High-speed Rail Network Research Articles

AI-Driven Neural Networks for Real-Time Passenger Flow Optimization in High-Speed Rail Networks

AI-Driven Neural Networks for Real-Time Passenger Flow Optimization in High-Speed Rail Networks

Unsupervised domain adaptation for drive-by condition monitoring of multiple railway tracks

Monitoring railway tracks through drive-by vibration data collected by in-service trains offers a cost-effective and adaptable solution for inspecting multiple railway lines. However, numerous existing drive-by monitoring methods rely on supervised learning models, necessitating extensive labelled data for each line. In this paper, a novel framework is proposed based on Unsupervised Domain Adaptation (UDA) concept which facilitates the transfer of a geometric defects diagnosis model learned from one line to a new line without the need for any labelled data from the new line. The proposed framework learns the dynamic-based features that are sensitive to damage and also invariant to different railway tracks. It comprises three components: data pre-processing, UDA implementation, and damage diagnosis. The framework uses the data from the source domain, including corresponding labels, as well as the unlabelled data from the target domain as input. The outputs of the framework consist of the predicted labels for the target domain. The performance of the proposed framework is evaluated using a comprehensive dataset of field measurements of a high-speed train passing 4 different lines within the French high-speed rail network. The proposed UDA framework is implemented using four common UDA algorithms including Information-Theoretical Learning (ITL), Geodesic Flow Kernel (GFK), Transfer Component Analysis (TCA), and Subspace Alignment (SA). The results show that the proposed framework has a 14% increase in the anomaly detection accuracy compared to traditional unsupervised learning methods in which UDA is not used. Furthermore, this study investigates the impact of incorporating a percentage of target data labels during training (semi-supervised domain adaptation), along with various sensor layouts and different tuning parameters, on the accuracy of the proposed approach. The results show that the proposed framework can significantly facilitate the monitoring of railway track conditions using the data collected by in-service trains which could be great interest of railway owners.

Does government-driven infrastructure boost green innovation? Evidence of new infrastructure plan in China

The role of government-driven investment in improving environmental quality has long been an essential concern of environmental research. Using a spatial difference-in-differences model, this study investigates the influence of government-driven new infrastructure investment on green innovation. Based on a panel dataset of 276 Chinese cities from 2005 to 2019, we find a positive effect of high-speed rail (HSR) and smart city (SC) construction on green innovation. Compared with cities that are unconnected to the HSR network, those that are accessible by HSR experienced a 20.6 % increase in per capita green patents. In addition, being a SC planned by the government is associated with 14.8 % more green patents per capita than other cities. Moreover, government-promoted new infrastructure has significant spatial spillover effects on green innovation in adjacent cities. Regional sensitivity is found in promotional and spatial spillover effects. The findings of our study offer essential insights for developing effective policies for advancing infrastructure modernization and environmental protection simultaneously.

Empowering super-stars or rising-stars? Dynamics of the high-speed rail network planning in China

ABSTRACT The development of high-speed rail (HSR) systems as a critical component of the global 'infrastructure turn' is deeply embedded in regional socioeconomic contexts. Drawing on advances in actor-oriented network modelling and longitudinal inter-city HSR data in China during 2008-2022, this study explores how the evolution of the HSR network is dynamically and differentially underpinned by attribute-based effects of socioeconomic scale and growth rate to balance the short-term efficiency and long-term equity of nationwide development. After controlling for structure-based effects (transitive triads and balance) as well as attribute-based effects related to geographic, natural and cultural contexts, the results provide evidence that while the scale and the growth rate of economy and population both positively impact HSR link formation, the impacts of scale-related effects significantly diminish over time whereas the impacts of growth-rate-related effects exhibit a significant strengthening trend. The results further illustrate that while the scale-related and growth-rate-related effects of economy function as substitutes in driving HSR link formation, the two corresponding effects of population complement each other, providing evidence for the heterogeneous roles of economic and social contexts in underpinning HSR network planning. The findings provide implications for more effective and equitable regional socioeconomic development through strategic HSR network planning.

