Boundary Prompting: Elastic Urban Region Representation via Graph-based Spatial Tokenization
This work addresses urban region representation for applications like urban planning and resource allocation, offering a novel method to handle dynamic boundaries, though it appears incremental as it builds on graph-based and tokenization techniques.
The paper tackles the problem of representing urban regions with fixed boundaries by proposing the Boundary Prompting Urban Region Representation Framework (BPURF), which allows for elastic region definitions using graph-based spatial tokenization, and demonstrates its effectiveness in capturing complex urban characteristics through extensive experiments.
Urban region representation is essential for various applications such as urban planning, resource allocation, and policy development. Traditional methods rely on fixed, predefined region boundaries, which fail to capture the dynamic and complex nature of real-world urban areas. In this paper, we propose the Boundary Prompting Urban Region Representation Framework (BPURF), a novel approach that allows for elastic urban region definitions. BPURF comprises two key components: (1) A spatial token dictionary, where urban entities are treated as tokens and integrated into a unified token graph, and (2) a region token set representation model which utilize token aggregation and a multi-channel model to embed token sets corresponding to region boundaries. Additionally, we propose fast token set extraction strategy to enable online token set extraction during training and prompting. This framework enables the definition of urban regions through boundary prompting, supporting varying region boundaries and adapting to different tasks. Extensive experiments demonstrate the effectiveness of BPURF in capturing the complex characteristics of urban regions.