Origin-destination Flows Research Articles

Multitype Origin‐Destination (OD) Passenger Flow Prediction for Urban Rail Transit: A Deep Learning Clustering First Predicting Second Integrated Framework

Accurately predicting origin‐destination (OD) passenger flows serves as the basis for implementing efficient plans, including line planning and timetabling. However, due to the complexity and variety of OD passenger flows types, general prediction models have difficulty in capturing the features of different OD passenger flows, which in turn leads to poor prediction performance. To address this issue, we propose an integrated framework that combines clustering and prediction methods. First, an unsupervised deep learning model is devised to automatically cluster OD flow types by capturing shape characteristics. Second, three types of features are created to enhance training efficiency, including static features, time‐dependent observed features, and time‐dependent known features. Based on the clustering of OD passenger flow, a weighted adaptive passenger flow prediction model is developed. The study employs a temporal fusion transformers model to enable multitype OD passenger flow prediction. In the numerical experiments, the model was applied to the urban rail transit in South China, and the model clustered 15,168 OD pairs into 4 types for prediction. The findings show that this approach enhanced the prediction accuracy by 2.0%–9.6% compared to the LSTM model and by 1.6%–4.3% compared to the Graph WaveNet. Moreover, the model can accurately assess the various features for diverse types of OD flows.

A two-stage stochastic programming approach for dynamic OD estimation using LBSN data

Estimating origin–destination (OD) demand is essential for urban transport management and traffic control systems. With the ubiquity of smartphones, location based social networks (LBSN) data has emerged as a new rich data source with broad urban spatial and temporal coverage highly suitable for OD estimation. Its nature of confirmed trip purpose (activity) and activity chain host makes it more advantageous than other data (e.g., household travel surveys and traffic network detection). On the other hand, LBSN data is a more direct and accurate representation of demand patterns and can remove the significant burden of developing traffic models and estimating simulation-based objective functions. However, thus far, most LBSN-based estimation models only focus on static (day-level) OD estimation, making less use of those characteristics. To this end, this paper establishes a two-stage stochastic programming (TSSP) framework integrating the activity chains to model activity-level dynamic mobility flows using LBSN data. The first-stage model aims to minimize the errors introduced by the inter-zone OD flows alongside the expected errors of the check-in patterns. The second-stage model attempts to minimize the errors produced by the considered check-in pattern scenarios. Markov chain Monte Carlo (MCMC) sampling is used to generate plausible check-in scenarios. A generalized Benders decomposition (GBD) algorithm is presented to solve the two-stage stochastic programming model. We conduct the experiments on the case study of Tokyo, Japan, under the employment of the generalized least squares (GLS) estimator. The results show that algorithm convergence can be guaranteed within several iterations. The approach can provide satisfactory estimations of check-in patterns, zonal production and attraction, and OD flows. Furthermore, multiple objective function states are tested for evaluating the completeness of the proposed framework and exploring its potential for simplification and extension. Incorporating specific penalty terms into the objective function also provides a way to verify the reliability of the two-stage structure and validate the effectiveness of the model. Finally, we discuss the model enhancement from the perspectives of online OD estimation by integrating with LBSN simulations, network-wide OD extrapolation using appropriate scaling methods, and removing the user-side data requirement by leveraging activity chain modeling. The proposed framework provides a novel and effective approach to OD demand estimation using LBSN data.

GNN-based passenger request prediction

ABSTRACT Passenger request prediction is essential for operations planning, control, and management in ride-hailing platforms. While the demand prediction problem has been studied extensively, the Origin-Destination (OD) flow prediction of passengers has received less attention from the research community. This paper develops a Graph Neural Network (GNN) framework along with the Attention Mechanism to predict the OD flow of passengers. The proposed framework exploits various linear and non-linear dependencies that arise among requests originating from different locations and captures the repetition pattern and the contextual data of that place. Moreover, the optimal size of the grid cell that covers the road network and preserves the complexity and accuracy of the model is determined. Extensive simulations are conducted to examine the characteristics of our proposed approach and its various components. The results show the superior performance of our proposed model compared to the existing baselines.

