Characterizing the Temporal Patterns of Travel Production: A Bird's Eye View of the Urbanization Levels in The Netherlands

Abstract

This paper explores the temporal patterns in travel production using a full month of production data from traffic analysis zones (TAZ) in the (entire) Netherlands. This data is a processed aggregated derivative (due to privacy concerns) from GSM traces of a Dutch telecommunication company. This research thus also sheds light on whether such a processed data source is representative of both regular and non-regular patterns in travel production. To this end, the weekly patterns of hour-by-hour travel production of over 1200 TAZs are clustered using inception convolutional neural networks with k-mean methods. A silhoutte score shows that three dominant clusters can be discerned. Each cluster shows different within-day and day-to-day patterns in production. Furthermore, a spatial analysis of these clusters shows that they are related to urbanization levels: Urban, Rural, and mixed group. The findings of this study provide further insights in mobility, relevant for transportation analysis and policies.