arXiv subjects

Ziyou Gao

Publications and source records attributed to Ziyou Gao.

At least 19 recordsLinked to original sources

arXiv2026

As Cities Grow, They Spread Out Rather Than Rise

Cities and settlements are a global phenomenon, and their continued expansion is fundamentally transforming patterns of resource demand. This transformation is reflected in growing pressures on land, material use, and infrastructure. Thus, understanding how cities grow in space is essential for planning future urban development and determining all its consequences. Here, we characterize four geometrically related dimensions of urban growth: two horizontal dimensions describing the urban area, one vertical dimension represented by average building height, which together with the urban area defines building volume, and the population dimension. Analyzing a global dataset of growing cities, for the period 1975-2025 we identify three main patterns. First, urban growth is fundamentally anisotropic -- as cities gain population, they expand much more rapidly in the horizontal than in the vertical direction. Second, average building height decreases in the vast majority of cities as they grow, indicating that vertical development is not only slower than horizontal expansion but on average, can act in an effectively negative manner by giving greater weight to the horizontal dimensions. Third, despite their diverse growth trajectories, cities converge toward characteristic population densities, both with respect to urban area and building volume. We further explore alternative scenarios for future urban growth. These projections show that different assumptions about horizontal and vertical scaling can lead to substantially different demands for urban land and building volume. These findings reveal constraints on the long-term evolution of urban form and provide a quantitative assessment for understanding the spatial dynamics and development of cities.

physics.soc-ph↗

arXiv2026

Self-similarity of mobility networks

Mobility systems of people and goods are inherently multi-scale, spanning levels of organization from individual cities to regions and nations. Understanding whether mobility networks exhibit similar patterns across these scales is important. Such similarity would point to common organizing principles, enabling insights gained at one scale to inform planning and management at others. Despite growing efforts to analyze mobility at multiple scales, such cross-scale similarity remains poorly understood, and renormalization provides a natural framework for addressing this question. Here, we propose a Neighbor-Limited Box Covering method to renormalize undirected weighted mobility networks. This method iteratively selects box centers in descending order of node strength, merges each center with a fixed number of its highest-weight neighbors to form a renormalized node, and aggregates edge weights between renormalized nodes to generate the network at the next scale. We apply this technique to uncover multi-scale structures of real-world inter-city human mobility and freight trip networks in China and find that the topological structures, weighted structural features, and dynamic processes all exhibit self-similarity across these multi-scale mobility networks. Moreover, we find that the constituent nodes in most renormalized nodes show a strong spatial cohesion, and the boundaries of them closely follow existing political and socio-economic borders, even though the method does not explicitly incorporate any spatial information. Our study not only reveals the consistency of multi-scale inter-city mobility patterns, but also provides important insights into their spatial organization. Furthermore, our method is applicable to mobility networks of different sizes and has potential as a powerful tool for the multi-scale analysis of various other real-world complex systems.

physics.soc-ph↗

arXiv2025

Modeling the residual queue and queue-dependent capacity in a static traffic assignment problem

The residual queue during a given study period (e.g., peak hour) is an important feature that should be considered when solving a traffic assignment problem under equilibrium for strategic traffic planning. Although studies have focused extensively on static or quasi-dynamic traffic assignment models considering the residual queue, they have failed to capture the situation wherein the equilibrium link flow passing through the link is less than the link physical capacity under congested conditions. To address this critical issue, we introduce a novel static traffic assignment model that explicitly incorporates the residual queue and queue-dependent link capacity. The proposed model ensures that equilibrium link flows remain within the physical capacity bounds, yielding estimations more aligned with data observed by traffic detectors, especially in oversaturated scenarios. A generalized link cost function considering queue-dependent capacity, with an additional queuing delay term is proposed. The queuing delay term represents the added travel cost under congestion, offering a framework wherein conventional static models, both with and without physical capacity constraints, become special cases of our model. Our study rigorously analyzes the mathematical properties of the new model, establishing the theoretical uniqueness of solutions for link flow and residual queue under certain conditions. We also introduce a gradient projection-based alternating minimization algorithm tailored for the proposed model. Numerical examples are conducted to demonstrate the superiority and merit of the proposed model and solution algorithm.

