaps in data. We present a multi-agent LLM system comprising three key agents, the Zensus agent, the OSM agent, and the Monument agent, that fuse data from heterogeneous sources. A data orchestrator and harmonizer geocodes and deduplicates building imprints. Using this fused ground truth, we introduce BuildingAgeCNN, a satellite-only classifier based on a ConvNeXt backbone augmented with a Feature Pyramid Network (FPN), CoordConv spatial channels, and Squeeze-and-Excitation (SE) blocks. Under spatial cross validation, BuildingAgeCNN attains an overall accuracy of 90.69% but a modest macro-F1 of 67.25%, reflecting strong class imbalance and persistent confusions between adjacent historical cohorts. To mitigate risk for planning applications, the address-to prediction pipeline includes calibrated confidence estimates and flags low-confidence cases for manual review. This multi-agent LLM system not only assists in gathering structured data but also helps energy demand planners optimize district-heating networks and target low-carbon sustainable energy systems.