Bike Sharing Research Articles

Forecasting the Usage of Bike-Sharing Systems through Machine Learning Techniques to Foster Sustainable Urban Mobility

Bike-sharing systems can definitely contribute to the achievement of sustainable urban mobility. In spite of this potential, their planning and operation are not free of difficulties. The main operational problem of bike-sharing systems is the unbalanced distribution of bicycles over the service region, resulting in zones where bicycles are scarce and zones where bicycles accumulate. In order to provide an acceptable level of service, the operator needs to carry out repositioning movements, which are costly. Bike-sharing repositioning optimization solutions have been developed that rely on the estimation of the expected number of requests and returns at each location. Errors in this prediction are directly transferred to suboptimal repositioning solutions. For this reason, the development of methodologies able to accurately forecast bike-sharing usage is an issue of great concern. This paper deals with this problem using machine learning regression methods, which yield usage predictions from inputs such as historical usage and meteorological data. Three different machine learning regression techniques have been analyzed (i.e., random forest, gradient boosting, and artificial neural networks) and applied to a case study based on the New York City bike-sharing system. This paper describes the variables of the models and their calibration processes. Results are analyzed and compared in order to determine which one of the three techniques and under what conditions is the most adequate. Comparisons are not only made in terms of accuracy but also with respect to the applicability of the algorithms. Results indicate that, given the similar accuracy of all methods, the simpler calibration process of the random forest technique makes it advisable for most applications.

Short-Term Travel Volume Prediction and Delivery Volume Prediction of Shared Bicycles Built on Different Sites

Short-Term Travel Volume Prediction and Delivery Volume Prediction of Shared Bicycles Built on Different Sites

Prediction of bike-sharing station demand using explainable artificial intelligence

Bike-sharing systems have grown in popularity in metropolitan areas, providing a handy and environmentally friendly transportation choice for commuters and visitors alike. As demand for bike-sharing programs grows, efficient capacity planning becomes critical to ensuring good user experience and system sustainability in terms of demand. The random forest model was used in this study to predict bike-sharing station demand and is considered a strong ensemble learning approach that can successfully capture complicated nonlinear correlations and interactions between input variables. This study employed data from the Smart Location Database (SLD) to test the model accuracy in estimating station demand and used a form of explainable artificial intelligence (XAI) function to further understand machine learning (ML) prediction outcomes owing to the blackbox tendencies of ML models. Vehicle Miles of Travel (VMT) and Greenhouse Gas (GHG) emissions were the most important features in predicting docking station demand individually but not holistically based on the datasets. The percentage of zero-car households, gross residential density, road network density, aggregate frequency of transit service, and gross activity density were found to have a moderate influence on the prediction model. Further, there may be a better prediction model generating sensible results for every type of explanatory variable, but their contributions are minimum to the prediction outcome. By measuring each feature's contribution to demand prediction in feature engineering, bike-sharing operators can acquire a better understanding of the bike-sharing station capacity and forecast future demands during planning. At the same time, ML models will need further assessment before a holistic conclusion.

Investigating the impact of fuel price shocks on bicycle sharing usage in Budapest

The creation of sustainable urban communities is contingent upon the establishment of a sustainable, efficient, and fast transportation system. Bicycle sharing systems (BSS) are one of the most sustainable and inclusive ways of transportation in cities. An important question is how to increase BSS ridership and whether it can effectively replace cars in cities, hence contributing to achieving the 11th Sustainable Development Goal and creating sustainable urban communities. This paper aims to contribute to this stream of research by investigating the effect of fuel prices on BSS ridership. We exploit a natural experiment from Budapest, Hungary, where fuel prices were capped between November 15, 2021, and December 6, 2022. Once the price cap was suddenly eliminated, fuel prices increased by around one-third immediately leading to a very substantial and rarely observable one-time price increase. The difference-in-difference regression results indicate a 2–6% increase in BSS ridership after the elimination of the fuel price cap. The geographical pattern of the change shows that BSS usage mainly increased in the outer part of the city; however, some areas observed a decline. The regression results are also reinforced by survey findings. Understanding these dynamics is crucial for effective urban planning and transportation policymaking.