eess.SY↗

arXiv2024

Hidden high-risky states identification from routine urban traffic

One of the core risk management tasks is to identify hidden high-risky states that may lead to system breakdown, which can provide valuable early warning knowledge. However, due to high dimensionality and nonlinear interaction embedded in large-scale complex systems like urban traffic, it remains challenging to identify hidden high-risky states from huge system state space where over 99% of possible system states are not yet visited in empirical data. Based on maximum entropy model, we infer the underlying interaction network from complicated dynamical processes of urban traffic, and construct system energy landscape. In this way, we can locate hidden high-risky states that have never been observed from real data. These states can serve as risk signals with high probability of entering hazardous minima in energy landscape, which lead to huge recovery cost. Our finding might provide insights for complex system risk management.

physics.soc-ph↗

arXiv2023

STG-GAN: A spatiotemporal graph generative adversarial networks for short-term passenger flow prediction in urban rail transit systems

Short-term passenger flow prediction is an important but challenging task for better managing urban rail transit (URT) systems. Some emerging deep learning models provide good insights to improve short-term prediction accuracy. However, there exist many complex spatiotemporal dependencies in URT systems. Most previous methods only consider the absolute error between ground truth and predictions as the optimization objective, which fails to account for spatial and temporal constraints on the predictions. Furthermore, a large number of existing prediction models introduce complex neural network layers to improve accuracy while ignoring their training efficiency and memory occupancy, decreasing the chances to be applied to the real world. To overcome these limitations, we propose a novel deep learning-based spatiotemporal graph generative adversarial network (STG-GAN) model with higher prediction accuracy, higher efficiency, and lower memory occupancy to predict short-term passenger flows of the URT network. Our model consists of two major parts, which are optimized in an adversarial learning manner: (1) a generator network including gated temporal conventional networks (TCN) and weight sharing graph convolution networks (GCN) to capture structural spatiotemporal dependencies and generate predictions with a relatively small computational burden; (2) a discriminator network including a spatial discriminator and a temporal discriminator to enhance the spatial and temporal constraints of the predictions. The STG-GAN is evaluated on two large-scale real-world datasets from Beijing Subway. A comparison with those of several state-of-the-art models illustrates its superiority and robustness. This study can provide critical experience in conducting short-term passenger flow predictions, especially from the perspective of real-world applications.

cs.LG↗

arXiv2023

Spatial-Temporal Attention Fusion Network for short-term passenger flow prediction on holidays in urban rail transit systems

The short term passenger flow prediction of the urban rail transit system is of great significance for traffic operation and management. The emerging deep learning-based models provide effective methods to improve prediction accuracy. However, most of the existing models mainly predict the passenger flow on general weekdays or weekends. There are only few studies focusing on predicting the passenger flow on holidays, which is a significantly challenging task for traffic management because of its suddenness and irregularity. To this end, we propose a deep learning-based model named Spatial Temporal Attention Fusion Network comprising a novel Multi-Graph Attention Network, a Conv-Attention Block, and Feature Fusion Block for short-term passenger flow prediction on holidays. The multi-graph attention network is applied to extract the complex spatial dependencies of passenger flow dynamically and the conv-attention block is applied to extract the temporal dependencies of passenger flow from global and local perspectives. Moreover, in addition to the historical passenger flow data, the social media data, which has been proven that they can effectively reflect the evolution trend of passenger flow under events, are also fused into the feature fusion block of STAFN. The STAFN is tested on two large-scale urban rail transit AFC datasets from China on the New Year holiday, and the prediction performance of the model are compared with that of several conventional prediction models. Results demonstrate its better robustness and advantages among benchmark methods, which can provide overwhelming support for practical applications of short term passenger flow prediction on holidays.

cs.LG↗

arXiv2023

ST-former for short-term passenger flow prediction during COVID-19 in urban rail transit system

Accurate passenger flow prediction of urban rail transit is essential for improving the performance of intelligent transportation systems, especially during the epidemic. How to dynamically model the complex spatiotemporal dependencies of passenger flow is the main issue in achieving accurate passenger flow prediction during the epidemic. To solve this issue, this paper proposes a brand-new transformer-based architecture called STformer under the encoder-decoder framework specifically for COVID-19. Concretely, we develop a modified self-attention mechanism named Causal-Convolution ProbSparse Self-Attention (CPSA) to model the multiple temporal dependencies of passenger flow with low computational costs. To capture the complex and dynamic spatial dependencies, we introduce a novel Adaptive Multi-Graph Convolution Network (AMGCN) by leveraging multiple graphs in a self-adaptive manner. Additionally, the Multi-source Data Fusion block fuses the passenger flow data, COVID-19 confirmed case data, and the relevant social media data to study the impact of COVID-19 to passenger flow. Experiments on real-world passenger flow datasets demonstrate the superiority of ST-former over the other eleven state-of-the-art methods. Several ablation studies are carried out to verify the effectiveness and reliability of our model structure. Results can provide critical insights for the operation of URT systems.

