Short-term forecasting of high-speed rail demand: A hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China

Short-term forecasting of high-speed rail (HSR) passenger flow provides daily ridership estimates that account for day-to-day demand variations in the near future (e.g., next week, next month). It is one of the most critical tasks in high-speed passenger rail planning, operational decision-making and dynamic operation adjustment. An accurate short-term HSR demand prediction provides a basis for effective rail revenue management. In this paper, a hybrid short-term demand forecasting approach is developed by combining the ensemble empirical mode decomposition (EEMD) and grey support vector machine (GSVM) models. There are three steps in this hybrid forecasting approach: (i) decompose short-term passenger flow data with noises into a number of intrinsic mode functions (IMFs) and a trend term; (ii) predict each IMF using GSVM calibrated by the particle swarm optimization (PSO); (iii) reconstruct the refined IMF components to produce the final predicted daily HSR passenger flow, where the PSO is also applied to achieve the optimal refactoring combination. This innovative hybrid approach is demonstrated with three typical origin–destination pairs along the Wuhan-Guangzhou HSR in China. Mean absolute percentage errors of the EEMD-GSVM predictions using testing sets are 6.7%, 5.1% and 6.5%, respectively, which are much lower than those of two existing forecasting approaches (support vector machine and autoregressive integrated moving average). Application results indicate that the proposed hybrid forecasting approach performs well in terms of prediction accuracy and is especially suitable for short-term HSR passenger flow forecasting.     

Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks

Reliable and accurate short-term subway passenger flow prediction is important for passengers, transit operators, and public agencies. Traditional studies focus on regular demand forecasting and have inherent disadvantages in predicting passenger flows under special events scenarios. These special events may have a disruptive impact on public transportation systems, and should thus be given more attention for proactive management and timely information dissemination. This study proposes a novel multiscale radial basis function (MSRBF) network for forecasting the irregular fluctuation of subway passenger flows. This model is simplified using a matching pursuit orthogonal least squares algorithm through the selection of significant model terms to produce a parsimonious MSRBF model. Combined with transit smart card data, this approach not only exhibits superior predictive performance over prevailing computational intelligence methods for non-regular demand forecasting at least 30 min prior, but also leverages network knowledge to enhance prediction capability and pinpoint vulnerable subway stations for crowd control measures. Three empirical studies with special events in Beijing demonstrate that the proposed algorithm can effectively predict the emergence of passenger flow bursts.     

A novel passenger flow prediction model using deep learning methods

Currently, deep learning has been successfully applied in many fields and achieved amazing results. Meanwhile, big data has revolutionized the transportation industry over the past several years. These two hot topics have inspired us to reconsider the traditional issue of passenger flow prediction. As a special structure of deep neural network (DNN), an autoencoder can deeply and abstractly extract the nonlinear features embedded in the input without any labels. By exploiting its remarkable capabilities, a novel hourly passenger flow prediction model using deep learning methods is proposed in this paper. Temporal features including the day of a week, the hour of a day, and holidays, the scenario features including inbound and outbound, and tickets and cards, and the passenger flow features including the previous average passenger flow and real-time passenger flow, are defined as the input features. These features are combined and trained as different stacked autoencoders (SAE) in the first stage. Then, the pre-trained SAE are further used to initialize the supervised DNN with the real-time passenger flow as the label data in the second stage. The hybrid model (SAE-DNN) is applied and evaluated with a case study of passenger flow prediction for four bus rapid transit (BRT) stations of Xiamen in the third stage. The experimental results show that the proposed method has the capability to provide a more accurate and universal passenger flow prediction model for different BRT stations with different passenger flow profiles.     

What determines rail transit passenger volume? Implications for transit oriented development planning

Transit oriented development (TOD) has been an important topic for urban transportation planning research and practice. This paper is aimed at empirically examining the effect of rail transit station-based TOD on daily station passenger volume. Using integrated circuit (IC) card data on metro passenger volumes and cellular signaling data on the spatial distribution of human activities in Shanghai, the research identifies variations in ridership among rail transit stations. Then, regression analysis is performed using passenger volume in each station as the dependent variable. Explanatory variables include station area employment and population, residents’ commuting distances, metro network accessibility, status as interchange station, and coupling with commercial activity centers. The main findings are: (1) Passenger volume is positively associated with employment density and residents’ commuting distance around station; (2) stations with earlier opening dates and serving as transfer nodes tend to have positive association with passenger volumes; (3) metro stations better integrated with nearby commercial development tend to have larger passenger volumes. Several implications are drawn for TOD planning: (1) TOD planning should be integrated with rail transit network planning; (2) location of metro stations should be coupled with commercial development; (3) high employment densities should be especially encouraged as a key TOD feature; and (4) interchange stations should be more strategically positioned in the planning for rail transit network.     