Enhancing geospatial retail analysis by integrating synthetic human mobility simulations

The accuracy of retail location models depends on their precise calibration, but the data necessary for such a key task is seldom available. In this research, we use synthetic human mobility data, which introduces commuting dynamics, to improve the reliability of such models. We use the origin-destination flows to distribute households' potential expenditures in their home and commuting locations with the aim of modeling non-residential-driven demand in the commercial streets of Tokyo. We estimate potential revenues of commercial streets using the Huff model with its conventional specification as well as a variation of it that adopts pedestrian trajectory counts as the deterrence variable. We found that redistributing the potential expenditures toward the households' daytime locations significantly increased the model's performance. Additionally, we found that our use of pedestrian trajectory counts is comparable to using distance within the Huff model framework, but our proposed model was still outperformed by the conventional Huff model specification. We conclude that combining synthetic human mobility simulations and retail location models significantly increases the reliability of analysis in data-constrained situations.

An origin–destination passenger flow prediction system based on convolutional neural network and passenger source-based attention mechanism

An accurate origin–destination (OD) passenger flow prediction system is crucially important for urban metro operation and management. However, there are still lacking targeted prediction systems focusing on the passenger travel demand causing urban metro oversaturation. In this study, we first identify the passenger sources of the oversaturated sections and pinpoint the key part of passenger travel demand causing major oversaturation. Next, we take advantage of the attention mechanism and the masked loss function to incorporate the passenger source information into the prediction model and develop a passenger source attention mechanism based convolutional neural network (PSAM-CNN) model. Finally, the developed PSAM-CNN model is validated using the actual passenger travel demand data of Shenzhen Metro. Comparing with several state-of-art benchmark models, the PSAM-CNN model can predict the OD passenger flows causing urban metro oversaturation more accurately, providing more targeted and accurate OD flow information for improving the operation and management of urban metro.

GODDAG: Generating Origin-Destination Flow for New Cities Via Domain Adversarial Training

Origin-destination (OD) flow data, which reflects population mobility patterns in the city, is very important in many urban applications, such as urban planning and public resource allocation, etc. However, due to the high cost of money and time during device deployment and social surveys, it is challenging to obtain OD flow data, especially in developing cities and emerging cities where historical OD flow data is scarce. Therefore, it is necessary to investigate a method that can generate OD flow in cities where OD flow data are not available. The research on modeling population mobility in the city has a long history. Traditional gravity models, etc., are too simple to model the complex population mobility; recently proposed machine learning models and deep learning models are not applicable in cities where data are scarce because the parameters must be fitted with abundant data. To solve the problem of difficult access to OD flow data, we propose a method to learn mobility knowledge with ample data in the source city and generate OD flow data in new cities named <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GODDAG</b> ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>G</u></b> enerating <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>O</u></b> rigin- <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>D</u></b> estination Flow via <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>D</u></b> omain <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>A</u></b> dversarial Trainin <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>g</u></b> ). Our proposed method consists of two parts, one is a GNN (graph neural networks) based mobility model generating OD flow between every two regions based on regional attributes such as census and POI distribution, and the other is a domain adversarial training strategy to make the model have better transfer ability between different cities. Extensive experiments are conducted on two real-world datasets to prove the validity of our methods.

Strength-weighted flow cluster method considering spatiotemporal contiguity to reveal interregional association patterns

ABSTRACT One of the most crucial topics in spatial interaction studies is mining patterns from extensive origin-destination (OD) flow data to capture interregional associations. However, prevailing methodologies tend to disregard the importance of using the relative closeness of interregional connections as weights, treat spatial and temporal dimensions independently, or overlook the temporal dimension completely. Consequently, the identified patterns are susceptible to inaccuracies, and the precise identification of pattern occurrence time and duration, despite their fundamental importance, remains elusive. In light of these challenges, this study proposes a strategy to calculate and combine the strength of weighted spatiotemporal flows, and develops a clustering method and evaluation metrics based on this framework. Compared to alternative density-based methods, the strength-based calculation approach demonstrates a capacity to identify flow patterns characterized by relatively high interregional closeness. Thus, the identification of flow patterns expands beyond density-based approaches, encompassing strength-based considerations and a shift from absolute to relative closeness between regions. Experiments using synthetic datasets conducted in this research demonstrate the effectiveness, efficiency, and extraction accuracy of the proposed method. Furthermore, a case study using real Chinese population migration data demonstrates the efficacy of the method in revealing implicit spatiotemporal association patterns between regions. The present study implements an interaction strength-based flow clustering and evaluation method that considers spatiotemporal continuity, making it applicable to spatial flow data analysis involving interaction volume and time attributes. As a result, this method holds promise for facilitating the modeling of intricate spatial flows within various contexts of study.

