Origin-destination Pairs Research Articles

Evaluating Google Maps’ Eco-Routes: A Metaheuristic-Driven Microsimulation Approach

Eco-routing, as a key strategy for mitigating urban pollution, is gaining prominence due to the fact that minimizing travel time alone does not necessarily result in the lowest fuel consumption. This research focuses on the challenge of selecting environmentally friendly routes within an urban street network. Employing microsimulation modelling and a computer-generated mirror of a small traffic network, the study integrates real-world traffic patterns to enhance accuracy. The route selection process is informed by fuel consumption and emissions data from trajectory parameters obtained during simulation, utilizing the Comprehensive Modal Emission Model (CMEM) for emission estimation. A comprehensive analysis of specific origin–destination pairs was conducted to assess the methodology, with all vehicles adhering to routes recommended by Google Maps. The findings reveal a noteworthy disparity between microsimulation results and Google Maps recommendations for eco-friendly routes within the University of Pittsburgh Campus street network. This incongruence underscores the necessity for further investigations to validate the accuracy of Google Maps’ eco-route suggestions in urban settings. As urban areas increasingly grapple with pollution challenges, such research becomes pivotal for refining and optimizing eco-routing strategies to effectively contribute to sustainable urban mobility.

A Study on Maximizing Traffic Reachability in Contingency Scenarios Based on Genetic Algorithms

This paper presents a study on maximizing traffic demand accessibility in transportation networks under contingency scenarios using genetic algorithms. Transportation demand accessibility is defined as the proportion of allocated traffic that can reach its destination, considering potential disruptions in the network. The study begins by formulating a model for calculating transportation demand accessibility between different origin-destination pairs, taking into account the possibility of unforeseen events on any road segment. By applying genetic algorithms, the study aims to optimize the allocation of traffic flows in a way that maximizes the expected reachability across the network, even when multiple road sections experience contingencies. Several scenarios are considered, including the introduction of capacity constraints on road segments and varying traffic demands. The results demonstrate that the proposed method can effectively optimize traffic flow allocation, enhancing the robustness and efficiency of transportation networks under uncertain conditions. This research provides valuable insights for urban planners and traffic managers seeking to improve network resilience in the face of unexpected disruptions.

Estimation of Arterial Path Flow Considering Flow Distribution Consistency: A Data-Driven Semi-Supervised Method

To implement fine-grained progression signal control on arterial, it is essential to have access to the time-varying distribution of the origin–destination (OD) flow of the arterial. However, due to the sparsity of automatic vehicle identification (AVI) devices and the low penetration of connected vehicles (CVs), it is difficult to directly obtain the distribution pattern of arterial OD flow (i.e., path flow). To solve this problem, this paper develops a semi-supervised arterial path flow estimation method considering the consistency of path flow distribution by combining the sparse AVI data and the low permeability CV data. Firstly, this paper proposes a semi-supervised arterial path flow estimation model based on multi-knowledge graphs. It utilizes graph neural networks to combine some arterial AVI OD flow observation information with CV trajectory information to infer the path flow of AVI unobserved OD pairs. Further, to ensure that the estimation results of the multi-knowledge graph path flow estimation model are consistent with the distribution of path flow in real situations, we introduce a generative adversarial network (GAN) architecture to correct the estimation results. The proposed model is extensively tested based on a real signalized arterial. The results show that the proposed model is still able to achieve reliable estimation results under low connected vehicle penetration and with less observed label data.

Distributed Methodology for a Cell-Transmission-Based System Optimal Dynamic Traffic Assignment

