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.     

The variation in the value of travel-time savings and the dilemma of high-speed rail in China

This paper examines the variation in the value of travel-time savings (VTTS), a fundamental element determining the market demand for high-speed rail. Following a review of time allocation theories, a time allocation model for general travel behavior is proposed as a further elaboration of Evans’ (1972) activities analysis. There are relationships among activities that can be expressed using a linear inequality to show the constraints on the arrangement of activities. This model indicates that two or more activities can be simultaneously rearranged to improve time management, which may be a source of variation in VTTS. This time allocation model can explain why large-scale high-speed rail construction in China faces significant market risks and a high likelihood of economic loss. Data from a new ticket sales and booking system for railway passengers indicate that passengers prefer conventional overnight sleeper trains, rather than high-speed trains, for long-distance travel, which supports the analysis of the time allocation model.     

Grand challenges for high-speed rail environmental assessment in the United States

The comprehensiveness of environmental assessments of future long-distance travel that include high-speed rail (HSR) are constrained by several methodological, institutional, and knowledge gaps that must and can be addressed. These gaps preclude a robust understanding of the changes in environmental, human health, resource, and climate change impacts that result from the implementation of HSR in the United States. The gaps are also inimical to an understanding of how HSR can be positioned for 21st century sustainability goals. Through a synthesis of environmental studies, the gaps are grouped into five overarching grand challenges. They include a spatial incompatibility between HSR and other long-distance modes that is often ignored, an environmental review process that obviates modal alternatives, siloed interest in particular environmental impacts, a dearth of data on future vehicle and energy sources, and a poor understanding of secondary impacts, particularly in land use. Recommendations are developed for institutional investment in multimodal research, knowledge and method building around several topics. Ultimately, the environmental assessment of HSR should be integrated in assessments that seek to understand the complementary and competitive configurations of transportation services, as well as future accessibility.     

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.     

Long-term impact of the Shinkansen on rail and air demand: analysis with data from Northeast Japan

This paper analyses how the high-speed rail construction in Northeast Japan (Tohoku) has affected total demand and interregional travel patterns. We use annual interregional passenger data from 1989 to 2012 and apply regression analysis with the demand between Tokyo and the Tohoku prefectures as the dependent variable. We distinguish particularly between the ‘Full-’ and the ‘Mini-’ Shinkansen, where the latter are branch services running with reduced speed. We find that the ‘Full-Shinkansen’ quickly increases rail and total public transport trips and generates additional rail demand year on year. The ‘Mini-Shinkansen’ impacts are less pronounced. Furthermore, our analysis shows that the Shinkansen has shifted some demand from air to rail once it started operation and increased rail share gradually. We therefore suggest that predictions of demand impacts should carefully distinguish immediate from gradual impacts. We also discuss differences in regional demand in that not all prefectures have gained equally from Shinkansen construction.     

The impact of high-speed rail investment on economic and environmental change in China: A dynamic CGE analysis

This study investigates the impact of high-speed rail investment on the economy and environment in China using a computable general equilibrium (CGE) model. The analysis is implemented in a dynamic recursive framework capturing long-run capital accumulation and labor market equilibrium. A national level impact was simulated through direct impact drivers including land use conversion, output expansion, cost reduction, productivity increase, transport demand substitution and induced demand. The results suggest that rail investment in China over the past decade has been a positive stimulus to the economy, while the effect on CO₂ emissions generation has been large. Overall, the economic impacts of rail investment are achieved primarily through induced demand and output expansion, whereas the contribution from a reduction of rail transportation costs and rail productivity increases were modest. In addition, negligible negative impacts were found from land use for rail development and the substitution effect among other modes. Emissions reduction from substitution of rail for other modes was small and offset by output expansion due to lowered rail transport costs and induced demand.     

