Bike-sharing Stations Research Articles

Enhancing bikeshare planning and operation: Strategic use of web-based public feedback

Bikeshare system operators have leveraged online platforms to gather user feedback on station experiences and service quality. This crowdsourced data presents a valuable opportunity to enhance bikeshare planning and operations. However, planners have limited methods to analyze those qualitative data given the sparse nature of this data, which is insufficient for training comprehensive machine learning models. Addressing this challenge, our study employs a novel approach combining spatial analysis and Factor Analysis of Mixed Data (FAMD) to delve into bikeshare users’ perceptions and expectations. Focusing on Chicago’s bikeshare system, we utilize its limited online comments to demonstrate the robustness of our algorithm and its applicability to both large and small datasets. Our findings reveal a geographic pattern in feedback: negative comments on bike rebalancing, station locations, and facilities are concentrated in the city center, while dissatisfaction with the cycling environment is consistent across both urban and peripheral areas. Moreover, we discovered that the demographic and employment characteristics of areas surrounding bikeshare stations significantly influence positive feedback, overshadowing the impact of station design and local infrastructure. Overall, this study offers a quantitative framework for leveraging limited crowdsourced feedback effectively, providing strategic insights for refining bikeshare planning and operational decisions.

Multi-Source Data-Driven Local-Global Dynamic Multi-Graph Convolutional Network for Bike-Sharing Demands Prediction

The prediction of bike-sharing demand plays a pivotal role in the optimization of intelligent transportation systems, particularly amidst the COVID-19 pandemic, which has significantly altered travel behaviors and demand dynamics. In this study, we examine various spatiotemporal influencing factors associated with bike-sharing and propose the Local-Global Dynamic Multi-Graph Convolutional Network (LGDMGCN) model, driven by multi-source data, for multi-step prediction of station-level bike-sharing demand. In the temporal dimension, we dynamically model temporal dependencies by incorporating multiple sources of time semantic features such as confirmed COVID-19 cases, weather conditions, and holidays. Additionally, we integrate a time attention mechanism to better capture variations over time. In the spatial dimension, we consider factors related to the addition or removal of stations and utilize spatial semantic features, such as urban points of interest and station locations, to construct dynamic multi-graphs. The model utilizes a local-global structure to capture spatial dependencies among individual bike-sharing stations and all stations collectively. Experimental results, obtained through comparisons with baseline models on the same dataset and conducting ablation studies, demonstrate the feasibility and effectiveness of the proposed model in predicting bike-sharing demand.

Examining social-demographic determinants of bike-sharing station capacity

This study applied Negative Binomial models to examine the social-demographic determinants of bike-sharing station capacity. It used social-demographic data from Smart Location Database and over 7,000 bike-sharing stations located in the United States. Results revealed that the station's city, households with no cars, the percentage of workers aged 18–64, gas prices, the Caucasian population, gross residential density on unprotected land, intersection density, and low to medium-earning workers are associated with the increase in station capacity. Contrarily, station capacity decreased with vehicle miles traveled and the number of high-earning workers. Findings are crucial to planners and operators in improving bike-sharing operations.

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.

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

Data-driven prioritization strategies for inventory rebalancing in bike-sharing systems

The popularity of bike-sharing systems has constantly increased throughout the recent years. Most of such success can be attributed to their multiple benefits, such as user convenience, low usage costs, health benefits and their contribution to environmental relief. However, satisfying all user demands remains a challenge, given that the inventories of bike-sharing stations tend to be unbalanced over time. Bike-sharing system operators must therefore intervene to rebalance station inventories to provide both available bikes and empty docks to the commuters. Due to limited rebalancing resources, the number of stations to be rebalanced often exceeds the system’s rebalancing capacity, especially close to peak hours. As a consequence, operators are forced to manually select a subset of stations that should be prioritized for rebalancing. While most of the literature has concentrated either on predicting optimal station inventories or on the rebalancing itself, the identification of critical stations that should be prioritized for rebalancing has received little attention. Given the importance of this step in current operating practices, we propose three strategies to select the stations that should be prioritized for rebalancing, using features such as the predicted trip demand and the inventory levels at the stations themselves. Two sets of computational experiments aim at evaluating the performance of the proposed prioritization strategies on real-world data from Montreal’s bike-sharing system operator. The first set of experiments focuses on both the 2019 and 2020 seasons, each of which exhibits distinct travel patterns given the restrictive measures implemented in 2020 to prevent the spread of COVID-19. One of these strategies significantly improves by reducing the estimated lost demand by up to 65%, while another strategy reduces the estimated number of required rebalancing operations by up to 33% when compared to the prioritization scheme currently in use at the considered bike-sharing system. The second set of experiments evaluates the performance of the proposed strategies when rebalancing decisions are optimized in a rolling horizon planning. The results highlight various benefits of the proposed strategies, which are efficiently solved as transportation problems and improve lost demand over two intuitive baselines.