A kriging interpolation model for geographical flows

The kriging model can accommodate various spatial supports and has been extensively applied in hydrology, meteorology, soil science, and other domains. With the expansion of applications, it is essential to extend the kriging model for new spatial support of high-dimensional data. Geographical flows can depict the movements of geographical objects and imply the underlying mobility patterns in geographical phenomena. However, due to the bias, sparsity, and uneven quality of flow data in the real world, research about flows remains hindered by the lack of complete flow data and effective flow interpolation methods. In this study, we design a kriging interpolation model for flows based on several flow-related concepts and the autocorrelation of flows. We also analyze the second-order stationarity and anisotropy in the flow spatial random field. To illustrate the effectiveness and applicability of our method, we conduct two case studies. The former case study compares several experiments of flow density interpolation using Beijing mobile signaling data and illustrates the conditions of applicable areas. The latter case study extends our model to other flow attributes, such as travel time uncertainty, using Beijing taxi origin-destination flow data. The results of these cases demonstrate the effectiveness and high accuracy of our model.

A hybrid modelling framework for the estimation of dynamic origin–destination flows

The dynamic origin–destination flow estimation (DODE) problem requires scalable methods for large scale traffic networks and consistent techniques for capturing both uncongested and congested traffic conditions. Despite numerous efforts on incorporating multifold data sources and developing manifold mathematical models, the DODE problem remains a challenging problem in terms of both scalability and consistency. To fill this gap, we propose a novel hybrid DODE framework that integrates region-level (macro) and centroid-level (micro) traffic dynamics. The region-level traffic flows are described by the macroscopic fundamental diagram, while the centroid-level traffic flows are represented by the linear mapping of origin–destination flows onto link counts. This hybrid approach enables us to (i) incorporate region-level traffic measures into the problem, addressing scalability issues arising in large scale traffic networks, and (ii) capture non-linear behaviour of traffic in the regional context, enhancing consistency of the estimation results with respect to traffic conditions. The proposed methodology is experimented in a large-scale traffic network, which is benchmarked for DODE problems. The results indicate an outstanding performance of the hybrid DODE particularly in congested traffic conditions and highlight the effectiveness of aggregated (regional) traffic models in enhancing DODE methods with minimal computational burden.

A spatiotemporal analysis of the impact of lockdown and coronavirus on London’s bicycle hire scheme: from response to recovery to a new normal

ABSTRACT The coronavirus pandemic that started in 2019 has had wide-ranging impacts on many aspects of people’s daily lives. At the peak of the outbreak, lockdown measures and social distancing changed the ways in which cities function. In particular, they had profound impacts on urban transportation systems, with public transport being shut down in many cities. Bike share systems (BSS) were widely reported as having experienced an increase in demand during the early stages of the pandemic before returning to pre-pandemic levels. However, the studies published to date focus mainly on the first year of the pandemic, when various waves saw continual relaxing and reintroductions of restrictions. Therefore, they fall short of exploring the role of BSS as we move to the post-pandemic period. To address this gap, this study uses origin-destination (O-D) flow data from London’s Santander Cycle Hire Scheme from 2019–2021 to analyze the changing use of BSS throughout the first two years of the pandemic, from lockdown to recovery. A Gaussian mixture model (GMM) is used to cluster 2019 BSS trips into three distinct clusters based on their duration and distance. The clusters are used as a reference from which to measure spatial and temporal change in 2020 and 2021. In agreement with previous research, BSS usage was found to have declined by nearly 30% during the first lockdown. Usage then saw a sharp increase as restrictions were lifted, characterized by longer, less direct trips throughout the afternoon rather than typical peak commuting trips. Although the aggregate number of BSS trips appeared to return to normal by October 2020, this was against the backdrop of continuing restrictions on international travel and work from home orders. The period between July and December 2021 was the first period that all government restrictions were lifted. During this time, BSS trips reached higher levels than in 2019. Spatio-temporal analysis indicates a shift away from the traditional morning and evening peak to a more diffuse pattern of working hours. The results indicate that the pandemic may have had sustained impacts on travel behavior, leading to a “new normal” that reflects different ways of working.

