Spatial Distribution Estimation of Urban Population in Zagreb, Croatia, Using LiDAR Data

Abstract

Accurate information on intra-urban population distribution is essential for urban planning, infrastructure management, exposure assessment, and evidence-based decision-making. However, census data are usually available only for predefined administrative units and often lack the spatial detail required for fine-scale urban analyses. This study evaluates a top-down approach for estimating population distribution within the city of Zagreb, Croatia, using building footprints, three-dimensional building characteristics, OpenStreetMap (OSM) semantic information, and census population counts. The citywide population total was redistributed to LiDAR-derived roof and WSF-derived settlement polygons and aggregated to 17 city districts for validation. Two built-environment datasets were tested: locally derived LiDAR roof polygons and WSF-derived settlement polygons. Area-based scenarios were implemented for both datasets, while height-enhanced scenarios incorporated LiDAR-derived nDSM information. The WSF height-enhanced scenario therefore combined globally available WSF geometry with locally derived LiDAR height information and is referred to as WSF + nDSM. Results show that 3D models consistently outperformed 2D models. Total relative error (TRE) decreased from 15.5% to 11.8% for LiDAR and from 19.6% to 11.4% for WSF. OSM-based refinement further improved all scenarios, with the LiDAR 3D + OSM and WSF + nDSM + OSM scenarios achieving comparable overall performance (TRE = 9.0% for both at the city-district validation level). These findings demonstrate the value of combining vertical and semantic building information for more accurate urban population disaggregation.