Dynamic demand patterns in the profit optimisation of bike-sharing station locations: an agent-based analysis of the greater Vienna region

ABSTRACT This study employs the MATSim agent-based simulation model to analyse bike-sharing station locations by examining dynamic trip flows and individual behavioural changes. It explores demand on a microscopic scale, capturing the behaviour of multi-segment trips. A protocol was established to evaluate different station configurations’ impact on profitability and demand. Findings suggest that optimising the station count from 219 to 66 strategic locations can significantly enhance both revenue and operational efficiency. The simulation produces data on the number of users arriving and departing from each station in different configurations, indicating the size of each station. This data allows stations to be classified into three types: generator, attractor, and interchange; displaying their changes across different configurations. This quantification offers operators insights for predicting bike distribution and planning operational strategies. Considering spatial and built environment factors, the findings underscore the potential of bike-sharing stations to evolve into mobility hubs, offering valuable insights for policymakers.

Optimizing bikeshare service to connect affordable housing units with transit service

Affordable housing and transit accessibility have long been focal points for housing and urban development agencies at all levels, from national to regional. However, these elements are often considered and planned for independently, leading over time to an expanding spatial gap between affordable housing and transit services. This separation creates issues of mobility equity. Fortunately, bikeshare, an emerging mobility solution, provides the potential to bridge this spatial gap between affordable housing communities and transit services. To leverage this, we designed a bikeshare station (BSS) location optimization tool that aims to alleviate the impacts of this spatial divide through bikeshare services. Specifically, we developed a multimodal agent-based modeling (ABM) and simulation framework aimed at enhancing accessibility to a variety of destinations. To solve this optimization problem, we developed a genetic algorithm to determine the optimal locations for BSS. There are three main conclusions from this research. First, the strategic positioning of BSS will enhance accessibility for affordable housing community (AHC) residents by reducing average transit travel time and walk distance, or increasing the number of destinations accessible by transit. This underscores the advantages of combining bikeshare and transit systems to cater to the mobility requirements of AHC residents, especially for non-work-related trips in suburban areas. Second, the relationship between transit and bikeshare is twofold: complementation and substitution. In instances where a lengthy trip involves multiple transit transfers and significant waiting time, bikeshare could replace some transit trips. Lastly, but most importantly, this study advises a forward-looking approach for governments and operators to avoid the waste of public resources when planning bikeshare systems. The tool developed by this research can facilitate this forward-looking approach in practice.

Bikeshare–Metrorail Integration in Washington, D.C.: What are the Characteristics of Neighborhoods that Encourage Capital Bikeshare Trips to and from the Metrorail?

Bikeshare has gained popularity worldwide and can serve as a first mile/last mile feeder for public transport. In many bikeshare systems, docking stations near a metrorail station are popular trip origins and destinations and bikeshare can help increase the ridership of the metrorail system as well. The goal of this study is to identify the determinants of bikeshare trips between neighborhood stations and bikeshare docking stations near the metrorail in Washington, D.C. For this study, we divided the bikeshare stations in Washington, D.C., into two categories: docking stations near a metrorail station (defined as bikeshare docking stations within a quarter mile radius of metrorail stations) and neighborhood stations (bikeshare docking stations outside the quarter mile radius of metrorail stations). We used two stepwise linear regression models of bikeshare trips between neighborhoods and metrorail stations stratifying the analysis by the determinants of neighborhood docking stations into four categories: socio-demographic conditions, transportation related, land use, and points of interests. In the backward elimination model, expanding the bike trail supply by an additional 100 m was associated with an increase in 70 annual bikeshare trips between a neighborhood station and a docking station near the metrorail. The forward selection model showed that a 1% increase in the poverty rate of the neighborhood stations was associated with 52 fewer annual such bikeshare trips. This study also found that adding bikeshare docking stations near national parks and neighborhoods with higher population density can promote bikeshare that starts/ends near metrorail stations.