Connect to green: High-speed rail network and firms’ environmental performance

High-speed rail (HSR) has completely revolutionized intercity travel, significantly impacting economic activities. Recent studies have increasingly focused on how HSR affects environmental pollution. Given China’s extensive HSR policy in recent years, we extend this discussion in the context of China, introducing several new dimensions. Firstly, by manually collecting the daily operating routes of each HSR line in China, we construct a dynamic, directed, and weighted HSR network and provide a detailed description of the topological evolution of Chinese HSR from 2007 to 2014. Secondly, by employing network theory algorithms, we develop a city-level HSR strength index. This approach diverges from the commonly used multi-period difference-in-differences (DID) specification, allowing us to better address heterogeneity and discontinuity issues in identifying HSR effects. Thirdly, by leveraging the specific structure of the HSR network, we analyze how cities are interconnected and, for the first time, discuss the impact of “HSR-catalyzed supervision pressure” on firms’ pollution performance. Our findings show that firms exposed to higher HSR service intensity are more likely to reduce their SO2 emissions, a result that remains robust across various checks and other pollutants. We propose an intercity interaction story, predicting that HSR facilitates spillovers among city groups, thereby increasing environmental supervision pressure from neighboring cities in the HSR network. In further empirical analysis, we identify three specific sources of supervision pressure: peer pressure, vertical pressure, and public pressure.

Promotion Effects of High-Speed Rail on Urban Development: Evidence from Three Lines in China

Amid the vigorous development of the high-speed rail (HSR) network, local governments in China generally consider the construction of HSR as a crucial task in their regional development strategies. Currently, most provincial capitals and prefecture-level cities in the eastern and central regions of China already have operational HSR services. This study aims to examine a key question: has the objective of local governments to promote urban development through the construction of HSR been effective? The research selects cities along the Beijing–Shanghai, Beijing–Guangzhou, and Harbin–Dalian HSR lines as the study subjects. Based on the principles of proximity and similarity, cities with operational HSR and those without are chosen as the experimental group and the control group, respectively. Following the double difference (difference-in-differences) approach, an advantage index is proposed to systematically evaluate the impact of HSR operation on urban development from three dimensions: population aggregation, economic development, and expansion of construction land. Furthermore, the evaluation results are systematically clustered to identify city types that exhibit different promotional effects in various dimensions. The research findings indicate the following: (1) The promotion effect of HSR on the development of small to medium-sized cities is more reflected in economic growth and construction land growth. (2) The promotion effect of HSR on the development of large cities is more reflected in the growth of the employment population. (3) For smaller or economically less-developed cities, HSR may be detrimental to the aggregation of resident and employment populations. (4) Cities with moderate size and good economic development have the opportunity to use HSR to promote population aggregation. On this basis, combined with the findings above, strategies to promote the coordinated development of high-speed rail construction and urban systems are discussed.

Impact of high-speed railway network improvement on consumption synergy in Beijing-Tianjin-Hebei region

This paper investigates the impact of high-speed rail (HSR) network improvement on the consumption synergy of the Beijing-Tianjin-Hebei region by using the panel data of 13 prefectural-level cities from 2006 to 2021. The results show that: (1) The improvement of the HSR network in the Beijing-Tianjin-Hebei region has a significant positive impact on raising overall regional consumption levels. (2) The HSR network improvement has a heterogeneous impact on consumption in different cities within the Beijing-Tianjin-Hebei region. (3) The promotional effect on peripheral cities is greater than on central cities, thereby promoting the coordinated consumption development of the Beijing-Tianjin-Hebei region. The findings of this study have important policy implications, confirming that the construction of the HSR network can narrow the consumption gap within the region and promote consumption synergy across the region.

When green transportation backfires: High-speed rail's impact on transport-sector carbon emissions from 315 Chinese cities

High-speed rail is often viewed as a green transportation mode, substituting for carbon-intensive vehicular and aviation trips. However, its potential to induce additional travel demand and transport-sector carbon emissions has been largely overlooked. Here, we empirically examine the impacts of high-speed rail accessibility, the ease with which one city can reach other cities via the high-speed rail network, on transport-sector carbon emissions across 315 Chinese cities between 2010 and 2020, using a two-stage least squares model. Contrary to the anticipated emission-reduction effect, our analysis suggests a net positive impact of high-speed rail on transport-sector carbon emissions. Specifically, a 1% increase in high-speed rail accessibility leads to a 0.18% increase in transport-sector carbon emissions in the long run, as carbon emissions generated from induced travel demand have outweighed the carbon savings from substitution for carbon-intensive inter-city trips. This high-speed rail-induced increase in carbon emissions is observed in the road transport subsector, while the aviation subsector exhibits a compensatory reduction. Moreover, we find that integrating the high-speed rail network into local subway systems can curb the emission-intensifying effect, highlighting the importance of joint public transit planning. This study reveals an unexpected environmental impact of high-speed rail, conveying valuable insights into transport-sector decarbonization.

