The spatial homogeneity of an urban road network (URN) measures whether each distinct component is analogous to the whole network and can serve as a quantitative manner bridging network structure and dynamics. However, given the complexity of cities, it is challenging to quantify spatial homogeneity simply based on conventional network statistics. In this work, we use Graph Neural Networks to model the 11,790 URN samples across 30 cities worldwide and use its predictability to define the spatial homogeneity. The proposed measurement can be viewed as a non-linear integration of multiple geometric properties, such as degree, betweenness, road network type, and a strong indicator of mixed socio-economic events, such as GDP and population growth. City clusters derived from transferring spatial homogeneity can be interpreted well by continental urbanization histories. We expect this novel metric supports various subsequent tasks in transportation, urban planning, and geography.

本文提出了基于图形机器学习的方法来量化城市道路网络（URNs）中子网络的空间同质性，并发现在城市内和跨城市的空间同质性与社会经济地位以及跨城市的城市网络结构相似性高度关联。

利用图神经网络量化城市道路网络的空间均匀性