Achieving environmental sustainability beyond technological improvements: Potential role of high-speed rail in the United States of America

In order to reduce energy use and cut emissions that contribute to climate change, countries need to radically reinvent their fossil-fuel intensive transportation systems. As a major consumer of energy and contributor to greenhouse gas (GHG) emissions, the U.S. transportation sector faces extraordinary challenges in the twenty-first century. Transportation in the U.S. depends heavily on fossil-fuel dependent cars and planes to the near exclusion of more energy-efficient electric trains. In order to address this concern, some policy makers refer to “technological optimism” which seeks no systemic change but instead focuses on employing technology to reduce the energy demand and environmental impact of the status quo. On the other hand, some researchers suggest a systematic paradigm shift away from cars and planes to intermodal systems that improve the sustainability of the system as a whole. High-speed rail (HSR) is arguably such an investment that can further this shift and help to achieve a more diversified and balanced transportation system. In this respect, by largely examining the role of the U.S. cars and planes “culture” in the economy, this paper elaborates on how building a HSR system may help U.S. advance towards environmental sustainability in transportation, make a break from the status quo, and create a more balanced, multimodal transportation system that will improve the quality and efficiency of travel.     

Assessment of schedule-based and frequency-based assignment models for strategic and operational planning of high-speed rail services

Despite some substantial limitations in the simulation of low-frequency scheduled services, frequency-based (FB) assignment models are by far the most widely used in practice. They are less expensive to build and less demanding from the computational viewpoint with respect to schedule-based (SB) models, as they require neither explicit simulation of the timetable (on the supply side), nor segmentation of OD matrices by desired departure/arrival time (on the demand side).The objective of this paper is to assess to what extent the lack of modeling capabilities of FB models is acceptable, and, on the other hand, the cases in which such approximations are substantial and more detailed SB models are needed. This is a first attempt to shed light on the trade-off between (frequency-based) model inaccuracy and (scheduled-based) model development costs in the field of long-distance (e.g. High-speed Rail, HSR) service modeling.To this aim, we considered two modeling specifications estimated using mixed Revealed Preferences (RP) and Stated Preferences (SP) surveys and validated with respect to the same case study. Starting from an observed (baseline) scenario, we artificially altered the demand distributions (uniform vs. time-varying demand) and the supply configuration (i.e. train departure times), and analyzed the differences in modal split estimates and flows on individual trains, using the two different model specifications.It resulted that when the demand distribution is uniform within the period of analysis, such differences are significant only when departure times of trains are strongly unevenly spaced in time. In such cases, the difference in modal shares, using FB w.r.t. SB, is in the range of [0%, +5%] meaning that FB models tend to overestimate HSR modal shares. When the demand distribution is not uniform, the difference in modal shares, using FB w.r.t. SB, is in the range of [−10%, +10%] meaning that FB models can overestimate or underestimate HSR modal shares, depending on timetable settings with respect to travelers’ desired departure times. The differences in on-board train flow estimates are more substantial in both cases of uniform and not uniform demand distribution.     

Designing an integrated distribution system for catering services for high-speed railways: A three-echelon location routing model with tight time windows and time deadlines

An emerging task in catering services for high-speed railways (CSHR) is to design a distribution system for the delivery of high-quality perishable food products to trains in need. This paper proposes a novel model for integrating location decision making with daily rail catering operations, which are affected by various aspects of rail planning, to meet time-sensitive passenger demands. A three-echelon location routing problem with time windows and time budget constraints (3E-LRPTWTBC) is thus proposed toward formulating this integrated distribution system design problem. This model attempts to determine the capacities/locations of distribution centers and to optimize the number of meals delivered to stations. The model also attempts to generate a schedule for refrigerated cars traveling from distribution centers to rail stations for train loading whereby meals can be catered to trains within tight time windows and sold before a specified time deadline. By relaxing the time-window constraints, a relaxation model that can be solved using an off-the-shelf mixed integer programming (MIP) solver is obtained to provide a lower bound on the 3E-LRPTWTBC. A hybrid cross entropy algorithm (HCEA) is proposed to solve the 3E-LRPTWTBC. A small-scale case study is implemented, which reveals a 9.3% gap between the solution obtained using the HCEA and that obtained using the relaxation model (RM). A comparative analysis of the HCEA and an exhaustive enumeration algorithm indicates that the HCEA shows good performance in terms of computation time. Finally, a case study considering 156 trains on the Beijing-Shanghai high-speed corridor and a large-scale case study considering 1130 trains on the Chinese railway network are addressed in a comprehensive study to demonstrate the applicability of the proposed models and algorithm.     

