Bike-sharing mobility patterns: a data-driven analysis for the city of Lisbon (original) (raw)
Related papers
Spatiotemporal Mining of BSS Data for Characterising Seasonal Urban Mobility Dynamics
International Journal on Advanced Science, Engineering and Information Technology, 2018
Digital traces of individual mobility can be revealed from the origin-destination sensing systems of BSS (Bicycle Sharing System). This record enables wide analysis of human mobility traits in urban area including pattern, trend, and anomalies. This study investigates and compares trip history of BSS open data from two cities, London and New York, along a year period with respect to annual weather data as explanatory factors. This aims to get insights about seasonal urban mobility dynamics both temporally and spatially. Results show that, for both cities, there are differences as well as similarities of temporal correlation level between riding behavior of BSS users and hour of the day, day of the week, season, and local weather. Practically, the most correlated factor can be further considered and used as predictive features. Meanwhile, the proposed spatial analysis shows the positive bikes imbalance occurs in the morning, mostly at inner stations because of inward flow, and vice versa. This spatial extent can be used for redistribution purpose, specifically in order to provide enough resources at the highly visited stations before peak time occurs.
Spatiotemporal analysis of urban mobility dynamics: a case study of bicycle sharing system
Understanding human mobility dynamics is of fundamental significance for many applications, and a wide range of data-driven mobility studies have been conducted using different datasets. Mobility traces which provide digital records of individual mobility allow analysis of individual mobility patterns, trends, and anomalies. Bicycle Sharing Systems (BSS) with origin-destination (OD) sensing systems that record departure and arrival times of each trip are among the most promising urban transport systems which do have such digital data available. BSS allow users to choose their own origin, route, and destination as well as travel time based on their needs. This flexibility leads to uncertainty on the operator side in terms of system use, and this thesis explores both uncertainty and regularity in demand to gain new insights for improving BSS deployments, services, and operations. Using BSS data from two cities (London and Washington DC), this thesis focuses on three main topics: station neighbourhood analysis, individual next place prediction, and prediction of system demand from system-level to individual station-level. Stations neighbourhood analysis aims to reveal the quality of connections among nearby stations by examining users' behaviour in choosing other stations when their commonly visited station is disturbed because it is of out of service (shutdown) or in an imbalanced state (full or empty). Two methods are proposed to conduct this analysis which are spatial-mobility-motifs and station temporary shutdown. Two metrics are also proposed to measure the quality of connections which are impact distance and usage transformation. Results show that 300 metres of travel distance is the impact distance of a station shutdown as measured by at least 20% usage change for nearby stations. 300 metres is also the most common distance that appears during motif analysis when users choose nearby stations within a neighbourhood. Results from these both analyses could be used to help BSS operators identify potentially ineffective stations and isolated stations. 300 metres can also be used as a standard distance between stations when deploying a new system or redesigning the existing network topology. User clustering aims to group users with similar mobility behaviour. Information theory is then used to measure the next-location predictability of each cluster. The goal is to identify highly predictable users so that useful services might be offered based on their predicted next place. Two temporal clustering metrics are proposed which are total trips (1 feature) and hourly trips across the day (24 features). These metrics adequately reflect the frequency and the regularity of user mobility. Three clusters are identified with distinct spatiotemporal characteristics which are named casual users, regular users, and commuters. Entropy analysis demonstrates that
Sustainability
The ongoing COVID-19 pandemic is creating disruptive changes in urban mobility that may compromise the sustainability of the public transportation system. As a result, worldwide cities face the need to integrate data from different transportation modes to dynamically respond to changing conditions. This article combines statistical views with machine learning advances to comprehensively explore changing urban mobility dynamics within multimodal public transportation systems from user trip records. In particular, we retrieve discriminative traffic patterns with order-preserving coherence to model disruptions to demand expectations across geographies and show their utility to describe changing mobility dynamics with strict guarantees of statistical significance, interpretability and actionability. This methodology is applied to comprehensively trace the changes to the urban mobility patterns in the Lisbon city brought by the current COVID-19 pandemic. To this end, we consider passenge...
Bikemi Bike-Sharing Service Exploratory Analysis on Mobility Patterns
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020
Bike Sharing Systems (BSS) are growing worldwide for the social and environmental benefits that they can provide. Thanks to the increasing popularity of the BSS and the availability of monitoring technologies, there is a continuous production of data that can help to understand bike usage and to improve its design and management. This study aims at exploring BSS users' mobility patterns habits and the demand for the service. To reach this scope, the available data have been preprocessed in order to allow data mining and data visualization with open source tools based on Python. The study case regards the BikeMi BSS of the City of Milan between June 2015 to December 2018. The suggested approach proceeded, first, with the categorization of the user typology based on the frequency of use of the service; at a second stage, the influence of the day typology on the use of the service has been explored; third, the spatial and temporal patterns of the BSS use among the stations has been analysed; fourth, the influence of meteorological conditions on the use of the service has been considered; at last, the clustering of the stations with similar bikes use activity through K-Means has been performed. As expected, it was observed that the service is extensively used for commuting to work-related activities. Regular users compose a large part of the BSS community making use of the service mostly during weekdays. In addition, it was noted that only 'strong' meteorological conditions can impact the use of the service. Both the identification of the demand for the service and of the external factors that can affect its use support the clustering activities, allowing for the elimination of not relevant information and facilitating the interpretation of the obtained clusters.