Improving the forecasting accuracy of air passenger and air cargo demand: the application of back-propagation neural networks

This study employs back-propagation neural networks (BPN) to improve the forecasting accuracy of air passenger and air cargo demand from Japan to Taiwan. The factors which influence air passenger and air cargo demand are identified, evaluated and analysed in detail. The results reveal that some factors influence both passenger and cargo demand, and the others only one of them. The forecasting accuracy of air passenger and air cargo demand has been improved efficiently by the proposed procedure to evaluate input variables. The established model improves dramatically the forecasting accuracy of air passenger demand with an extremely low mean absolute percentage error (MAPE) of 0.34% and 7.74% for air cargo demand.     

An optimization model of energy and transportation systems: Assessing the high-speed rail impacts in the United States

This paper presents a long-term investment planning model that co-optimizes infrastructure investments and operations across transportation and electric infrastructure systems for meeting the energy and transportation needs in the United States. The developed passenger transportation model is integrated within the modeling framework of a National Long-term Energy and Transportation Planning (NETPLAN) software, and the model is applied to investigate the impact of high-speed rail (HSR) investments on interstate passenger transportation portfolio, fuel and electricity consumption, and 40-year cost and carbon dioxide (CO₂) emissions. The results show that there are feasible scenarios under which significant HSR penetration can be achieved, leading to reasonable decrease in national long-term CO₂ emissions and costs. At higher HSR penetration of approximately 30% relative to no HSR in the portfolio promises a 40-year cost savings of up to $0.63 T, gasoline and jet fuel consumption reduction of up to 34% for interstate passenger trips, CO₂ emissions reduction by about 0.8 billion short tons, and increased resilience against petroleum price shocks. Additionally, sensitivity studies with respect to light-duty vehicle mode share reveal that in order to realize such long-term cost and emission benefits, a change in the passenger mode choice is essential to ensure higher ridership for HSR.     

Isolating high-priority metro and feeder bus transfers using smart card data

Fixed-rail metro (or ‘subway’) infrastructure is generally unable to provide access to all parts of the city grid. Consequently, feeder bus lines are an integral component of urban mass transit systems. While passengers prefer a seamless transfer between these two distinct transportation services, each service’s operations are subject to a different set of factors that contribute to metro-bus transfer delay. Previous attempts to understand transfer delay were limited by the availability of tools to measure the time and cost associated with passengers’ transfer experience. This paper uses data from smart card systems, an emerging technology that automatically collects passenger trip data, to understand transfer delay. The primary objective of this study is to use smart card data to derive a reproducible methodology that isolates high priority transfer points between the metro system and its feeder-bus systems. The paper outlines a methodology to identify transfer transactions in the smart card dataset, estimate bus headways without the aid of geographic location information, estimate three components of the total transfer time (walking time, waiting time, and delay time), and isolate high-priority transfer pairs. The paper uses smart card data from Nanjing, China as a case study. The results isolate eight high priority metro-bus transfer pairs in the Nanjing metro system and finally, offers several targeted measures to improve transfer efficiency.     

快速公交系统（BRT）规划模式分类研究

文章通过汇总已建的城市快速公交系统的数据,从投入成本和预期达到的客运量两方面因素入手,将快速公交规划模式分为库里提巴模式、波哥大模式、鲁昂模式及厦门模式,并对这四种模式的特征及具体内容进行了详细阐述,为城市快速公交系统规划提供理论依据。     

Incorporating sustainability assessment in transportation planning: an urban transportation vehicle-based approach