Spatial Analysis of Bike-Sharing Ridership for Sustainable Transportation in Houston, Texas

This study aims to analyze bike-sharing information and related urban factors to promote bike-sharing utilization in Houston, Texas. The research was initiated with a descriptive analysis, where the hourly and daily variations in bike demand are investigated, thereby revealing the time-related patterns of bike tours. The models included data on socio-demographics, public transportation availability, land use patterns, tree canopy coverage, bike routes, and job density within 0.25-mile and 0.5-mile buffer zones around each bike-sharing station. Stepwise regression was utilized to examine the effects of urban factors on bike-sharing ridership, and the explanatory power of the model was enhanced by selecting meaningful variables. The analysis found that tree canopy coverage was a significant factor in influencing bike-sharing ridership. Expansion of tree coverage can help make biking a sustainable mode of transportation. These findings have the potential to guide the development of practical policies that aim to promote sustainable urban mobility through bike-sharing programs.

A feature correlation reinforce clustering and evolutionary algorithm for the green bike-sharing reposition problem

This paper tackles the green bike-sharing reposition problem (GBSRP) considering the reposition quality and carbon emission during the reposition simultaneously. With the expanding scale of today’s bike-sharing system (BSS), the environmental pollution during the reposition becomes obvious. GBSRP aims to satisfy the inventory request of every bike-sharing station through an identified route set while minimizing the routing fuel consumption and relevant carbon emission. This paper provides an effective feature correlation mechanism for both the clustering strategy and algorithm design, which aims at solving large-scale reposition. The original problem is clustered through the feature correlation reinforce clustering (FCRC) strategy. Then, a multi-objective evolutionary algorithm based on decomposition combined with feature correlation mechanism (FC-MOEA/D) is designed considering both the carbon emission and reposition quality. Finally, the carbon emissions of each module of the Comprehensive Modal Emissions Modeling under different reposition qualities are analyzed. The Pareto front of each instance is displayed and compared based on different clustering strategies and algorithms. The results demonstrate the competitiveness of the FCRC strategy and FC-MOEA/D algorithm. We also further discuss the relevant strategies for different reposition quality preferences and how they minimize the carbon emission during the reposition for BSS managers reference.

Geographic Information System-Based Comprehensive Shared Micromobility Station Siting Optimization for Small Urban Areas

Shared micromobility travel modes such as dockless e-scooters and bikeshare programs have become increasingly popular in the U.S. in the last decade because of their potential to improve multi-modal accessibility within communities. Smaller urbanized areas with lower population densities and fewer resources for system planning, operation, and maintenance present unique challenges with siting optimal station/service area locations. This research develops a comprehensive geographic information system (GIS)-based methodology for optimizing micromobility stations/service area locations using available and rasterized geospatial data to capture bikeshare demand indicators. Inputs are prioritized by overall importance according to the results of a survey of transportation professionals, with weights calculated by an analytic hierarchy process. These different factors are combined to create a new spatial index value to identify hotspots for candidate station/service area locations, which can be further analyzed to choose optimal locations based on the budgeted quantity of station/service area locations and ideal spacing between stations/service areas. The case study of the methodology is presented on a bikeshare station siting study in Iowa City, Iowa, U.S., using data from the Metropolitan Planning Organization of Johnson County. This research seeks to improve shared micromobility station/service area planning to better orient service to a variety of transportation goals including regular/commuting use, recreational use, equity, first/last mile connection to transit, and operational partnership opportunities. Multimodal travel times and job accessibility in the study area are evaluated both before and after the introduction of bikeshare, and both greatly improve with the introduction of optimal stations. Public agencies could expect to benefit from this comprehensive methodology because it uses easily obtainable data sources and provides the flexibility to weight the importance of factors differently to fit their communities’ specific transportation goals.