cs.LG↗

arXiv2022

Integrated optimization of train timetables rescheduling and response vehicles on a disrupted metro line

When an unexpected metro disruption occurs, metro managers need to reschedule timetables to avoid trains going into the disruption area, and transport passengers stranded at disruption stations as quickly as possible. This paper proposes a two-stage optimization model to jointly make decisions for two tasks. In the first stage, the timetable rescheduling problem with cancellation and short-turning strategies is formulated as a mixed integer linear programming (MILP). In particular, the instantaneous parameters and variables are used to describe the accumulation of time-varying passenger flow. In the second one, a system-optimal dynamic traffic assignment (SODTA) model is employed to dynamically schedule response vehicles, which is able to capture the dynamic traffic and congestion. Numerical cases of Beijing Metro Line 9 verify the efficiency and effectiveness of our proposed model, and results show that: (1) when occurring a disruption event during peak hours, the impact on the normal timetable is greater, and passengers in the direction with fewer train services are more affected; (2) if passengers stranded at the terminal stations of disruption area are not transported in time, they will rapidly increase at a speed of more than 300 passengers per minute; (3) compared with the fixed shortest path, using the response vehicles reduces the total travel time about 7%. However, it results in increased travel time for some passengers.

eess.SY↗

arXiv2022

Structure and evolution of urban heavy truck mobility networks

Revealing the structural properties and understanding the evolutionary mechanisms of the urban heavy truck mobility network (UHTMN) provide insights in assessment of freight policies to manage and regulate the urban freight system, and are of vital importance for improving the livability and sustainability of cities. Although massive urban heavy truck mobility data become available in recent years, in-depth studies on the structure and evolution of UHTMN are still lacking. Here we use massive urban heavy truck GPS data in China to construct the UHTMN and reveal its a wide range of structure properties. We further develop an evolving network model that simultaneously considers weight, space and system element duplication. Our model reproduces the observed structure properties of UHTMN and helps us understand its underlying evolutionary mechanisms. Our model also provides new perspectives for modeling the evolution of many other real-world networks, such as protein interaction networks, citation networks and air transportation networks.

physics.soc-ph↗

arXiv2022

Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method

With the prevailing of mobility as a service (MaaS), it becomes increasingly important to manage multi-traffic modes simultaneously and cooperatively. As an important component of MaaS, short-term passenger flow prediction for multi-traffic modes has thus been brought into focus. It is a challenging problem because the spatiotemporal features of multi-traffic modes are critically complex. Moreover, the passenger flows of multi-traffic modes differentiate and fluctuate significantly. To solve these problems, this paper proposes a multitask learning-based model, called Res-Transformer, for short-term inflow prediction of multi-traffic modes (subway, taxi, and bus). Each traffic mode is treated as a single task in the model. The Res-Transformer consists of two parts: (1) several modified Transformer layers comprising the conv-Transformer layer and the multi-head attention mechanism, which helps to extract the spatial and temporal features of multi-traffic modes, (2) the structure of residual network is utilized to obtain the correlations of different traffic modes and prevent gradient vanishing, gradient explosion, and overfitting. The Res-Transformer model is evaluated on two large-scale real-world datasets from Beijing, China. One is the region of a traffic hub and the other is the region of a residential area. Experiments are conducted to compare the performance of the proposed model with several baseline models. Results prove the effectiveness and robustness of the proposed method. This paper can give critical insights into the short-term inflow prediction for multi-traffic modes.

cs.LG↗

arXiv2022

Oscillation growth in mixed traffic flow of human driven vehicles and automated vehicles: Experimental study and simulation