Environmental assessments are on the critical path for the development of land, infrastructure and transportation systems. These assessments are based on planning methods which, in turn, are subject to continuous enhancement. The substantial impacts of transportation on environment, society and economy strongly urge the incorporation of sustainability into transportation planning. Two major developments that enhance transportation sustainability are new fuels and vehicle power systems. Traditional planning ignores technology including the large differences among conventional, hybrid and alternative fuel vehicles and buses. The introduction of alternative fuel vehicles is likely to change the traditional transportation planning process because different characteristics need to be taken into account. In this study a sustainability framework is developed that enables assessment of transportation vehicle characteristics. Identified indicators are grouped in five sustainability dimensions (Environment, Technology, Energy, Economy and Users). Our methodology joins life cycle impacts and a set of quantified indicators to assess the sustainability performance of seven popular light-duty vehicles and two types of transit buses. Bus Rapid Transit receives the highest sustainability index and the pickup truck the lowest. Hybrid electric vehicles are found to have the highest sustainability index among all other passenger vehicles. A sensitivity analysis shows the proposed sustainability dimensions produce robust sustainability assessment for several weighting scenarios. The results are both technology and policy sensitive, thus useful for both short- and long-term planning.     

Public transport demand estimation by calibrating a trip distribution-mode choice (TDMC) model from passenger counts: A case study in Bandung,Indonesia

A problem always found in developing countries is the lack of information required for short, medium and long term planning purposes due to money and time constraints. This becomes even more valuable for problems which require ‘quick-response’ treatment. A flexible model approach allows monitoring a long term plan in order to check its short term performance at regular intervals using easily-available data. If found necessary, changes to the plan may be evaluated and eventually implemented. For this reason, the approach is deemed appropriate for long term planning and project evaluation even in the case of rapid changes in land-use, socio-economic and population parameters usually occurs in most of developing countries. A key element of the approach is a system to update the forecasting model (in particular its trip distribution and mode choice elements) using low-cost and/or easily-available information. Traffic counts are particularly attractive to be used in developing countries for planning purposes. The estimation of public transport demand, particularly important for planning purposes, is an expensive and time consuming undertaking. The need for a low-cost method to estimate the public transport demand is therefore obvious. The objective of this paper is the development of methods and techniques for modelling the public transport demand using traffic (passenger) count information and other simple zonal-planning data. We will report on a family of aggregate model combined with a family of mode choice logit models which can be calibrated from traffic (passenger) counts and other low-cost data. The model examined was the Gravity (GR) model combined with the Multi-Nominal-Logit (MNL) model. Non-Linear-Least-Squares (NLLS) estimation method was used to calibrate the parameter of the combined model. The combined TDMC model and the calibration method have been implemented into a micro-computer package capable of dealing with the study area consisting of up to 300 zones, 3000 links and 6000 nodes. The approach has been tested using the 1988 Public Transport Data Survey in Bandung (Indonesia). The model was found to provide a reasonably good fit and the calibrated parameter can then be used for forecasting purposes. General conclusion regarding the advantageous and the applicability of the approach to other environments are given.     

An integrated Bayesian approach for passenger flow assignment in metro networks

This paper proposes an integrated Bayesian statistical inference framework to characterize passenger flow assignment model in a complex metro network. In doing so, we combine network cost attribute estimation and passenger route choice modeling using Bayesian inference. We build the posterior density by taking the likelihood of observing passenger travel times provided by smart card data and our prior knowledge about the studied metro network. Given the high-dimensional nature of parameters in this framework, we apply the variable-at-a-time Metropolis sampling algorithm to estimate the mean and Bayesian confidence interval for each parameter in turn. As a numerical example, this integrated approach is applied on the metro network in Singapore. Our result shows that link travel time exhibits a considerable coefficient of variation about 0.17, suggesting that travel time reliability is of high importance to metro operation. The estimation of route choice parameters conforms with previous survey-based studies, showing that the disutility of transfer time is about twice of that of in-vehicle travel time in Singapore metro system.     

