Future Transp., Volume 1, Issue 1 (June 2021) – 8 articles

Predicting car ownership patterns at high spatial resolution is key to understanding pathways for decarbonisation—via electrification and demand reduction—of the private vehicle fleet. As the factors widely understood to influence car ownership are highly interdependent, linearised regression models, which dominate previous work on spatially explicit car ownership modelling in the UK, have shortcomings in accurately predicting the relationship. This paper presents predictions of spatially disaggregated car ownership—and change in car ownership over time—in Great Britain (GB) using deep neural networks (NNs) with hyperparameter tuning. The inputs to the models are demographic, socio-economic and geographic datasets compiled at the level of Census Lower Super Output Areas (LSOAs)—areas covering between 300 and 600 households. It was found that when optimal hyperparameters are selected, these neural networks can predict car ownership with a mean absolute error of up to 29% lower than when formulating the same problem as a linear regression; the results from NN regression are also shown to outperform three other artificial intelligence (AI)-based methods: random forest, stochastic gradient descent and support vector regression. The methods presented in this paper could enhance the capability of transport/energy modelling frameworks in predicting the spatial distribution of vehicle fleets, particularly as demographics, socio-economics and the built environment—such as public transport availability and the provision of local amenities—evolve over time. A particularly relevant contribution of this method is that by coupling it with a technology dissipation model, it could be used to explore the possible effects of changing policy, behaviour and socio-economics on uptake pathways for electric vehicles —cited as a vital technology for meeting Net Zero greenhouse gas emissions by 2050. Full article

The role of infrastructure in encouraging transportation cycling in smaller cities with a low prevalence of cycling remains unclear. To investigate the relationship between the presence of infrastructure and transportation cycling in a small city (Lethbridge, AB, Canada), we interviewed 246 adults along a recently-constructed bicycle boulevard and two comparison streets with no recent changes in cycling infrastructure. One comparison street had a separate multi-use path and the other had no cycling infrastructure. Questions addressed time spent cycling in the past week and 2 years prior and potential socio-demographic and psychosocial correlates of cycling, including safety concerns. Finally, we asked participants what could be done to make cycling safer and more attractive. We examined predictors of cycling using gender-stratified generalized linear models. Women interviewed along the street with a separate path reported cycling more than women on the other streets. A more favorable attitude towards cycling and greater habit strength were associated with more cycling in both men and women. Qualitative data revealed generally positive views about the bicycle boulevard, a need for education about sharing the road and for better cycling infrastructure in general. Our results suggest that, even in smaller cities, cycling infrastructure may encourage cycling, especially among women. Full article

The Park and Ride (P&R) system is integrated into the transport infrastructure of a city’s urban environment. P&R is an intermodal connection point between private vehicles and public transport, and therefore is considered a fundamental element in transport planning. The planning of a P&R system is linked to numerous parameters related to transport planning, such as origin and purpose of travel in the P&R system, P&R location problem, P&R and potential demand, P&R and catchment area, P&R and public transport, and P&R in the future transportation (autonomous, electric vehicles). Thus, the planning process becomes essential for the successful implementation of the P&R system. However, most studies have shown each part of the planning process separately. Therefore, the researchers in this paper have conducted a comprehensive analysis of the available literature on P&R system planning, and studies that consider the planning sections separately are to be part of the complete research. In conclusion, the planning of P&R facilities should not be regarded as a separate mobility design element. Instead, it should be viewed as an essential component integrated into the city’s urban environment. Full article

In this paper, we explore lifetime private mobility milestones in Greece and identify the factors that affect them, to explore the everchanging mobility landscape. In total, five archetypal private mobility milestones were examined: the age of getting a car driving license and the period until getting a car following that; the age of getting a motorbike driving license; the age of getting a first bicycle as an adult; and the age of first traveling by airplane. To this end, duration modeling and namely Kaplan-Meier and Cox Proportional Hazards models were developed. Results show that mobility paradigms are evolving and are affected by a wide array of factors. Generational differences are particularly highlighted, as younger travelers are less likely to get a car driving license or a car sooner but are more likely to get a bicycle as adults. Higher parents’ income diversely affects multiple mobility milestones. Growing up in rural locations and sustainable transport awareness also significantly affect mode choice related mobility milestones. Men were more likely to get both car and motorbike driving licenses at younger ages. The above results highlight the mobility profiles of Greek citizens and the factors that affect them, while offering insights into a future mobility landscape. Full article

In the last decades, car sharing has been a tool for city planners to reduce private car traffic and pollution in big urban areas. The emergence of the ICTs (Information and Communication Technologies), together with the development of the collaborative economy, has allowed for the birth of the new Free-Floating Carsharing (FFCS): A more flexible type of carsharing, in which electric cars can be used. Little research has been devoted using real FFCS flows data, to the FFCS impacts on user behavior and even on the public transport system thus far. Furthermore, in big metropolitan areas, central rail stations should promote modal interchanges, including new modes of electric FFCS systems. The aim of this paper is to design a web-based platform to collect and analyze FFCS demand on the surrounding areas of rail stations and makes a proposal to provide these systems with electrical recharging energy obtained from the regenerative braking of high-speed trains. This case study includes Atocha and Chamartín Central Stations in Madrid (Spain). Scientific evidence shows a high demand of FFCS cars at central rail stations and a trip profile with a short time duration linked to the closest districts of rail stations. Full article

Traffic forecasting remains an active area of research in the transport and data science fields. Decision-makers rely on traffic forecasting models for both policy-making and operational management of transport facilities. The wealth of spatial and temporal real-time data increasingly available from traffic sensors on roads provides a valuable source of information for policymakers. This paper adopts the Long Short-Term Memory (LSTM) recurrent neural network to predict speed by considering both the spatial and temporal characteristics of real-time sensor data. A total of 288,653 real-life traffic measurements were collected from detector stations on the Eastern Freeway in Melbourne/Australia. A comparative performance analysis among different models such as the Recurrent Neural Network (RNN) that has an internal memory that is able to remember its inputs and Deep Learning Backpropagation (DLBP) neural network approaches are also reported. The LSTM results showed average accuracies in the outbound direction ranging between 88 and 99 percent over prediction horizons between 5 and 60 min, and average accuracies between 96 and 98 percent in the inbound direction. The models also showed resilience in accuracies as the prediction horizons increased spatially for distances up to 15 km, providing a remarkable performance compared to other models tested. These results demonstrate the superior performance of LSTM models in capturing the spatial and temporal traffic dynamics, providing decision-makers with robust models to plan and manage transport facilities more effectively. Full article

The COVID-19 pandemic has had an enormous impact on the public transport sector. After the start of the pandemic, passenger demand dropped significantly for public transport services. In addition, social distancing measures have resulted in introducing pandemic-imposed capacity limitations to public transport vehicles. Consequently, public transport operators should adjust their planning to minimize the impact of the COVID-19 pandemic. This study introduces a mixed-integer quadratic program that sets the optimal frequencies of public transport lines and sublines in order to conform with the pandemic-imposed capacity. The focus is on cases where the public transport demand is high, but the crowding levels inside public transport vehicles should remain below the pandemic-imposed capacities. Of particular interest are public transport lines with skewed demand profiles that can benefit from the introduction of short-turning sublines that serve the high-demand line segments. The frequency setting model is tested on a network containing two high-demand bus lines in the Twente region in the Netherlands, and it demonstrates that the revenue losses due to social distancing can be reduced when implementing short-turning service patterns. Full article