This study introduces a distributed methodology for system optimal dynamic traffic assignment formulated using the cell transmission model (CTM). Using CTM increases the methodology’s accuracy in predicting link flows and its dynamics; however, it increases the computational complexity significantly. Our methodology is specifically designed to address this challenge and provide a balance between the quality of the solution and computational complexity while ensuring first-in-first-out (FIFO) queuing discipline. The methodology follows a receding horizon framework and distributes the network-level traffic assignment into several intersection-level sub-problems and solves them in parallel. Therefore, this heuristic significantly reduces the computational complexity and finds solutions in real-time. The distribution is achieved by relaxing coupling constraints among different sub-problems. The sub-problems coordinate their decisions with each other by sharing information and implementing it in the re-introduced constraints that were previously relaxed. This process was used to avoid infeasible solutions, reduce the likelihood of finding local solutions, and promote system-level optimality. The information that needs to be exchanged is estimated using CTM simulation runs. All optimal sub-problem solutions are implemented in network-level CTM simulations, and cell occupancies and flows are obtained. The FIFO discipline is also approximated in CTM. We have tested the methodology in networks of 20 and 40 intersections with 15 and 25 origin-destination pairs, respectively, under various demand levels, and compared the performance with a benchmark approach capable of finding the optimal solutions. The maximum observed optimality gap in case studies with 20 and 40 intersections was 3.1%, and the solutions were found in real-time in all scenarios.

EXplainable DEA approach for evaluating performance of public transport origin-destination pairs

Understanding public transportation efficiency is crucial to enhancing urban mobility and economic growth. This study aims to evaluate the efficiency of the public transportation system using an explainable data envelopment analysis approach. Specifically, data envelopment analysis and explainable artificial intelligence techniques were incorporated to uncover the black-box relationship between the inputs and outputs of the efficiency score. The efficiency of the public transportation system was defined as travel times for subway, bus, and multimodal modes relative to the number of trips and travel distances. The efficiency score was evaluated by the origin-destination pair unit. As a result, the efficiency score was estimated to be 0.69 on average, indicating that a reduction of 31% in travel times is required to achieve a perfect score of 1.00. Among the 33,313 origin-destination pairs, 39 had a perfect score of 1.00. The results of the interpretation model showed the order of importance for features—buses, subways, and multimodal modes—with SHapley Additive Explanations values of 0.047, 0.029, and 0.022, respectively. These results suggest that focusing primarily on reducing bus travel times is effective for improving overall efficiency. In this manner, the explainable data envelopment analysis helps measure performance, understand results, and suggest improvement directions.

Optimized demand-based charging networks for long-haul trucking in Europe

Abstract Battery electric trucks (BETs) are the most promising option for fast and large-scale CO2 emission reduction in road freight transport. Yet, the limited range and longer charging times compared to diesel trucks make long-haul BET applications challenging, so a comprehensive fast charging network for BETs is required. However, little is known about optimal truck charging locations for long-haul trucking in Europe. Here we derive optimized truck charging networks consisting of publicly accessible locations across the continent. Based on European truck traffic flow estimates for 2030 and actual truck stop locations we construct a long-term charging network that minimizes the total number of required locations. Our approach introduces an origin-destination (OD) pair sampling method and includes local capacity constraints to compute an optimized stepwise network expansion along the highest demand routes in Europe. For an electrification target of 15% BET share in long-haul and without depot charging, our results suggest that about 91% of electric long-haul truck traffic across Europe can be enabled already with a network of 1,000 locations, while 500 locations would suffice for about 50%. We furthermore show how the coverage of OD flows scales with the number of locations and the size of the stations. Ideal locations to cover many truck trips are at highway intersections and along major European road freight corridors (TEN-T core network).

Additional Taxi-Out Time Prediction for Flights at Busy Airports by Fusing Flow Control Information

The taxi-out time of an airport scene can be categorized into the unimpeded taxi-out time and the additional taxi-out time. Usually, additional taxi-out time is used as a key index to monitor taxi-out performance, and its accurate prediction plays an important role in optimizing the allocation of time slots at an airport and improving scene operation efficiency. Taking Shanghai Pudong International Airport as the research object, we first analyze its layout and construct the origin–destination pairs (ODPs) based on the stand groups and runways. Then, we develop a multiple linear regression model based on the arrival and departure flows to calculate the unimpeded taxi-out times for all ODPs. The actual taxi-out time is then subtracted from the unimpeded taxi-out time to obtain the historical additional taxi-out time of each flight. We propose three new flow features related to the structure: the corridor departure flow, the corridor arrival flow, and the departure flow proportion of ODPs, based on which we construct a dataset for training the prediction model. We then propose an additional taxi-out time prediction model based on the nutcracker optimization algorithm (NOA) and XGBoost and run comparison experiments on the operation data of our target airport. The results show that the optimized prediction model we proposed has the best performance compared with the traditional XGBoost model and other commonly used prediction models, and the proposed structure-related features have high correlations with additional taxi-out time.

