Bus bunching from a stop-based perspective: insights from visual analytics

Abstract

Bus bunching can deteriorate bus service quality and jeopardise the effectiveness of public transit in promoting sustainable urban transport. This study applies artificial intelligence (AI) techniques in visual analytics to examine the spatiotemporal characteristics of bus bunching from a stop-based perspective. A total of 25 405 real-time traffic images were extracted and analysed from 11 bus stops in Hong Kong in August 2019 (7am–7pm, Tuesdays–Thursdays). An image classification model was developed with an overall accuracy of 85%. Three distinct groups were identified based on the spatiotemporal characteristics of bus bunching at different bus stops. They are (a) systematic peak hour, (b) minor and intermittent and (c) random bus bunching. Specific traffic conditions in terms of traffic speed, traffic composition and bus occupancy rate are highly associated with the onset of bus bunching. Overall, traditional bus management tactics such as schedule synchronisation and headways control need to be supplemented by stop-based strategies that consider the temporal profiles of bus bunching and associated traffic conditions on road.