Land price dynamics in response to high-speed rail network characteristics: An empirical analysis

High-speed railway (HSR) has become the backbone of China's rapid and comprehensive urban transportation network system. However, the impact of the network characteristics of HSR on urban land prices has not been studied in sufficient detail. To fill this gap, this study focuses on both the Yangtze River Delta urban agglomeration and the Beijing-Tianjin-Hebei urban agglomeration and explores the linkage relationship between the HSR network and urban land prices. For this analysis, social network analysis and fixed effects model are used. The results show that the overall HSR network density of these two urban agglomerations still has room for improvement. Affected by regional proximity and the direction of HSR lines, HSR presents a spatial pattern of a multi-center–multi-tier network. The “siphon effect” is the main effect of the HSR network characteristics on land prices. However, the weakening degree of spatial spillover effect on siphon effect of the HSR network in the Yangtze River Delta urban agglomeration is stronger than that in the Beijing-Tianjin-Hebei urban agglomeration. Local governments should fully utilize the spatial effects of HSR and enhance the level of coordinated development among urban agglomerations.

Impact of high-speed rail on wage premiums for migrant workers in China

The extensive high-speed rail (HSR) network in China has significantly enhanced regional population mobility, yet its impact on the well-being of migrant workers remains underexplored. Utilizing data from the China Migrant Dynamic Survey (CMDS) from 2014 to 2018, this study investigates the influence of HSR on wage premiums for migrant workers and identifies the factors driving these premiums using the non-parametric nearest neighbor matching method. The findings reveal that HSR confers a significant wage premium of 13.1% for migrant workers in cities with HSR infrastructure compared to cities without it. This wage premium effect is particularly pronounced in less developed western China and in cities with larger populations and a higher proportion of tertiary sector economy. The study finds a 10.54% increase in wage premiums for intra-province migrant workers due to HSR, while the effect remains negligible for inter-province migrant workers. Moreover, the wage premium effect is stronger for higher-skilled labor and for migrant workers aged 16 to 45. It is particularly significant for professionals, administrative staff, and workers in the service industry. The HSR wage premium effect is multifaceted, exhibiting both level and growth effects, with the latter intensifying over time after HSR introduction. Overall, the findings suggest that HSR deployment positively influences migrant worker wages by enhancing travel convenience, improving market access, fostering knowledge spillovers, and facilitating industry transfers. However, these impacts vary by location, skill level, and industry.

High-speed rail new towns and their impacts on urban sustainable development: a spatial analysis based on satellite remote sensing data

With the rapid expansion of China’s high-speed rail network, numerous high-speed rail new towns have been established. While these new towns have brought about significant economic opportunities, they also impose pressure on local resources and environment. Accurately assessing the impacts of high-speed rail new towns on urban sustainable development is therefore a crucial issue to address. Our study employs satellite remote sensing data and spatial econometric methods to evaluate the impacts of 223 high-speed rail new towns in China from 2011 to 2021. The results indicate a gradual narrowing of development disparities among high-speed rail new towns in different cities. The construction of high-speed rail new towns has facilitated the sustainable development of cities. Notably, central high-speed rail new towns demonstrate a more considerably driving effect on the urban sustainable development compared to peripheral ones. The findings of the study provide valuable insights for policymakers and urban planners in China and other countries embarking on high-speed rail development projects. Our research highlights the importance of considering the potential impacts of high-speed rail new towns on the urban sustainable development and the need for careful planning and management to ensure that these newly-established towns contribute to a more sustainable urban future.

Transport capacity optimization for high-speed rail network considering flexible train composition and additional capacity pool

To balance the limited capacity and constantly changing demand in the high-speed rail network, a transport capacity optimization problem is investigated by adjusting train composition through uncoupling/coupling operations at the origin station, scheduling additional trains from the capacity pool, and optimizing the seat allocation among ODs. To make joint decisions, a two-stage stochastic programming model is formulated to minimize both operating cost and penalty cost for unsatisfied passengers, while incorporating various constraints such as flow conservation, loading capacity, flexible composition, etc. The two-stage model is linearized into a mixed-integer linear programming model, which can be effectively solved for small networks but is still intractable to solve for realistic networks. Therefore, a Lagrangian relaxation algorithm is proposed integrating parallel computing and sub-gradient method. Finally, two sets of case tests, including a toy network and a real-world case of a high-speed rail network in China, are implemented to show the performance of the proposed approach. The results illustrate that the parallel heuristic algorithm could generate a high-quality solution with a slight discrepancy from the optimal solution, while achieving a commendable computation time. Furthermore, the findings emphasize the advantages of applying flexible train composition and additional capacity pool in the high-speed railway system for cost-saving and supply–demand matching.