Modeling traveler mode choice behavior of a new high-speed rail corridor in China

This study examines mode choice behavior for intercity business and personal/recreational trips. It uses multinomial logit and nested logit methods to analyze revealed preference data provided by travelers along the Yong-Tai-Wen multimodal corridor in Zhejiang, China. Income levels are found to be positively correlated with mode share increases for high-speed rail (HSR), expressway-based bus, and auto modes, while travel time and trip costs are negatively correlated with modal shift. Longer distance trips trigger modal shifts to HSR services but prevent modal shift to expressway-based auto use due to escalation of fuel cost and toll charges. Travelers are less elastic in their travel time and cost for trips by nonexpressway-based auto use modes. The magnitude of elasticity for travel time is higher than trip costs for business trips and lower for personal/recreational trips. The study provides some policy suggestions for transportation planners and decision-makers.     

A bi-level model for single-line rail timetable design with consideration of demand and capacity

This paper proposes a bi-level model to solve the timetable design problem for an urban rail line. The upper level model aims at determining the headways between trains to minimize total passenger cost, which includes not only the usual perceived travel time cost, but also penalties during travel. With the headways given by the upper level model, passengers’ arrival times at their origin stops are determined by the lower level model, in which the cost-minimizing behavior of each passenger is taken into account. To make the model more realistic, explicit capacity constraints of individual trains are considered. With these constraints, passengers cannot board a full train, but wait in queues for the next coming train. A two-stage genetic algorithm incorporating the method of successive averages is introduced to solve the bi-level model. Two hypothetical examples and a real world case are employed to evaluate the effectiveness of the proposed bi-level model and algorithm. Results show that the bi-level model performs well in reducing total passenger cost, especially in reducing waiting time cost and penalties. And the section loading-rates of trains in the optimized timetable are more balanced than the even-headway timetable. The sensitivity analyses show that passenger’s desired arrival time interval at destination and crowding penalty factor have a high influence on the optimal solution. And with the dispersing of passengers' desired arrival time intervals or the increase of crowding penalty factor, the section loading-rates of trains become more balanced.     

GHG-emission models for assessing the eco-friendliness of road and rail freight transports

Intermodal rail/road transportation is an instrument of green logistics, which may help reducing transport related greenhouse gas (GHG) emissions. In order to assess the environmental impact of road and rail transports, researchers have formulated very detailed microscopic models, which determine vehicle emissions precisely based on a vast number of parameters. They also developed macroscopic models, which estimate emissions more roughly from few parameters that are considered most influential. One of the goals of this paper is to develop mesoscopic models that combine the preciseness of micro-models while requiring only little more information than macro-models. We propose emission models designed for transport planning purposes which are simple to calibrate by transport managers. Despite their compactness, our models are able to reflect the influence of various traffic conditions on a transport’s total emissions. Furthermore, contrasting most papers considering either the road or the rail mode, we provide models on a common basis for both modes of transportation. We validate our models using popular micro- and macroscopic models and we apply them to artificial and real world transport scenarios to identify under which circumstances intermodal transports actually effect lower emissions. We find that travel speed and country-specific energy emission factors influence the eco-friendliness of intermodal transports most severely. Hence, the particular route chosen for a transnational intermodal transport is an important but so far neglected option for eco-friendly transportation.     