Assessment of loss of life owing to dam-failure flooding considering population distribution and evacuation

Dam failures pose a serious threat to the safety of downstream populations. Scientifically assessing loss of life (LOL) from dam-failure flooding contributes to the emergency response. Population distribution varies spatially and temporally even within a day, and has different information dissemination and response speeds, which impacts the chances of safe evacuation. This study established an LOL assessment model that considers the initial population distribution and population evacuation process. Shared bike big data and other multi-source data were used to identify daily population activity. The evacuation process includes receiving warnings, responses, and horizontal or vertical evacuation choices, and the evacuation results were then evaluated. This model was applied to a dam in China. During nighttime, commuting, and working hours, the issuance of warnings 214 min, 137 min, and 0 min prior to dam failure, respectively, significantly mitigated LOL. Under the same communication and response speeds, the commuting period poses the highest risk of LOL. Assessments of LOL due to dam failure flooding need to consider the impact of the timing of dam failure and population distribution. The model used in this study proposes varying effective early warning times based on the time of dam failure occurrence, which can contribute to effective dam risk management, helping prevent personnel loss.

Integration between Dockless Bike-Sharing and Buses: The Effect of Urban Road Network Characteristics

Globally, dockless bike-sharing (DBS) systems are acclaimed for their convenience and seamless integration with public transportation, such as buses and metros. While much research has focused on the connection between the built environment and the metro–DBS integration, the influence of urban road characteristics on DBS and bus integration remains underexplored. This study defined the parking area of DBS around bus stops by a rectangular buffer so as to extract the DBS–bus integration, followed by measuring the access and egress integration using real-time data on dockless bike locations. This indicated that the average trip distance for DBS–bus access and egress integration corresponded to 1028.47 m and 1052.33 m, respectively. A zero-inflated negative binomial (ZINB) regression model assessed how urban roads and other transportation facilities correlate with DBS–bus integration across various scenarios. The findings revealed that certain street patterns strongly correlate with frequent connection hotspots. Furthermore, high-grade roads and ‘dense loops on a stick’ street types may negatively influence DBS–bus integration. The increase in the proportion of three-legged intersections and culs-de-sac in the catchment makes it difficult for bus passengers to transfer by DBS. These insights offer valuable guidance for enhancing feeder services in public transit systems.

Evaluating the Impact of Maintenance Actions on Diverse Users in Shared Automobile, Bicycle, and Pedestrian Facilities

Evaluating the Impact of Maintenance Actions on Diverse Users in Shared Automobile, Bicycle, and Pedestrian Facilities

Decision System Based on Markov Chains for Sizing the Rebalancing Fleet of Bike Sharing Stations

Decision System Based on Markov Chains for Sizing the Rebalancing Fleet of Bike Sharing Stations

Developing deep learning models for predicting urban bike-sharing usage patterns

Urban traffic systems are facing significant challenges due to the ever-growing number of vehicles on the road, leading to increased congestion and suboptimal traffic flow. Traditional research focusing on individual traffic flows is often insufficient to meet the complex demands of modern urban transportation. While studying integrated shared single-vehicle flows offers a potential solution to mitigate these issues, the unique characteristics of shared bikes present substantial obstacles to accurate traffic flow research. These obstacles include the high liquidity, sparsity, and variability of shared bikes, the vagueness of travel characteristics, the lack of correlation between travel groups, and the unpredictability of travel patterns. The study endeavors to confront the challenges above by proposing an innovative model that correlates multiuser interactions and elucidates behavioral dynamics. This model utilizes a deep clustering method to analyze the evolution of superlarge-scale shared bike systems in Beijing. It uncovers the complex mechanisms governing user behavior and employs a neural network algorithm to predict shared bike users’ travel patterns effectively. By focusing on the theoretical and algorithmic aspects of behavioral dynamics for large-scale shared single-vehicle flows, this study offers a unique contribution to the field, with significant implications for multi-traffic flow management and urban planning in scenarios with extensive multi-traffic flows.

