Rhythm of the streets: a street classification framework based on street activity patterns

Abstract

As the living tissue connecting urban places, streets play significant roles in driving city development, providing essential access, and promoting human interactions. Understanding street activities and how these activities vary across different streets is critical for designing both efficient and livable streets. However, current street classification frameworks primarily focus on either streets' functions in transportation networks or their adjacent land uses rather than actual activity patterns, resulting in coarse classifications. This research proposes an activity-based street classification framework to categorize street segments based on their temporal street activity patterns, which is derived from high-resolution de-identified and privacy-enhanced mobility data. We then apply the proposed framework to 18,023 street segments in the City of Boston and reveal 10 distinct activity-based street types (ASTs). These ASTs highlight dynamic street activities on streets, which complements existing street classification frameworks, which focus on the static or transportation characteristics of the street segments. Our results show that a street classification framework based on temporal street activity patterns can identify street categories at a finer granularity than current methods, which can offer useful implications for state-of-the-art urban management and planning. In particular, we find that our classification distinguishes better those streets where crime is more prevalent than current functional or contextual classifications of streets.

Keywords: Clustering; FCM; Mobile phone GPS data; Street activity; Street classification; Temporal patterns; Urban management.

Figure 1

The framework of activity-based street classification

Figure 2

Identification of volume clusters. Boxplots indicating the distribution of average weekly total activity volume in the identified four Volume Clusters, where Subdued, Calm, Moderate and Vibrant Clusters are drawn from left to right

Figure 3

Spatial distribution of the volume clusters. The detailed map in each frame shows a zoom-in of Boston’s downtown area

Figure 4

Identification of pattern clusters. The line graphs show the average street activity rhythms of Work, Hybrid, and Leisure pattern clusters

Figure 5

Average street activity rhythms of ASTs

Figure 6

Spatial distribution of ASTs

Figure 7

ASTs of three example Boston neighborhoods and information of selected street segments, including Google Street View Images, ASTs, street categories in the functional classification system (i.e., CFCC), and street categories in contextual classification framework (i.e., land used-based framework)

Figure 8

The comparison between functional street types (on the left side) and AST results (on the right side)

Figure 9

The comparison between land use-based street types (on the left side) and AST results (on the right side)

Figure 10

The comparison between POI-based street types (on the left side) and AST results (on the right side)

Figure 11

Scatter plot of unweighted and weighted activity count for each street at each hour

Figure 12

Elbow method to choose best c for volume clustering, we choose $c=3$ where the elbow of the curve happens

Figure 13

Methods to choose best c for pattern clustering, on left plot, elbow of the curve happens at $c=3$ and 5, on right plot, the clustering achieves highest average silhouette score at $c=3$. Combining two plots together, we choose $c=3$ as the best cluster number for pattern clustering