Analysis of Economic Development in Urban Agglomerations by High-Speed Rail Network: Taking Beijing-Tianjin-Hebei City Cluster as an Example

With the increasing impact of the opening of high-speed railway on the inner city, many indicators within the city have changed significantly, which plays an important role in the impact of the city's economy. Therefore, this paper explores how the high-speed railway network affects intra-city economic development based on the changes in three indicators of city size, per capita disposable income of residents and the structure of the three industries, as reflected by the population flow in the Beijing-Tianjin-Hebei city cluster. It is found that the opening of high-speed railway has led to a "siphon phenomenon" in the Beijing-Tianjin-Hebei urban agglomeration, which has both advantages and disadvantages for the development of large cities and small and medium-sized cities; it has a positive effect on the increase of disposable income of the residents; and it also has a positive effect on the development of tertiary industry.

High-Speed Rail: A game changer for Spanish motorway transport?

Spain has deployed the world’s largest High-Speed Rail (HSR) network, in per capita terms, under the premise that this infrastructure provides a cleaner mode for reaching their environmental commitments. However, for observing environmental gains, there should be inter-modal substitution from polluter modes to the HSR. This paper analyzes the impact of new HSR openings on car traffic, using a Generalized and Staggered Difference-in-Difference approach. Unlike previous studies, we analyzes the entire Spanish HSR network. We matched the georeferenced data on car traffic with the origin–destination routes provided by Google Maps API to estimate the impact of the HSR on car traffic. We found that the HSR has not generated modal split, except for few of the HSR segments, in which we estimated a 6%–8% reduction in the annual average daily traffic. These results have public policy implications for the transport policy in the EU, and the effectiveness of decarbonization policies.

Experimental Study on Compression Failure of Type II Ballastless Track Slab Based on Optical Fiber Sensing

Ballastless track structures are widely employed in high-speed rail networks because of their superior safety and durability. Among the various types of ballastless track, the Type II slab is currently one of the most extensively used and mature technologies in practice. Over the course of its service life, the damage within the ballastless track structure gradually accumulates in response to increased external loads. Therefore, it is crucial to continuously monitor the health condition of the track structure. In this study, a quasi-distributed fiber optic sensing system is adopted to monitor the deformation capacity and force performance of a Type II ballastless track slab under vertical load. The investigation aims to analyze the damage mechanism of the track structure under vertical pressure by assessing the deformation differences among its different components. The findings reveal that the incorporation of vertical reinforcement can enhance the pressure bearing capacity of the cement asphalt mortar layer to a certain extent, subsequently affecting the stress dilation. The stress performance of the ballastless track slab can be effectively monitored using the quasi-distributed fiber optic sensing technology under pressure. The outcomes of this research offer valuable insights for controlling displacement and analyzing damage in ballastless railway systems subjected to compression.

A GIS-based Study of The Impact of HSR Network Distribution on Firms' Total Factor Productivity: Evidence from Listed Manufacturing Firms in China

With the rapid development of the economy, enterprises are increasingly pursuing efficient division of labor and communication, and in order to achieve high-quality economic growth and sustainable development, high speed rail (HSR) has been born. Therefore, the study of the impact of HSR accessibility on the total factor productivity (TFP) of enterprises has become a hot topic of research in today's academia. In this paper, firstly, based on GIS network analysis, the routes and stations after opening are matched with the locations of enterprises to describe the spatial correlation between HSR and the locations of enterprises as well as the distribution of HSR among enterprises; secondly, a multi-period difference-in-difference model (DID) is utilized to study the impact of HSR opening on TFP of enterprises on the basis of the data of China's listed manufacturing enterprises in the period of 2000-2017; and The PSM-DID model to test the robustness of the empirical results; finally, the path of the impact of HSR on the TFP is explored. The empirical results are as follows: (1) The distribution of HSR and the location of listed enterprises are highly correlated in terms of geographic distribution information; (2) HSR has a significant impact on the TFP, and the impact effect is different in different periods; (3) HSR mainly affects the TFP of enterprises by using the innovative behavior of enterprises and industrial agglomeration as the mediating variables.