The impact of the social-built environment on the inequity of bike-sharing use: A case study of Divvy system in Chicago

Bikeshare is increasingly recognized as a healthy travel behaviour worldwide. However, issues of inequity in bike-sharing usage exist and hinder the social benefits of bike-sharing system. This paper aims to unveil the spatiotemporal evolution of inequalities in bike-sharing usage and their social-built environment correlates, using Chicago’s Divvy system as a case study. Specifically, Gini coefficients and panel data regression models are applied to analyse equity concerns in bike-sharing uses and its social-built environmental factors. Thirty-two disadvantaged communities and forty-five non-disadvantaged communities are identified based on ethnicity, income, and education levels. The Gini index indicates a greater level of inequity and inconsistency in bike-sharing usage within disadvantaged communities compared to non-disadvantaged communities over time. Model results further reveal that built environment factors such as park space positively impact equitable bike-sharing uses in disadvantaged communities. In contrast, the social factor of educational levels in non-disadvantaged communities shows a negative relationship. These findings aim to promote essential, efficient, and equitable bike-sharing usage for Chicago, stakeholders and users.

Meteorological gaps in audits of pedestrian environments: a scoping review

BackgroundWeather and season are determinants of physical activity. Therefore, it is important to ensure built environments are designed to mitigate negative impacts of weather and season on pedestrians to prevent these losses. This scoping review aims to identify built environment audits of pedestrian environments developed for use during a specific weather condition or season. Secondly, this review aims to investigate gaps in the inclusion of relevant weather mitigating built environment features in pedestrian environment audit tools.MethodsFollowing a standard protocol, a systematic search was executed in CINAHL, Medline and Web of Science to identify built environment audit tools of pedestrian spaces. These databases were chosen since they are well-known to comprehensively cover health as well as multi-disciplinary research publications relevant to health. Studies were screened, and data were extracted from selected documents by two independent reviewers (e.g., psychometric properties and audit items included). Audit items were screened for the inclusion of weather mitigating built environment features, and the tool’s capacity to measure temperature, precipitation, seasonal and sustainability impacts on pedestrians was calculated.ResultsThe search returned 2823 documents. After screening and full text review, 27 articles were included. No tool was found that was developed specifically for use during a specific weather condition or season. Additionally, gaps in the inclusion of weather mitigating items were found for all review dimensions (thermal comfort, precipitation, seasonal, and sustainability items). Poorly covered items were: (1) thermal comfort related (arctic entry presence, materials, textures, and colours of buildings, roads, sidewalk and furniture, and green design features); (2) precipitation related (drain presence, ditch presence, hazards, and snow removal features); (3) seasonal features (amenities, pedestrian scale lighting, and winter destinations and aesthetics); and (4) sustainability features (electric vehicle charging stations, renewable energy, car share, and bike share facilities).ConclusionsCurrent built environment audit tools do not adequately include weather / season mitigating items. This is a limitation as it is important to investigate if the inclusion of these items in pedestrian spaces can promote physical activity during adverse weather conditions. Because climate change is causing increased extreme weather events, a need exists for the development of a new built environment audit tool that includes relevant weather mitigating features.

Developing a strategy of data collection and pre-processing to assess bike-sharing system station placements with the help of GIS

Our research presents a methodological framework for analyzing bicycle-sharing systems, using the self-service bike operations of JCDecaux in Toulouse as a case study. The objective was to identify a method for obtaining a cleansed and structured attribute list that could be useful in evaluating and optimizing the placement of bicycle rental docks. Utilizing open data, our approach involves developing a Python script within QGIS to create new layers around each of the 288 studied bicycle rental stations, based on a selected 100-meter buffer. This buffer size is chosen to reduce data overlap in dense urban settings. The script is designed to collect urban features within these buffers that register as multipolygons (mainly buildings) or points (amenities, transportation features), moreover it applies categorization of data, such as identifying and marking the different building types. The method includes a basic visualization of potential data in QGIS using OpenStreetMap.

Could free-floating bikeshare weed out station-based bikeshare? Analyzing the relationship between two bikeshare systems from bivariate flow clustering