A novel spatio-temporal clustering technique to study the bike sharing system in Lyon
2020
In the last decades cities have been changing at an incredible rate growing the needs of efficient urban transportation to avoid traffic jams and high environmental pollution. In this context, bike sharing systems (BSSs) have been widely adopted by major regions like Europe, North America and Asia-Pacific becoming a common feature of all metropolitan areas. Its fast growing has increased the need of new monitoring and forecasting tools to take fast decisions and provide an efficient mobility management. In this context we focus on the BSS of Lyon in France, called Vélo’v. In particular we analyse a dataset containing the loading profiles of 345 bike stations over one week, treating the data as continuous functional observations over a period of one day. The aim of this work is to identify spatio-temporal patterns on the usage of bike sharing stations, identifying groups of stations and days with similar behaviour, with the purpose of providing useful information to the fleet manager...
Examining spatio-temporal mobility patterns of bike-sharing systems: the case of BiciMAD (Madrid)
Journal of Maps
Over the past decades, Bike-Sharing Systems have been implemented in hundreds of cities all around the world. During this time, numerous academic studies have been published with analyses from different perspectives. The aim of this study is to build upon this research by bringing together a spatial and a temporal analysis of the cycling flow of BiciMAD, the Madrid Bike-Sharing System. By combining over 21 million GPS records and various maps the study visually explores cycling mobility patterns across the city on three different temporal scales: over the course of the day, during working days or weekends and over the course of a whole year to provide a better understanding of the season-dependent demand. The study also reveals the most important flows between origin-destination pairs and uncovers the radically different spatio-temporal travel patterns of frequent users and occasional users.
2021
The lockdown rules in London indeed change the citizen's mobility and the usage of public transport. Especially, the people's activities based on the docked bicycle system in London shows significant differences. In order to understand the impact of Lockdown rules on the cycling patterns and study the changes in people's intention with this shared bicycle system, our work focuses on the spatiotemporal changes in the daily usage of Santander Cycles, London before and during the lockdown. In this work, we achieved a comprehensive analysis from graph theory and hierarchical clustering, finding that citizens' daily cycling patterns have shown more regional differences after lockdown and also people are prone to use the shared bicycles for leisure purposes. With our current results, we could tentatively provide a basic outline of the new cycling patterns to the public sectors. And also, these new patterns influenced by the pandemic and lockdown rules show great significan...
Comparing cities’ cycling patterns using online shared bicycle maps
2015
Bicycle sharing systems are increasingly being deployed in urban areas around the world, alongside online maps that disclose the state (i.e., location, number of bicycles/number of free parking slots) of stations in each city. Recent work has demonstrated how regularly monitoring these online maps allows for a granular analysis of a city’s cycling trends; further, the literature indicates that different cities have unique spatio-temporal patterns, reducing the generalisability of any insights or models derived from a single system. In this work, we analyse 4.5 months of online bike-sharing map data from ten cities which, combined, have 996 stations. While an aggregate comparison supports the view of cities having unique usage patterns, results of applying unsupervised learning to the temporal data shows that, instead, only the larger systems display heterogeneous behaviour, indicating that many of these systems share intrinsic similarities. We further show how these similarities are reflected in the predictability of stations’ occupancy data via a cross-city comparison of the error that a variety of approaches achieve when forecasting the number of bicycles that a station will have in the near future. We close by discussing the impact of uncovering these similarities on how future bicycle sharing systems can be designed, built, and managed.
The Impact of SARS-COVID-19 Outbreak on European Cities Urban Mobility
Frontiers in Future Transportation, 2021
The global outbreak of the SARS-COVID-19 pandemic has changed our lives, driving an unprecedented transformation of our habits. In response, the authorities have enforced several measures, including social distancing and travel restrictions that lead to thetemporaryclosure of activities centered around schools, companies, local businesses to those pertaining to the recreation category. As such, with a mobility reduction, the life of our cities during the outbreak changed significantly. In this paper, we aim at drawing attention to this problem and perform an analysis for multiple cities through crowdsensed information available from datasets such as Apple Maps, to shed light on the changes undergone during both the outbreak and the recovery. Specifically, we exploit data characterizing many mobility modes like driving, walking, and transit. With the use of Gaussian Processes and clustering techniques, we uncover patterns of similarity between the major European cities. Further, we p...