This paper reports an experimental study on oscillation growth in mixed traffic flow of automated vehicles (AVs) and human driven vehicles (HVs). The leading vehicle moves with constant speed in the experiment. The following vehicles consist of six developable AVs and different number of HVs. Thus, the market penetration rate (MPR) of AVs decreases with the increase of platoon size. The AVs are homogeneously distributed in the platoon. The constant time gap car-following policy is adopted for the AVs and the gap is set to 1.5 s. The experiment shows that in the 7-vehicle-platoon, the oscillations grow only slightly. In the 10-vehicle-platoon, the AVs could still significantly suppress the growth of oscillations. With the further decrease of MPR of AVs in the 13- and 20-vehicle-platoon, the AVs become having no significant impact on oscillation growth. On the other hand, with the decrease of MPR of AVs, average density of the vehicles and flow rate of the platoon increase, which demonstrates a trade-off between traffic stability and throughput under the given setup of AVs. The simulation study is also carried out, which exhibits good agreement with the experiment. Finally, sensitivity analysis of the parameters in the AV upper-level control algorithm has been performed, which is expected to guide future experiment design.

physics.soc-ph↗

arXiv2022

An end-to-end predict-then-optimize clustering method for intelligent assignment problems in express systems

Express systems play important roles in modern major cities. Couriers serving for the express system pick up packages in certain areas of interest (AOI) during a specific time. However, future pick-up requests vary significantly with time. While the assignment results are generally static without changing with time. Using the historical pick-up request number to conduct AOI assignment (or pick-up request assignment) for couriers is thus unreasonable. Moreover, even we can first predict future pick-up requests and then use the prediction results to conduct the assignments, this kind of two-stage method is also impractical and trivial, and exists some drawbacks, such as the best prediction results might not ensure the best clustering results. To solve these problems, we put forward an intelligent end-to-end predict-then-optimize clustering method to simultaneously predict the future pick-up requests of AOIs and assign AOIs to couriers by clustering. At first, we propose a deep learning-based prediction model to predict order numbers on AOIs. Then a differential constrained K-means clustering method is introduced to cluster AOIs based on the prediction results. We finally propose a one-stage end-to-end predict-then-optimize clustering method to assign AOIs to couriers reasonably, dynamically, and intelligently. Results show that this kind of one-stage predict-then-optimize method is beneficial to improve the performance of optimization results, namely the clustering results. This study can provide critical experiences for predict-and-optimize related tasks and intelligent assignment problems in express systems.

cs.LG↗

arXiv2021

Scaling of variations in traveling distances and times of taxi routes

The importance of understanding human mobility patterns has led many studies to examine their spatial-temporal scaling laws. These studies mainly reveal that human travel can be highly non-homogeneous with power-law scaling distributions of distances and times. However, investigating and quantifying the extent of variability in time and space when traveling the same air distance has not been addressed so far. Using taxi data from five large cities, we focus on several novel measures of distance and time to explore the spatio-temporal variations of taxi travel routes relative to their typical routes during peak and nonpeak periods. To compare all trips using a single measure, we calculate the distributions of the ratios between actual travel distances and the average travel distance as well as between actual travel times and the average travel time for all origin destinations (OD) during peak and nonpeak periods. In this way, we measure the scaling of the distribution of all single trip paths with respect to their mean trip path. Our results surprisingly demonstrate very broad distributions for both the distance ratio and time ratio, characterized by a long-tail power-law distribution. Moreover, all analyzed cities have larger exponents in peak hours than in nonpeak hours. We suggest that the interesting results of shorter trip lengths and times, characterized by larger exponents during rush hours, are due to the higher availability of travelers in rush hours compared to non-rush hours...

physics.soc-ph↗

arXiv2021

Network-wide link travel time and station waiting time estimation using automatic fare collection data: A computational graph approach

Urban rail transit (URT) system plays a dominating role in many megacities like Beijing and Hong Kong. Due to its important role and complex nature, it is always in great need for public agencies to better understand the performance of the URT system. This paper focuses on an essential and hard problem to estimate the network-wide link travel time and station waiting time using the automatic fare collection (AFC) data in the URT system, which is beneficial to better understand the system-wide real-time operation state. The emerging data-driven techniques, such as computational graph (CG) models in the machine learning field, provide a new solution for solving this problem. In this study, we first formulate a data-driven estimation optimization framework to estimate the link travel time and station waiting time. Then, we cast the estimation optimization model into a CG framework to solve the optimization problem and obtain the estimation results. The methodology is verified on a synthetic URT network and applied to a real-world URT network using the synthetic and real-world AFC data, respectively. Results show the robustness and effectiveness of the CG-based framework. To the best of our knowledge, this is the first time that the CG is applied to the URT. This study can provide critical insights to better understand the operational state in URT.