Against the backdrop of the strong market expansion of free-floating bikeshare systems (FFBS), the future of government-funded station-based bikeshare system (SBBS) is a matter of controversy. Merely relying on point density analysis proves to be inadequate in reflecting the flow characteristic, this paper employs a flow clustering analysis to investigate the relationship between SBBS and FFBS. To recognize both bikeshare flow clusters with inhomogeneous density and shape in less time, we propose a two-step network-constrained bivariate flow clustering method that organically combines multiplex-network community detection and bivariate flow clustering method. The performance and applicability of the method in flow clustering detection is exemplified by the SBBS and FFBS systems in Nanjing. The results indicate that though FFBS outnumbers SBBS in terms of bikes, there are still specific flow clusters where SBBS performs better. Spatiotemporal patterns of flow clusters reveal that about one-third of flow clusters dominated by FFBS move from the metro station to the business district during the morning peak, while more SBBS-dominated flow clusters (55.4%) move from the residence to the metro station. Conversely, during the evening peak, flow clusters are observed in the opposite direction. Nevertheless, if the difference in bike numbers is significant, SBBS will be at a disadvantage. It is necessary for SBBS to prioritize resource allocation towards target groups and advantageous areas to prevent decentralized development. Our findings contribute to a more profound comprehension of the interplay between SBBS and FFBS, thereby offering more informed recommendations for strategically aligning the functions of bikeshare systems.

Are We Back to Normal? A Bike Sharing Systems Mobility Analysis in the Post-COVID-19 Era

In recent years, numerous cities around the world have adopted bike sharing systems (BSSs). The increasing popularity of these transportation means is directly related to their eco-friendly and health advantages. Several factors affect how citizens make use of BSS, for instance, the size and configuration of a city, where docking stations are located, the associated prices, and others. Moreover, these systems have different usage patterns that vary according to the month, day, or hour but remain constant when compared yearly. However, the onset of the COVID-19 pandemic modified mobility behaviors as various governments around the world implemented mobility restrictions to avoid the spread of the virus. The objective of this investigation is to determine if the usage patterns of BSSs have changed permanently or if we have recovered pre-pandemic levels and usage patterns. Given the special characteristics of each BSS, this study focuses on Barcelona’s BSS, called Bicing. To understand the impact of other BSSs, the further analysis of each system’s unique characteristics is necessary. The study employs bike usage information from the public open data service maintained by Barcelona City Hall, namely, the Open Data BCN website, from January 2019 to December 2023, and it covers mechanical and electrical bikes with more than 4 million records per month. The results show that usage patterns were similar before and after the pandemic; the usage increased in 2021 and 2022 and stabilized in 2023, registering a rise of 17.5% in Bicing usage from 2021 to 2023. However, bike type preferences have changed for reasons unrelated to the pandemic restrictions. The main limitation of this investigation is the lack of continuity in the data due to a change in the company that provides the service in Barcelona. For future research, data from other transportation means can be used to analyze all communication behavior in this city. Additionally, if data are available, a study by gender and age can be performed and used to improve the system for certain groups.

A Sustainable Dynamic Capacity Estimation Method Based on Bike-Sharing E-Fences

Increasing urban traffic congestion and environmental pollution have led to the embrace of bike-sharing for its low-carbon convenience. This study enhances the operational efficiency and environmental benefits of bike-sharing systems by optimizing electronic fences (e-fences). Using bike-sharing order data from Shenzhen, China, a data-driven multi-objective optimization approach is proposed to design the sustainable dynamic capacity of e-fences. A dynamic planning model, solved with an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II), adjusts e-fence capacities to match fluctuating user demand, optimizing resource utilization. The results show that an initial placement of 20 bicycles per e-fence provided a balance between cost efficiency and user convenience, with the enterprise cost being approximately 76,000 CNY and an extra walking distance for users of 15.1 m. The optimal number of e-fence sites was determined to be 40 based on the solution algorithm constructed in the study. These sites are strategically located in high-demand areas, such as residential zones, commercial districts, educational institutions, subway stations, and parks. This strategic placement enhances urban mobility and reduces disorderly parking.

Bike Sharing Demand Forecasting Based on the Informer Model

Advancements in machine learning and artificial intelligence have been instrumental in enhancing demand forecasting for shared transportation modes, significantly benefiting urban traffic management and promoting a balanced supply-demand dynamic. This study harnesses the deep learning Informer model to forecast bike-sharing demand, integrating multiple factors to provide an empirical foundation for transport scheduling and redeployment, thereby contributing to the advancement of the field. Our experimental analysis reveals that the Informer model outperforms LSTM in predictive accuracy, as evidenced by improved R² scores and MSE values, reflecting gains in training efficiency and predictive precision. Despite these advances, predictions for extreme demand values, particularly during peak usage periods, indicate potential areas for refinement. Future research directions are oriented towards optimizing model accuracy by leveraging multimodal data for a comprehensive analysis and enhancement of traffic management strategies. This approach aims not only to better predict demand and alleviate congestion but also to deliver more optimized solutions for businesses and convenience for users. Furthermore, the model's application extends beyond bike-sharing to other forms of shared mobility, such as electric scooters, potentially aiding in reducing carbon emissions and furthering the development of the sharing economy and environmental sustainability.