A multiple criteria approach for the evaluation of the rail transit networks in Istanbul

The deficiencies in the Istanbul transportation system have led the local authorities to plan several alternative transportation projects. In this paper three alternative rail transit network proposals are evaluated by using Analytic Hierarchy Process (AHP), a multiple criteria decision support system. The AHP facilitates decision-making by organizing perceptions, experiences, knowledge and judgments, the forces that influence the decision, into a hierarchical framework with a goal, scenarios, criteria and alternatives of choice. Based on this analysis, the decision makers have developed a new alternative as a combination of the most closely competing two alternative rail transit networks. This combination rail transit network is currently under construction.     

A review and analysis of the investment in,and cost structure of,intermodal rail terminals

The results presented in this article identify the role of costs in the scientific and grey freight terminal handling literature and analyses the handling costs of different terminal sizes. The literature review shows that handling costs only play a marginal role in the scientific research in intermodal rail freight terminals (IRT). This is remarkable given the large role costs occupy in decision-making in freight transport. Furthermore, the used cost levels show a wide range of proposed amounts and terminal sizes or handling technologies are seldom addressed. Finally, many of the scientific papers do not make it clear whether the average transhipment cost or market price is referred to. Next, the analysis of the investment in, and cost structure of, IRTs shows that IRT investments are very capital-intensive leading to relatively high average costs per handling. However, given the cost characteristics of IRTs, the average cost per handling represents the underlying cost structure and are – in this sense – representative. The cost analysis demonstrates that extra-large IRTs actually have the lowest average handling costs, followed by small IRTs.     

A three-phase QFD-based framework for identifying key passenger needs to improve satisfaction with the seat of high-speed rail in China

This study aims to suggest a three-phased methodological framework based on the operational approach of quality function deployment (QFD) to improve the service quality and passenger satisfaction with China’s high-speed rail (HSR) by identifying the key passenger needs with regard the HSR seats. For the first phase, the collection of the voice of the customers/passengers (VOC), the processing of the collected VOC into need items and further into passenger needs of QFD would be explained in terms of knowledge management. For the second phase, a reference comparison-based fuzzy best–worst method is developed for determining the relative importance of passenger needs, with a particular purpose of coping with the uncertainty and ambiguity associated with qualitative assessment of respondents. For the third phase, the importance-performance analysis is performed to determine the improvement priorities for meeting passenger needs. Findings showed that Body-friendly seat structure and Reasonable layout of the seat are the two most important needs demanded by the passengers of second-class cabins, with the former being the top priority. The current study provides useful references for service operators of HSR to formulate development strategies for improving the seat comfortability, which subsequently contributes to improving HSR’s service quality and passenger satisfaction. Moreover, the proposed methodological framework for identifying the important passenger needs can be appropriately adjusted and expanded to similar transportation infrastructures and facilities.

     

A two-phase model for dry port location with an application to the port of Dalian in China

This paper provides guidance for an optimal and reasonable dry port layout for the port of Dalian in China. We present a two-phase framework on the location of dry ports, which solves the selection of candidate inland cities and optimal dry port location choice, respectively. Fuzzy C-Means Clustering is applied to select alternative cities in the vast hinterland of the seaport of Dalian, with a view to identify evaluation factors that affect the location selection decision. A cost-minimisation linear programming solution is proposed, with the aid of a genetic algorithm, to choose the optimal location as well as capacity level among the candidate inland cities.     