Measuring vulnerability of urban metro network from line operation perspective

Urban metro systems are subject to recurring service disruption for various reasons, such as mechanical or electrical failure, adverse weather, or other accidents. In recent years, studies on metro networks have attracted increasing attention because the consequence of operational accidents is barely affordable. This study proposes to measure the metro network vulnerability from the perspective of line operation by taking the Shanghai metro network as a case study. As opposed to previous studies that focused largely on disruption of important nodes or links, this study investigates the disruption from the line operation perspective. Betweenness centrality (BC) and passenger betweenness centrality (PBC), number of missed trips, weighted average path length, and weighted global efficiency were analyzed considering relative disruption probability of each line. Passenger flow distribution and re-distribution were simulated for different disruption scenarios based on all-or-nothing assignment rule. The results indicate that the metro lines carrying a large number of passengers generally have a significant impact on the network vulnerability. The lines with circular topological form also have a significant influence on passenger flow re-distribution in case of a disruption. The results of this study provide suggestions on metro system administration for potential improvement of the performance of operation, and passengers may meanwhile have an improved alternate plan for their commute trip when a disruption occurs.     

Dynamic charging infrastructure deployment for plug-in hybrid electric trucks

Inspired by the rapid development of charging-while-driving (CWD) technology, plans are ongoing in government agencies worldwide for the development of electrified road freight transportation systems through the deployment of dynamic charging lanes. This en route method for the charging of plug-in hybrid electric trucks is expected to supplement the more conventional charging technique, thus enabling significant reduction in fossil fuel consumption and pollutant emission from road freight transportation. In this study, we investigated the optimal deployment of dynamic charging lanes for plug-in hybrid electric trucks. First, we developed a multi-class multi-criteria user equilibrium model of the route choice behaviors of truck and passenger car drivers and the resultant equilibrium flow distributions. Considering that the developed user equilibrium model may have non-unique flow distributions, a robust deployment of dynamic charging lanes that optimizes the system performance under the worst-case flow distributions was targeted. The problem was formulated as a generalized semi-infinite min-max program, and a heuristic algorithm for solving it was proposed. This paper includes numerical examples that were used to demonstrate the application of the developed models and solution algorithms.     

Freight Data Assembling and Modeling: Methodologies and Practice

Abstract

In comparison to personal travel, freight movements within large metropolitan areas are much less studied. Most conventional transportation models and planning analysis that disregarded freight flows have been criticized on the plausibility of their results and conclusions. To alleviate these problems, this study proposes a non-survey based approach to assemble and process freight data in a systematic way. A freight origin–destination (OD) matrix of freight flows can be developed using secondary data sources. The estimated freight flows can be loaded together with conventional passenger flows onto the regional highway network of a large metropolitan area. As a case study, this non-survey based approach was applied to build a freight OD and study the traffic flows in Los Angeles. It concluded that this approach can be used to analyze urban freight movement in a low-cost way in which planning agencies can overcome the common omission of freight flow information in their transportation plans.     

Factors affecting car ownership and mode choice in rail transit-supported suburbs of a large Chinese city

As Chinese cities continue to grow rapidly and their newly developed suburbs continue to accommodate most of the enormous population increase, rail transit is seen as the key to counter automobile dependence. This paper examines the effects of rail transit-supported urban expansion using travel survey data collected from residents in four Shanghai suburban neighborhoods, including three located near metro stations. Estimated binary logit model of car ownership and nested logit model of commuting mode choice reveal that: (1) proximity to metro stations has a significant positive association with the choice of rail transit as primary commuting mode, but its association with car ownership is insignificant; (2) income, job status, and transportation subsidy are all positively associated with the probabilities of owning car and driving it to work; (3) higher population density in work location relates positively to the likelihood of commuting by the metro, but does not show a significant relationship with car ownership; (4) longer commuting distance is strongly associated with higher probabilities of riding the metro, rather than driving, to work; (5) considerations of money, time, comfort, and safety appear to exert measurable influences on car ownership and mode choice in the expected directions, and the intention to ride the metro for commuting is reflected in its actual use as primary mode for journey to work. These results strongly suggest that rail transit-supported urban expansion can produce important positive outcomes, and that this strategic approach can be effectively facilitated by transportation policies and land use plans, as well as complemented by timely provision of high quality rail transit service to suburban residents.     