A Georeferenced Dataset for Mapping and Assessing Subgrade Defects in China’s High-Speed Railways

China has the world’s longest high-speed rail (HSR) network, marked by dense transportation and complex operations. However, frequent train use coupled with extreme weather conditions has led to rising subgrade issues. Existing railway defect records suffer from inconsistency, hindering direct applicability. Currently, there is a lack of a relevant dataset dedicated to HSR subgrade defects. To bridge this gap, we developed a comprehensive georeferenced dataset that encompasses defect records extracted from peer-reviewed literature published between 1999 and 2023 in China. Rigorous quality control procedures were implemented to eliminate duplicate data and ensure the accuracy of the dataset. The dataset consists of georeferenced records for eight different defects, spanning across 661 locations and categorized at various scales, ranging from provinces to townships. The most commonly reported defect types include subgrade settlement, frost damage, uplift deformation, and mud pumping. This dataset provides a comprehensive map of historical subgrade defects affecting high-speed railways in China. It could facilitate operational risk assessments and the prediction of subgrade performance.

Semantic Segmentation of Remote Sensing Images Depicting Environmental Hazards in High-Speed Rail Network Based on Large-Model Pre-Classification.

With the rapid development of China's railways, ensuring the safety of the operating environment of high-speed railways faces daunting challenges. In response to safety hazards posed by light and heavy floating objects during the operation of trains, we propose a dual-branch semantic segmentation network with the fusion of large models (SAMUnet). The encoder part of this network uses a dual-branch structure, in which the backbone branch uses a residual network for feature extraction and the large-model branch leverages the results of feature extraction generated by the segment anything model (SAM). Moreover, a decoding attention module is fused with the results of prediction of the SAM in the decoder part to enhance the performance of the network. We conducted experiments on the Inria Aerial Image Labeling (IAIL), Massachusetts, and high-speed railway hazards datasets to verify the effectiveness and applicability of the proposed SAMUnet network in comparison with commonly used semantic segmentation networks. The results demonstrated its superiority in terms of both the accuracies of segmentation and feature extraction. It was able to precisely extract hazards in the environment of high-speed railways to significantly improve the accuracy of semantic segmentation.

High-speed rail operations, the cross-regional mobility of highly skilled talent, and regional innovation—evidence from the Yangtze River delta in China

ABSTRACT The correlation between high-speed rail (HSR) and regional innovation is vital for studying the economic impacts of HSR. Using 2003–2018 panel data on prefecture-level cities in China’s Yangtze River Delta (YRD), this paper investigates the impact of HSR on regional innovation using a multiperiod difference-in-differences (DID) model. HSR operations have a significant positive impact on urban innovation, as supported by robustness tests. Heterogeneity analysis reveals a threshold effect of cognitive capital on the promoting effect of HSR on regional innovation that is maximized when cognitive capital capacity falls within the range of 0.1254 to 0.1876. Mechanism analysis suggests that HSR construction facilitates the cross-regional mobility of highly skilled individuals. This expanded movement increases innovation within cities due to the resulting knowledge spillovers. Moreover, HSR operations and civil aviation, as well as internet communication tools, play a significant complementary role in promoting regional innovation. This study deepens the understanding of the impact of HSR operations on regional innovation from the perspective of the interregional mobility of highly skilled people. Furthermore, ArcGIS is used to construct the ‘least cost path’ of the HSR network, providing a new approach to addressing the endogeneity of HSR station locations.

Agent-based modelling of high-speed railway interdependent critical infrastructures facing physical and cyber threats

Globally, high-speed rail systems serve nearly 2 billion passenger-km daily. By virtue, they are a critical infrastructure like telecommunication and power networks. Accordingly, they become a catalyst for societal and economic growth stemming from the mobility business. The highspeed rail operations are very complex and interdependent, owing to the escalated demands for long-distance interconnected transportation. In recent years, there have been unreasonable delays for passengers as a new norm due to unfortunate train cancellations and relaxation of mobility performance requirements. Therefore, accurate measurements, monitoring and prediction of disruptive impacts and service performance metrices are indispensable. Within the scope of high-speed rail services, this paper examines how agent-based and multi-agent-based models are utilized to address such the challenges. Our findings reveal that the current use of agents or multi-agent models has some limitations for practical applications. Previous studies showed that mathematical methods to assess the resilience of critical infrastructures, railway scheduling, and vehicle dispatching can yield more satisfactory outcomes, although the approaches can be relatively time-consuming. In contrast, agent-based and multi-agent-based models can shorten processing time and uncover disruptive events more promptly. The paper thus showcases several emerging concepts, including i) the utilization of big data for crisis management, ii) interconnectivity analysis of high-speed rail infrastructures, and iii) enhancement of transport resilience. In addition, our findings identify the most influential agents and their possible applications to enhance systems resilience of highspeed rail networks when dealing with unforeseen physical and cyber threats.