Predicting cycling volumes using crowdsourced activity data

Mark Livingston,David Mcarthur,Jinhyun Hong,Kirstie English

doi:10.1177/2399808320925822

Mark Livingston, David Mcarthur + Show 2 more

Open Access

https://doi.org/10.1177/2399808320925822

Copy DOI

Abstract

Planning for cycling is often made difficult by the lack of detailed information about when and where cycling takes place. Many have seen the arrival of new forms of data such as crowdsourced data as a potential saviour. One of the key challenges posed by these data forms is understanding how representative they are of the population. To address this challenge, a limited number of studies have compared crowdsourced cycling data to ground truth counts. In general, they have found a high correlation over the long run but with limited geographic coverage, and with counters placed on routes already known to be popular with cyclists. Little is known about the relationship between cyclists present in crowdsourced data and cyclists in manual counts over shorter periods of time and on non-arterial routes. We fill this gap by comparing multi-year crowdsourced data to manual cyclist counts from a cordon count in Scotland’s largest city, Glasgow. Using regression techniques, we estimate models that can be used to adjust the crowdsourced data to predict total cycling volumes. We find that the order of magnitude can be predicted but that the predictions lack the precision that may be required for some applications.

Highlights

The increasing importance of achieving sustainable urban transport means that planners and policy makers need reliable information on modes of travel such as cycling
We suggest it is more pertinent to ask whether the journeys made by cyclists using the Strava app can be considered representative of cycling journeys in general
Another factor in previous comparisons is that many studies calculate correlations over time at specific locations. This seems to highlight Strava data’s ability to detect the strong temporal/seasonal patterns that are known to exist for cycle trips, but it says little about the ability to explain spatial variation in cycling using this data source

Summary

Introduction

The increasing importance of achieving sustainable urban transport means that planners and policy makers need reliable information on modes of travel such as cycling. Researchers and planners look to fill these gaps with crowdsourced data. While crowdsourced mobility data and volunteered geographic information offer new opportunities for researchers to understand travel patterns, how these data can be used appropriately has not been fully explored. Such data have been used to study areas such as routing and navigation (Hendawi et al, 2013; Keler and Mazimpaka, 2016; Prandi et al, 2014), disaster management, wheelchair routing and health (Griffin and Jiao, 2015). This paper reports on research that increases our understanding of the limitations of these data and extends the analysis to account for changes over time and the ability to predict out-of-sample cycling numbers

Background

Limitations

Findings

Discussion and conclusion