Understanding the interplay among urban public transport modes: Spatial variation and built environment effects

Research on public transport systems is continually driven by the societal benefits of transport services. However, the nuanced effects of the built environment on public transport mode shares across different modes have received little attention. Using multi-source travel data from Shenzhen, this study presents an analytical framework, which integrates the light gradient boosting machine and Shapley additive explanations, to delve into the complex interplay among public transport modes. The results reveal that most origin-destination pairs with available metro services exhibit a metro share exceeding 50%, underscoring the high attractiveness of the metro. Travel distance emerges as the primary determinant of mode share, with transport-related characteristics proving more influential than land use modifications. This study identifies nonlinear effects of the built environment on mode share, with specific thresholds for built environment characteristics suggesting fine-tuned planning strategies. Metro station densities of 2 counts/km2 correlates with increased metro share, while bus stop densities of 15 counts/km2 are associated with higher bus share. Areas within 2 km of a metro station or with bus stop densities below 15 counts/km2 tend to have higher bike shares. Specific land use ratios and high levels of land use mix are linked to increased shares of certain modes. The findings suggest optimizing bus services in relation to metro availability and offer guidance for balanced planning in promoting metro and shared mobility to achieve a sustainable transport system.

Short-Term Prediction of Origin–Destination Passenger Flow in Urban Rail Transit Systems with Multi-Source Data: A Deep Learning Method Fusing High-Dimensional Features

Short-term origin–destination (OD) passenger flow forecasting is crucial for urban rail transit enterprises aiming to optimise transportation products and increase operating income. As there are large-scale OD pairs in an urban rail transit system, OD passenger flow cannot be obtained in real time (temporal hysteresis). Additionally, the distribution characteristics are also complex. Previous studies mainly focus on passenger flow prediction at metro stations, while few methods solve the OD passenger flow prediction problems of an urban rail transit system. In view of this, we propose a novel deep learning method fusing high-dimensional features (HDF-DL) with multi-source data. The HDF-DL method is combined with three modules. The temporal module incorporates the time-varying, trend, and cyclic characteristics of OD passenger flow, while the latest OD passenger flow time sequence (within 1 h) is excluded from the time-varying characteristics. In the spatial module, the K-means and K-shape algorithms are used to classify OD pairs from multiple perspectives and capture the spatial features, reducing the difficulty of OD passenger flow predictions with large-scale and complex characteristics. Weather factors are considered in the external feature module. The HDF-DL method is tested on a large-scale metro system in China, in which eight baseline models are designed. The results show that the HDF-DL method achieves high prediction accuracy across multiple time granularities, with a mean absolute percentage error of about 10%. OD passenger flow in every departure time interval can be predicted with high and stable accuracy, effectively capturing temporal characteristics. The modular design of HDF-DL, which fuses high-dimensional features and employs appropriate neural networks for different data types, significantly reduces prediction errors and outperforms baseline models.

Student mobility in Southern Italy: An empirical analysis of preferential patterns

This paper presents an empirical analysis aimed at identifying chain migration patterns among university students from Sicily, Sardinia, and Apulia. Utilizing data from the national archive of university students enrolled in an Italian university from 2008 to 2017, we construct origin–destination matrixes and calculate residuals from a log-linear model to detect key student routes. Positive residuals between specific origin–destination pairs that persist over time can suggest significant attraction and potential chain migration. The results support a “large to large” and “small to small” city mobility model, particularly for Sicily and Sardinia. Students from Palermo, Catania, Messina, and Cagliari show strong connections with large cities such as Rome and Milan. Furthermore, results show historical links between Sardinia and Tuscany date back to the 1950s, and the enduring connections between Apulian students and universities in Emilia-Romagna, Veneto, and Lombardy have been evident since the 1970s. In Sicily, mobility patterns towards the Polytechnic of Turin began in the 1970s and persist today. These patterns underscore the influence of prior migrants on the mobility decisions of university students in Southern Italy, highlighting a potential chain migration effect.