Activity-based disaggregate travel demand model system with activity schedules

We present an integrated activity-based discrete choice model system of an individual’s activity and travel schedule, for forecasting urban passenger travel demand. A prototype demonstrates the system concept using a 1991 Boston travel survey and transportation system level of service data. The model system represents a person’s choice of activities and associated travel as an activity pattern overarching a set of tours. A tour is defined as the travel from home to one or more activity locations and back home again. The activity pattern consists of important decisions that provide overall structure for the day’s activities and travel. In the prototype the activity pattern includes (a) the primary – most important – activity of the day, with one alternative being to remain at home for all the day’s activities; (b) the type of tour for the primary activity, including the number, purpose and sequence of activity stops; and (c) the number and purpose of secondary – additional – tours. Tour models include the choice of time of day, destination and mode of travel, and are conditioned by the choice of activity pattern. The choice of activity pattern is influenced by the expected maximum utility derived from the available tour alternatives.     

An activity-based approach for scheduling multimodal transit services

This paper proposes a new activity-based transit assignment model for investigating the scheduling (or timetabling) problem of transit services in multi-modal transit networks. The proposed model can be used to generate the short-term and long-term timetables of multimodal transit lines for transit operations and service planning purposes. The interaction between transit timetables and passenger activity-travel scheduling behaviors is captured by the proposed model, as the activity and travel choices of transit passengers are considered explicitly in terms of departure time choice, activity/trip chain choices, activity duration choice, transit line and mode choices. A heuristic solution algorithm which combines the Hooke–Jeeves method and an iterative supply–demand equilibrium approach is developed to solve the proposed model. Two numerical examples are presented to illustrate the differences between the activity-based approach and the traditional trip-based method, together with comparison on the effects of optimal timetables with even and uneven headways. It is shown that the passenger travel scheduling pattern derived from the activity-based approach is significantly different from that obtained by the trip-based method, and that a demand-sensitive (with uneven headway) timetable is more efficient than an even-headway timetable.     

Bus Rapid Transit System in Istanbul: A Success Story or Flawed Planning Decision?

Abstract

There is a growing tendency in cities around the world to invest in Bus Rapid Transit (BRT) systems in an attempt to improve the capacity and quality of public transport services. The appeal of BRTs is based on their ability to combine the service level of rail transit systems with the flexibility of buses at relatively lower investment costs, and this was the motivation behind the opening of such a system in the Turkish city of Istanbul in 2007. This system has attracted mixed opinions as to its performance, as while passenger ridership figures are extremely high, proving the effectiveness of the system, there is an argument that the corridor should have been developed with rail technology, and that the BRT is failing to meet the demand. The paper presents a comprehensive analysis of this system, assessing its planning and performance through a comparative analysis of a number of BRTs in the world and Istanbul's metro and tram systems. The analysis confirms the success of the system in terms of passenger statistics, but also highlights a number of problems in certain planning decisions that should be addressed, thus taking the discussion beyond a simplified comparison of bus and rail technologies.     

Comparison of parametric and nonparametric models for traffic flow forecasting

Single point short-term traffic flow forecasting will play a key role in supporting demand forecasts needed by operational network models. Seasonal autoregressive integrated moving average (ARIMA), a classic parametric modeling approach to time series, and nonparametric regression models have been proposed as well suited for application to single point short-term traffic flow forecasting. Past research has shown seasonal ARIMA models to deliver results that are statistically superior to basic implementations of nonparametric regression. However, the advantages associated with a data-driven nonparametric forecasting approach motivate further investigation of refined nonparametric forecasting methods. Following this motivation, this research effort seeks to examine the theoretical foundation of nonparametric regression and to answer the question of whether nonparametric regression based on heuristically improved forecast generation methods approach the single interval traffic flow prediction performance of seasonal ARIMA models.     

基于交通渗流理论的城市轨道交通网络动态服务瓶颈识别

为准确把握轨道交通网络化运营的新态势和新要求,力求轨道交通系统在大客流下做到运输能力和服务水平的供需匹配,需对轨道交通网络的关键瓶颈进行有效识别和疏解。本文借鉴交通渗流理论,提出了限制网络整体服务水平和连通效能的动态服务瓶颈的识别方法,该方法综合考虑了城市轨道交通系统的网络特性、客流特性和服务特性。其中针对区间服务水平状态,该方法提出了定量评定的复合指标模型。以成都地铁线网为案例,基于实际客流运营数据,构建动态网络,识别服务瓶颈,验证了方法的适用性和准确性,对城市轨道交通系统运营管理有实际指导意义。