SUITABILITY ANALYSIS FOR URBAN BICYCLE TOURISM OF ILOILO CITY USING GIS

Abstract. Urban bicycle tourism refers to the recreational and enjoyable use of bicycles in navigating urban cities like Iloilo City. The city has already established an 11-kilometer cycling infrastructure within its boundaries. It is imperative to maximize its use to combat the negative impacts of rapid urbanization and promote safe and sustainable transportation. This paper shows the use of Geographic Information Systems (GIS) to assess the bike lanes network's suitability and accessibility for building a bike-sharing system that also caters to drop-off and ride-on points at each station. Deletion of duplicates and cleaning of road network data and tourist attraction point data was performed prior to any analysis. Service areas were generated to determine the number of tourist attractions catered by each potential bike share station – defined by main road intersections. Point distance analysis was performed to reduce the number of road intersections to just thirty-nine (39). Bicycle route maps and itineraries were produced to visualize the optimal routes tourists can use for exploring the city based on preferred sites category. From here, Route Analysis was conducted to create four (4) itineraries based on tourism categories: Top 10 Most Rated Tourist Attractions, Food and Dining, Museums and Churches, and Shopping and Leisure. The output maps and itineraries can be presented to the City Tourism Office of Iloilo City as a decision support tool for its programs and policies regarding bike lanes.

The Flow Termini Coverage Model for Locating Bike-Sharing Stations

As of 2022, more than 1,900 cities around the world had implemented bike-sharing systems (BSSs) with docking stations. Because there is a limit on how far most people are willing to walk to and from BSS stations, maximal coverage models have been a popular approach to optimizing dock station locations. Existing maximal coverage models, however, mainly evaluate demand coverage based on proximity to individual stations without considering the fact that BSS users must have dock stations convenient to both their pickup and drop-off sites. Given this, traditional single-node maximal coverage models might not locate stations to maximize the number of complete-able trips and will also tend to overestimate the coverage of demand. This study proposes a flow termini coverage model (FTCM) to locate BSS stations by considering the flow-based BSS usage demands and network connectivity. The model is tested on the Youbike system in Taipei, one of the most heavily used dock-station BSSs worldwide. This study compares the FTCM with both the traditional single-station maximal coverage model and Taipei’s official planning strategy. Results suggest that the FTCM consistently covers more origin–destination trips, especially in areas with unbalanced BSS usage. We also provide discussion on the cost–benefit trade-offs for transportation planners to choose the most appropriate modeling approaches. The FTCM could also be adapted to optimizing micromobility hubs for parking dockless shared bikes and e-scooters.

Taking a multimodal approach to equitable bike share station siting

Lack of reliable and efficient transportation is often cited as a pivotal barrier to healthcare and employment access. Many people without regular access to automobiles depend on public transit as their main mode of transportation. Shared bikes represent a significant opportunity to improve transit accessibility but have issues with low-density and inequitable distribution of services, typically in low-income areas. This study develops a method to estimate transit service supply within a region with micromobility using bus schedule and bike station location data. A bi-objective optimization model is developed and applied to Pittsburgh, USA as a case study, to illuminate how stakeholder preferences towards equity (i.e., improving mobility access for disadvantaged communities) impacts the design of docked bike share systems. Results indicate that bike share systems can significantly improve public transit supply within a region, particularly in neighborhoods that have bike stations deployed. High preference for equity enables disadvantaged communities to have greater access to transit routes, and a neutral preference for equity can help bridge transit supply disparities among population groups. Network connectivity constraints of bike share system necessitates a large number of stations to achieve comprehensive coverage of an urban area.

AI-Driven Decision Support System for Green and Sustainable Urban Planning in Smart Cities

Abstract This study focuses on innovative practices in sustainable urban planning, demonstrating significant advancements in key areas such as solar panel efficiency, rainwater harvesting capacity, community garden space, and bike-sharing station accessibility through in-depth experimentation and analysis. The research results show that the energy conversion rate of solar panels reached 25%, surpassing the market standard of 24%, which is crucial for enhancing self-sufficiency in energy in urban areas. The rainwater harvesting system performed well, achieving a capacity of 600 liters per square meter, slightly below the market rate of 650 liters, but still demonstrating significant potential in dense urban environments. Additionally, our project provided 3 square meters of community garden space per resident, exceeding the market average, effectively promoting urban greening and improving residents’ quality of life. In terms of transportation, our experimental model featured 1.5 bike-sharing stations per 1000 residents, better than the market data of 1.2 stations, contributing to the development of sustainable urban transportation. These outcomes not only showcase the potential of sustainable urban planning but also provide practical references and guidance for future urban development.