Travel Time Variability in Urban Mobility: Exploring Transportation System Reliability Performance Using Ridesharing Data

Travel time variability (TTV) is a crucial indicator of transportation network performance, assessing travel time reliability and delays. This study investigates TTV metrics within the context of shared mobility using probe data from transportation network companies (TNCs) in Chicago, Los Angeles, and Dallas–Fort Worth. Eight reliability metrics are analyzed and compared for each origin–destination (OD) pair in the network, including standard deviation (SD), the Planning Time Index (PTI), the Travel Time Index (TTI), the Buffer Index (BI), On-time Measures PR (alpha), and the Misery Index (MI), to evaluate their effectiveness in clustering OD pairs using K-means clustering. The findings confirm that SD, PTI, and MI are particularly effective in measuring travel time reliability and clustering within urban systems. This study identifies the most unbalanced supply–demand OD pairs/regions in each city, noting that low/medium-SD clusters around metropolitan airports indicate stable travel times even in high-demand zones, while high-SD clusters in downtown areas reveal significant traffic demands and unreliability. These patterns become more pronounced in study areas with multiple city centers. This study highlights the need for targeted strategies to enhance travel time reliability, particularly in regions like Dallas–Fort Worth, where public transportation alternatives are limited.

Generating sparse origin–destination flows on shared mobility networks using probabilistic graph neural networks

Shared mobility services, such as bike sharing, have gained immense popularity and emerged as an integral part of sustainable urban mobility solutions. The planning of such systems requires forecasting the potential origin–destination (OD) flows between mobility sites (e.g., bike sharing stations) within the proposed network. Existing methods primarily focus on mobility flows between large regions, and do not generalize well to detailed planning applications due to the high spatial resolution required, with increased uncertainty and data sparsity. This study proposes a zero-inflated negative binomial graph neural network (ZINB-GNN) to generate sparse OD flows while capturing complex spatial dependencies. To reflect sparsity, OD flows are modeled as following ZINB distributions parameterized via feed-forward networks. To capture spatial dependencies, localized graphs are constructed to represent proximity between OD pairs, with spatial features encoded using GNNs. ZINB-GNN is validated through a case study of the bike sharing system in New York City. The results verify its prowess in both prediction accuracy and uncertainty quantification under real-world network expansion scenarios. We also demonstrate its interpretability by revealing important factors affecting OD flows. These findings can directly inform the planning of bike sharing systems, and the methodology may be adapted for other shared mobility systems.

Connectivity reliability evaluation and most reliable shipping route choice in a seaborne crude oil network

The connectivity reliability of strait and canal nodes in seaborne crude oil networks is uncertain because of various risk factors. Existing studies have mainly focused on road networks and often ignored real-world factors by assuming fixed and identical values for the connectivity reliability of each node, leading to inaccurate estimations. Few studies have considered node reliability when identifying the most reliable routes for oil shipments in response to various external and changing risks. To address these limitations, we first establish new connectivity reliability evaluation methods for both nodes and networks. Then, we develop the α-most reliable shipping route and the very most reliable shipping route models using uncertain programming to dynamically identify the most reliable routes for crude oil, ensuring timely and safe transportation. We apply these models to China's seaborne network of imported crude oil. The results show a network connectivity reliability of 0.6228, which is impacted by unreliable origin–destination pairs in the Middle East. The risk values of the most reliable oil shipping routes vary regionally, with higher values in Africa and the Middle East than in Asia and Latin America. As node risk increases, regional disparities also increase. These findings will aid in the development of energy transportation and import strategies to enhance transportation reliability.