Retraction Note: A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system

Retraction Note: A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system

Unlocking Trends: Socio-Demographic Insights into Bike Sharing from the 2017 National Household Travel Survey

The implementation of bike-sharing systems represents a novel strategy aimed at enhancing urban mobility by offering shared bicycle services to improve accessibility and user convenience. Nevertheless, there has been a limited exploration into the user demographics of bike-sharing programs on a national scale. This study investigates the socio-demographic characteristics of bike-sharing system users, leveraging the 2017 National Household Travel Survey and negative binomial regression models. It finds that bike-sharing usage is more common among users than non-users, with African American and Hispanic individuals using the system more than other racial groups. Furthermore, low-income individuals (<USD 15,000) and residents of high-density areas (≥25,000 per square mile) show a higher tendency towards bike sharing. The research highlights the lack of national-level studies on bike-sharing user demographics and suggests that future policy and planning should address the needs of specific populations, aiming to enhance urban mobility and accessibility through bike-sharing services.

Impact of COVID-19 pandemic on characteristic of bike-sharing systems near metro and bus stations

ABSTRACT The COVID-19 pandemic has had a significant impact on various modes of mobility as it spread rapidly worldwide, leading to changes in the landscape of transportation. This research focuses on comparing the usage of bike-sharing and the shifts in cycling behaviour before (2019) and after (2020) the pandemic outbreak in Daejeon, South Korea. Additionally, it examines the role of bike-sharing as a supplementary mode of transport for public transportation systems such as buses and metros during these periods. Our analysis revealed that bike-sharing has become a more prominent mode of transport after the pandemic. We developed a model to calculate the demand ratio of bike-sharing within the catchment areas of bus and metro stations to assess its impact as a supplementary mode. The results indicate an increase in the usage of some dockless bike stations in the catchment areas of buses and metros by 0.22% and 7.29%, respectively. We also conducted a correlation analysis using Point of Interest (POI) data to understand the factors influencing bike-sharing usage. The findings suggest that travel behaviours have shifted towards commercial and recreational destinations. Given its cost-effectiveness and flexibility, bike-sharing could be a sustainable option for urban mobility. Therefore, city planners in Daejeon can use the results of this study to promote bike-sharing and cycling as viable transportation alternatives.

Cycling into the workshop: e-bike and m-bike mobility patterns for predictive maintenance in Barcelona’s bike-sharing system

Bike-sharing systems have emerged as a significant element of urban mobility, providing an environmentally friendly transportation alternative. With the increasing integration of electric bikes alongside mechanical bikes, it is crucial to illuminate distinct usage patterns and their impact on maintenance. Accordingly, this research aims to develop a comprehensive understanding of mobility dynamics, distinguishing between different mobility modes, and introducing a novel predictive maintenance system tailored for bikes. By utilising a combination of trip information and maintenance data from Barcelona’s bike-sharing system, Bicing, this study conducts an extensive analysis of mobility patterns and their relationship to failures of bike components. To accurately predict maintenance needs for essential bike parts, this research delves into various mobility metrics and applies statistical and machine learning survival models, including deep learning models. Due to their complexity, and with the objective of bolstering confidence in the system’s predictions, interpretability techniques explain the main predictors of maintenance needs. The analysis reveals marked differences in the usage patterns of mechanical bikes and electric bikes, with a growing user preference for the latter despite their extra costs. These differences in mobility were found to have a considerable impact on the maintenance needs within the bike-sharing system. Moreover, the predictive maintenance models proved effective in forecasting these maintenance needs, capable of operating across an entire bike fleet. Despite challenges such as approximated bike usage metrics and data imbalances, the study successfully showcases the feasibility of an accurate predictive maintenance system capable of improving operational costs, bike availability, and security.