Optimized Demand Forecasting for Bike-Sharing Stations through Multi-Method Fusion and Gated Graph Convolutional Neural Networks

Optimized Demand Forecasting for Bike-Sharing Stations through Multi-Method Fusion and Gated Graph Convolutional Neural Networks

Photovoltaic-battery powered bike share stations are not necessarily energy self-sufficient

Many cities use solar photovoltaic (PV) panels to power off-grid bike share stations to provide sustainable transportation. When a station's energy demand for operating the station’s kiosk and docks exceeds the PV panel's supply, the battery can be depleted, requiring manual battery replacement to avoid service disruption. However, existing research on siting, modeling, or assessing the environmental impacts of bike share stations has not accounted for spatially variable solar PV potential and energy usage. This study addresses this gap to analyze the performances of PV-battery systems for bike share stations and evaluates strategies to improve their energy independence, sustainability, and system reliability. Using Chicago’s Divvy bike share system as a case study, we simulated the battery charging, discharging, and replacements, and measured their performances with three metrics: energy self-sufficiency level, energy payback time (EPBT), and station downtime. We found that PV energy alone is insufficient to meet all energy needs of bike share stations, with the average energy self-sufficiency levels being 56%. Additionally, relying solely on battery replacement during rebalancing operations was insufficient to maintain stations' operational status. On average, bike share operators need to manually replace a station’s batteries 72 times a year. Furthermore, the current PV panels for most stations are sized too small. Increasing panel sizes could reduce most stations' downtime and increase their self-sufficiency without significantly affecting EPBT. The study highlights the need for bike share system modeling and operation planning to account for battery replacement needs and demonstrates the importance to evaluate smaller yet large-scale street-level PV applications. The modeling framework presented in this study can also be extended to examine other smaller PV-battery systems similar to bike stations.

Investigating the application of deep learning to identify pedestrian collision-prone zones

The main objective of this study is to understand the factors that contribute to the frequency of both the total pedestrian-vehicle collisions and collisions that involve pedestrian violations and identify collision-prone areas. The two Full Bayes (FB) macro-level models were applied to historical collision records of the City of Hamilton to identify the collision-prone zones and the key factors that contribute to collision occurrence in TAZs. Finally, a self-organizing map (SOM) deep learning model was developed to identify collision-prone zones for the two collision classes. The results showed that the SOM model identified collision-prone zones with a high accuracy that exceeded the traditional Bayesian approach, based on the developed consistency test. As for the total collisions, the SOM model revealed that intersection density is the most important factor in distinguishing between collision-prone and non-collision-prone zones, followed by the pedestrian network directness and the proportion of residential land uses. As for the collisions that involved pedestrian violations, intersection density was also found to be the most important factor, followed by the density of bike-share stations and parking lots in a TAZ. The results of this study could aid planners in designing pedestrian-friendly networks and develop specific recommendations to enhance safety in unsafe zones.

Towards a smart city: modelling a bike-sharing station via a queueing loss system

Purpose: The article aims to build a mathematical model of a bike-sharing station based on an appropriate queueing system and show the model's usefulness in practice. Design/methodology/approach: In designing the model, constructing a queueing system described by exponential distributions with a finite accumulating buffer was used. The existence of the steady state of the system and the global balance principle were used to obtain analytical results. Findings: The most important analytical results are the stationary probability distribution of the number of rented bikes, the so-called loss probability (the probability that the customer has to resign from sharing due to the lack of bikes), as well as the average (mean) values of the number of rented bikes. Originality/value: The paper fits into the broadly understood trend of research related to the smart city concept. The proposed model may be beneficial in practice when designing specific solutions related to the development of bicycle rental stations. Keywords: Bike-sharing station, customer loss, queueing system, smart city, stationary state. Category of the paper: Research paper.