Flowers and Bees: Spatial Network Effects in the Adoption of a Sharing-Economy Platform

This article empirically analyzes the spatiotemporal diffusion of a car-sharing platform that connects consumers with individual car owners. The authors develop a model of adoption by both consumers and providers that accommodates network effects across locations, as consumers travel to pick up cars, and information asymmetry, as only the providers’ locations are shown on a map. They apply it to data at the earliest stage of the platform and find that proximity and consumer mobility play a significant role in the spatial network effects of existing providers on consumers across locations. Consequently, the impact of additional supply at a destination on consumer adoptions at an origin varies by origin–destination pair and is asymmetric, as certain destinations draw more visitors than others and given differences in local characteristics. In contrast, existing consumers have a limited impact on provider adoptions. Through seeding experiments, the authors investigate how the geographic distribution of initial participants impacts the platform diffusion and find that targeting the supply side in big cities leads to the highest platform growth. They also use their parameter estimates to measure the long-term impact of a local promotional campaign and show that it is mostly local despite spatial network effects.

Short-Term Origin-Destination Demand Prediction Based on Spatiotemporal Encoder-Decoder Network with a Residual Feature Extractor

Online ride-hailing services play a crucial role in daily transportation, However, challenges persist in certain regions with limited access, and drivers encounter difficulties in receiving orders. Accurate prediction of short-term origin-destination (OD) demand is crucial for addressing these issues. This study leverages recent advancements in artificial intelligence and big data to introduce a spatiotemporal encoder-decoder network with a residual feature extractor (RF-STED) for short-term OD demand prediction in online ride-hailing services. The RF-STED model, built on deep learning models such as graph convolutional networks and convolutional long short-term memory (Conv-LSTM), includes spatiotemporal networks, encoding layers, and a residual feature extractor. The spatiotemporal network has two branches: branch one processes multi-pattern OD data using a multi-pattern temporal feature extraction module, utilizing a multi-channel Conv-LSTM to capture temporal correlations. Branch two utilizes a multi-spatial feature extraction module to convert OD pair associations into a spatial topology, extracting multi-spatial correlations. The encoding layer captures spatiotemporal dependencies, while the residual feature extractor decodes compressed vectors back into an OD graph for forecasting future demand. Experiments with a Manhattan taxi dataset in the U.S. show the RF-STED model outperforms 10 baseline models and four ablation models. The results emphasize the model’s strength and robustness in short-term OD flow prediction.

Short-term high-speed rail passenger flow prediction by integrating ensemble empirical mode decomposition with multivariate grey support vector machine

Short-term prediction of high-speed rail (HSR) passenger flow provides a daily ridership estimation for the near future, which is critical to HSR planning and operational decision making. This paper proposes a new methodology that integrates ensemble empirical mode decomposition with multivariate support vector machines (EEMD-MSVM). There are four steps in this hybrid forecasting approach: (i) explore the correlation of multivariate HSR passenger flows at various stations based on archived data; (ii) decompose empirical modes of historical passenger flows for each HSR station, using EEMD to generate a number of intrinsic mode functions (IMFs) and a trend term; (iii) predict the IMF for each correlated station pair using MSVM; and (iv) reconstruct the refined IMF components to predict daily multivariate HSR passenger flows. The proposed EEMD-MSVM approach is demonstrated with multiple OD pairs along the Wuhan-Guangzhou HSR in China. Results from various origin-destination pairs, show that the EEMD-MSVM approach outperforms the existing ensemble empirical mode decomposition with grey support vector machine approach (EEMD-GSVM). With the multivariate approach, the mean absolute percentage error in demand prediction is reduced by 13.9%, 1.2%, 1.0%, 2.0%, and 2.7% and the mean absolute deviation is reduced by 78.8, 38.0, 4.4, 4.6, and 3.9, between these OD pairs respectively. Such increase in short-term demand prediction accuracy can significantly improve HSR service planning, operations, and revenue management in the real world.