A shockwave profile model for traffic flow on congested urban arterials

In this paper a new traffic flow model for congested arterial networks, named shockwave profile model (SPM), is presented. Taking advantage of the fact that traffic states within a congested link can be simplified as free-flow, saturated, and jammed conditions, SPM simulates traffic dynamics by analytically deriving the trajectories of four major shockwaves: queuing, discharge, departure, and compression waves. Unlike conventional macroscopic models, in which space is often discretized into small cells for numerical solutions, SPM treats each homogeneous road segment with constant capacity as a section; and the queuing dynamics within each section are described by tracing the shockwave fronts. SPM is particularly suitable for simulating traffic flow on congested signalized arterials especially with queue spillover problems, where the steady-state periodic pattern of queue build-up and dissipation process may break down. Depending on when and where spillover occurs along a signalized arterial, a large number of queuing patterns may be possible. Therefore it becomes difficult to apply the conventional approach directly to track shockwave fronts. To overcome this difficulty, a novel approach is proposed as part of the SPM, in which queue spillover is treated as either extending a red phase or creating new smaller cycles, so that the analytical solutions for tracing the shockwave fronts can be easily applied. Since only the essential features of arterial traffic flow, i.e., queue build-up and dissipation, are considered, SPM significantly reduces the computational load and improves the numerical efficiency. We further validated SPM using real-world traffic signal data collected from a major arterial in the Twin Cities. The results clearly demonstrate the effectiveness and accuracy of the model. We expect that in the future this model can be applied in a number of real-time applications such as arterial performance prediction and signal optimization.     

Heterogeneous hazard model of PEV users charging intervals: Analysis of four year charging transactions data

Public charging infrastructure represents a key success factor in the promotion of plug-in electric vehicles (PEV). Given that a large initial investment is required for the widespread adoption of PEV, many studies have addressed the location choice problem for charging infrastructure using a priori simple assumptions. Ideally, however, identifying optimal locations of charging stations necessitates an understanding of charging behavior. Limited market penetration of PEV makes it difficult to grasp any regularities in charging behavior. Using a Dutch data set about four-years of charging transactions, this study presents a detailed analysis of inter-charging times. Recognizing that PEV users may exhibit different charging behavior, this study estimates a latent class hazard duration model, which accommodates duration dependence, unobserved heterogeneity and the effects of time-varying covariates. PEV users are endogenously classified into regular and random users by treating charging regularity as a latent variable. The paper provides valuable insights into the dynamics of charging behavior at public charging stations, and which strategies can be successfully used to improve the performance of public charging infrastructure.     

Public financing of private freight rail infrastructure to reduce highway congestion: A case study of public policy and decision making in the United States

As goods movement continues to increase it is expected to outpace infrastructure capacity in the United States. Moving a larger share of goods by rail rather than truck is a potentially cost effective part of a solution. Freight rail not only offers a substitute for truck trips but is a cleaner, more energy efficient, and safer alternative. Recently a number of private freight rail projects have received public funding. The public funds are aimed at increasing freight rail capacity with the goal of diverting some goods currently moved by truck to rail. While the benefits of moving goods by rail are relatively clear, it is unclear if public decision makers can effectively identify strategic rail investments that will achieve their policy goals. This study critically examines the analytical methods, models, and data that are commonly used to support decisions to provide public funds for private freight rail projects. This is accomplished through a case study of California’s Trade Corridors Improvement Fund program which provided $680 million for 11 freight rail projects. The study’s contributions include identifying critical analytical flaws and challenges affecting the benefit estimates that public funding decisions rely on. Improvements to current evaluation methods are also identified as are regulatory reforms and policy interventions that may offer more effective and reliable outcomes.     

A cell-based Merchant-Nemhauser model for the system optimum dynamic traffic assignment problem

A cell-based variant of the Merchant-Nemhauser (M-N) model is proposed for the system optimum (SO) dynamic traffic assignment (DTA) problem. Once linearized and augmented with additional constraints to capture cross-cell interactions, the model becomes a linear program that embeds a relaxed cell transmission model (CTM) to propagate traffic. As a result, we show that CTM-type traffic dynamics can be derived from the original M-N model, when the exit-flow function is properly selected and discretized. The proposed cell-based M-N model has a simple constraint structure and cell network representation because all intersections and cells are treated uniformly. Path marginal costs are defined using a recursive formula that involves a subset of multipliers from the linear program. This definition is then employed to interpret the necessary condition, which is a dynamic extension of the Wardrop’s second principle. An algorithm is presented to solve the flow holding back problem that is known to exist in many discrete SO-DTA models. A numerical experiment is conducted to verify the proposed model and algorithm.