Inferring Community Boundaries from Volunteered Geographical Data
Community jurisdictional boundaries are pivotal in the context of smart communities,where their prompt and accurate delineation is critical for providing high-quality grassroots services.Currently,the delineation of these boundaries relies heavily on manual labeling by grassroots workers,which poses considerable challenges,including substantial data collection barriers and delays in updating information.Utilizing spatially associated points within community jurisdictions offers a promising approach to address the complexities involved in generating accurate community boundaries.In this paper,we propose CB-GCN,a novel community boundary generation algorithm that integrates volunteered geographic information with graph neural network.This approach ensures the generation of high-quality,cost-effective,and timely community boundaries,even in the presence of complex point distributions and intricate regional divisions.CB-GCN consists of three fundamental components:semantic spatial feature extraction,spatial relationship graph construction,and jurisdictional area affiliation inference.In the initial phase of semantic feature extraction,the city area is partitioned into blocks using a multi-level road network.These blocks are then divided into spatial units based on the spatial coordinates of individual buildings.The use of semantic Areas of Interest (AOIs) and the multi-level road network blocks facilitates the extraction of containment and adjacency relationships between spatial units,which are crucial for constructing the spatial relation graph.During the phase of spatial relationship graph construction,edges are established between spatial units according to the extracted spatial semantic relationships,resulting in a comprehensive spatial relationship graph.The affiliation inference phase involves inferring proximity relationships between spatial units using graph convolutional networks.Spatially related point features of neighboring nodes are then aggregated with weighted adjustments based on these proximity relationships to accurately determine community affiliations.Based on the aggregation results,community affiliations of spatial units are classified,leading to the identification of definitive community jurisdictional boundaries.Experimental results demonstrate that CB-GCN substantially outperforms baseline methods in generating community jurisdictional boundaries,achieving notable improvements of 9.4％ in F1-score and 14.4％ in Intersection over Union (IoU).CB-GCN has also proven effective in complex scenarios involving fragmented jurisdictional areas,such as when a single AOI is intersected by multiple jurisdictional regions.Furthermore,CB-GCN can effectively generating regional AOIs despite variations in building distribution patterns and densities.By automating the generation of community jurisdictional boundaries,CB-GCN significantly enhances the efficiency of producing community boundary interest areas,representing a substantial advancement in boundary delineation methodologies.
NETL
NSTL
万方数据