Linear regression coupled Wasserstein generative adversarial network for direct demand modeling of ride-hailing trips in Chicago and Austin

ABSTRACT Accurate estimation of ride-hailing demand and understanding of its influencing factors are necessary for modern-day transportation planning. Although modern machine learning techniques improve the predictive accuracy of zone-to-zone direct demand models, they lack inference ability due to their complex model structure. Furthermore, zone-to-zone direct demand models suffer from limited sample size for machine learning due to fixed number of origin-destination (OD) pairs. To overcome these limitations, we propose a linear regression coupled Wasserstein generative adversarial network (LR-WGAN) for direct demand modeling of zone-to-zone ride-hailing trips that captures both linear explanatory components and non-linear patterns and improves the predictive accuracy by generating data to expand the OD sample size. The proposed LR-WGAN is found to significantly improve the predictive accuracy of OD ride-hailing demand in Chicago and Austin. Furthermore, the linear explanatory component of the model is utilized to draw inferences regarding the relationship between OD ride-hailing demand and predictor variables.

Efficient demand management for the on-time arrival problem: A convexified multi-objective approach assuming macroscopic traffic dynamics

This work proposes a novel solution approach to address the On-Time Arrival (OTA) problem, considering macroscopic traffic dynamics. In this context, all drivers who intend to use the road infrastructure are required to communicate their origin–destination pair and desired arrival time to a central scheduler prior to starting their trip. In response, the scheduler assigns a departure time and a multi-regional route to each driver to make possible their on-time arrival at the destination. The OTA problem is formulated as a nonconvex, nonlinear, multi-objective optimization problem considering two objective criteria. The first criterion aims at minimizing the travel time of all drivers in the network to prevent congestion, while the second criterion seeks to minimize the discrepancy between the desired and actual arrival time. The proposed formulation is solved efficiently through an approximated convex solution that leverages the Normal Boundary Intersection (NBI) method to efficiently generate a representative sample of the Pareto Front. Additionally, two solution methodologies based on “knee” solution and the Nash Bargaining Game is proposed which can be used to select a unique solution across all the Pareto points, that offers a reasonable trade-off between the two objective criteria. Finally, simulation results demonstrate that the proposed solution can significantly reduce congestion while ensuring that most drivers will arrive at their destination on their desired time.

Congestion-aware Spatio-Temporal Graph Convolutional Network-based A* Search Algorithm for Fastest Route Search

The fastest route search, which is to find a path with the shortest travel time when the user initiates a query, has become one of the most important services in many map applications. To enhance the user experience of travel, it is necessary to achieve accurate and real-time route search. However, traffic conditions are changing dynamically, and the frequent occurrence of traffic congestion may greatly increase travel time. Thus, it is challenging to achieve the above goal. To deal with it, we present a congestion-aware spatio-temporal graph convolutional network-based A* search algorithm for the task of fastest route search. We first identify a sequence of consecutive congested traffic conditions as a traffic congestion event. Then, we propose a spatio-temporal graph convolutional network that jointly models the congestion events and changing travel time to capture their complex spatio-temporal correlations, which can predict the future travel-time information of each road segment as the basis of route planning. Further, we design a path-aided neural network to achieve effective origin-destination (OD) shortest travel-time estimation by encoding the complex relationships between OD pairs and their corresponding fastest paths. Finally, the cost function in the A* algorithm is set by fusing the output results of the two components, which is used to guide the route search. Our experimental results on the two real-world datasets show the superior performance of the proposed method.

A general coupled morning–evening traffic equilibrium model with rideshare, ride-hailing, and public transit services

We develop a general equilibrium model to capture the complex interactions between different modes, such as solo driving, public transit, as well as rideshare and ride-hailing services such as Uber and Lyft, under a joint morning and evening commute framework. Formulated as a variational inequality (VI) and equivalently as a mixed complementarity problem (MiCP), the model allows (a) travelers to switch between different transportation modes and (b) passengers from different Origin-Destination (OD) pairs to share a ride together. The computational results on the Sioux-Falls network show that our model captures the possible mode switches and the coupling effects between morning and evening commutes. Furthermore, our numerical examples demonstrate that modelling morning and evening commutes separately tends to overestimate the travelers' disutility and the average Vehicle Miles Traveled (VMT) in the network.