Bayesian regionalization of urban mobility networks

A common method for delineating urban and suburban boundaries is to identify clusters of spatial units that are highly interconnected in a network of mobility flows, each cluster signaling a cohesive economic submarket. It is critical that the methods employed for this task are principled and free of unnecessary tunable parameters to avoid unwanted inductive biases while remaining scalable for high-resolution mobility data. Here, we systematically assess the benefits and limitations of a wide array of stochastic block models (SBMs)—a family of principled, nonparametric models for identifying clusters in networks—for regionalization with mobility data. We find that the data compression capability and relative performance of different SBM variants heavily depend on the spatial extent of the mobility network, its aggregation scale, and the method used for weighting network edges. By constructing a measure to assess the degree to which a network partition violates spatial contiguity, we find that traditional SBMs may produce substantial spatial discontiguities that require extensive postprocessing to make them suitable for regionalization. We propose a fast nonparametric agglomerative algorithm to alleviate this issue, achieving data compression close to that of unconstrained SBM models while ensuring spatial contiguity, benefiting from a deterministic optimization procedure, and being generalizable to wide range of community detection objective functions.