cs.LG↗

arXiv2021

Identifying intercity freight trip ends of heavy trucks from GPS data

The intercity freight trips of heavy trucks are important data for transportation system planning and urban agglomeration management. In recent decades, the extraction of freight trips from GPS data has gradually become the main alternative to traditional surveys. Identifying the trip ends (origin and destination, OD) is the first task in trip extraction. In previous trip end identification methods, some key parameters, such as speed and time thresholds, have mostly been defined on the basis of empirical knowledge, which inevitably lacks universality. Here, we propose a data-driven trip end identification method. First, we define a speed threshold by analyzing the speed distribution of heavy trucks and identify all truck stops from raw GPS data. Second, we define minimum and maximum time thresholds by analyzing the distribution of the dwell times of heavy trucks at stop location and classify truck stops into three types based on these time thresholds. Third, we use highway network GIS data and freight-related points-of-interest (POIs) data to identify valid trip ends from among the three types of truck stops. In this step, we detect POI boundaries to determine whether a heavy truck is stopping at a freight-related location. We further analyze the spatiotemporal characteristics of intercity freight trips of heavy trucks and discuss their potential applications in practice.

stat.AP↗

arXiv2021

Identifying intracity freight trip ends from heavy truck GPS trajectories

Intracity heavy truck freight trips are basic data in city freight system planning and management. In the big data era, massive heavy truck GPS trajectories can be acquired cost effectively in real-time. Identifying freight trip ends (origins and destinations) from heavy truck GPS trajectories is an outstanding problem. Although previous studies proposed a variety of trip end identification methods from different perspectives, these studies subjectively defined key threshold parameters and ignored the complex intracity heavy truck travel characteristics. Here, we propose a data-driven trip end identification method in which the speed threshold for identifying truck stops and the multilevel time thresholds for distinguishing temporary stops and freight trip ends are objectively defined. Moreover, an appropriate time threshold level is dynamically selected by considering the intracity activity patterns of heavy trucks. Furthermore, we use urban road networks and point-of-interest (POI) data to eliminate misidentified trip ends to improve method accuracy. The validation results show that the accuracy of the method we propose is 87.45%. Our method incorporates the impact of the city freight context on truck trajectory characteristics, and its results can reflect the spatial distribution and chain patterns of intracity heavy truck freight trips, which have a wide range of practical applications.

cs.OH↗

arXiv2020

A comparison study on the growth pattern of traffic oscillations in car-following experiments

The evolution of oscillations is a very important issue in traffic flow studies. A recent car-following experiment (Experiment-I) showed that the speed standard deviation grows in a concave way along a platoon of vehicles following one another. This finding indicates that the traditional traffic instability mechanism is debatable, in which the speed standard deviation initially grows in a convex way. This paper has investigated the growth pattern of traffic oscillations in another car-following experiment (Experiment-II) and compared it with that in Experiment-I. It is shown that the speed standard deviation also exhibits concave growth characteristics in Experiment-II. The paired-sample t-test and the Mann-Kendall (MK) trend test showed that there is no significant difference between the two datasets. However, the acceleration standard deviation was remarkably larger in Experiment-II since drivers were asked to follow closely. Furthermore, a comparison experiment has been performed which indicates that the set of experiments on a circular track can be considered equivalent to that on a straight track. Our study is expected to shed light not only on traffic flow dynamics itself but also on the future design of the experiment scheme.

physics.soc-ph↗

arXiv2020

Study on departure time choice behavior in commute problem with stochastic bottleneck capacity: Experiments and modeling

Uncertainty is inevitable in transportation system due to the stochastic change of demand and supply. It is one of the most important factors affecting travelers' choice behavior. Based on the framework of Vickrey's bottleneck model, we designed and conducted laboratory experiment to investigate the effects of stochastic bottleneck capacity on commuter departure time choice behavior. Two different scenarios with different information feedback are investigated. The experimental results show that the relationship between the mean cost (E(C)) and the standard deviation of cost (σ) can all be fitted approximately linearly with a positive slope σ=E(C)/λ^*-m (λ^*>0). This suggests that under the uncertain environment, travelers are likely to minimize their travel cost budget, defined as E(C)-λ^* σ, and λ^*>0 indicates that the travelers behave risk preferring. The experiments also found that providing the cost information of all departure times to the commuters lowered the commuters' risk preference coefficient (i.e., λ^* decreases). We propose a reinforcement learning model, which is shown to reproduce the main experimental findings well.

physics.soc-ph↗