Improving service qualities of cyclic line plans considering heterogeneous passenger origin-destination (OD) flow groups

ABSTRACT Cyclic train services provide huge conveniences to passengers. This work aims to fix one vital promise in major line planning studies that passengers were homogeneous. In fact, passengers’ rail travel expectations are heterogeneous. But those heterogeneities show common needs correlating with travel distances and defined station levels. Therefore, we cluster passenger heterogeneities into divided OD groups, extend service qualities, and add more train line factors to our line planning model. Cyclic line plan from this joint optimisation not only receives service quality improvements but also provides multiple train service types to match clustered OD groups. Moreover, we allow passengers to be served by different train service types, deliver a high level of direct services, and maintain the minimum operation cost. We compare concluded line plans with the results of the generic line planning model and the real-world line plan to show our solution advantages.

International Migration and Development: The Changing Impact of Migration on Redistributing Global Population

This research note explores the impact of international migration on global population distribution since the 1990s. The impact of migration on population distribution is a function of both the intensity as well as the effectiveness of migration, that is the imbalance between flows and counter-flows. The presence of reciprocal flows is a well-recognized feature of international migration systems; however, this dimension has been difficult to capture at the global level due to a lack of origin-destination flow data. In this research note, we apply metrics developed for the analysis of internal migration to global migration flows to explore the impact of international migration on global population distribution over time, and across levels of human development. In the five years to 2020, international migration redistributed 0.39 percent of the world's population (28 million people) despite 1.38 percent (101 million) changing country of residence. This has declined from 0.56 percent of the global population in 1990–1995. This decline in impact is underpinned by a reduction in migration effectiveness, that is, the migration system is becoming more balanced over time. The impact of migration was greatest for flows between countries at Very High levels of human development, reflecting high migration intensity and exchanges between countries at Low and Very High levels of human development, reflecting significant asymmetry of flows. Our results suggest systematic shifts in both the level and pattern of flows across the development ladder, with flows becoming more intense and balanced with higher levels of human development.

Estimation of spatial autoregressive models for origin–destination flows: A partial likelihood approach

We extend LeSage and Pace (2008)’s spatial autoregressive model for origin–destination flows by accommodating two-way fixed effects. A partial likelihood approach is used for estimation by applying an orthogonal transformation to remove fixed effects in the model. The quasi-maximum likelihood (QML) estimator of the partial log-likelihood function is consistent and asymptotically centered normal. Monte Carlo experiments verify this advantage in finite samples. From the U.S. migration flows, significant spatial influences are captured with smaller magnitudes than those from the model without fixed effects.

Exploring the spatiotemporal relationships between search flows and travel flows

AbstractNumerous studies attempted to associate search engine data with travel behaviors. However, most existing studies focus on the destinations of search and travel, while ignoring the origins, which embed critical information of where the search requests were initiated and where the travelers came from. In this study, we explore the relationships between two types of intercity origin–destination flow data, namely travel flows and search flows, which, respectively, record the number of travelers and search requests from one city towards another. By comparing the two flows during holiday and non‐holiday, we examine their complex spatiotemporal relationships from multiple perspectives, including time‐lag effect, distance decay effect, spatial autocorrelation, network community, cities' rankings, and important factors of search and travel activities. The findings can deepen our understanding of search and travel behaviors, hence they can help decision makers to develop targeted strategies to enhance city's attractiveness, improve transportation infrastructure, and promote tourism.

Exploring Crowd Travel Demands Based on the Characteristics of Spatiotemporal Interaction between Urban Functional Zones

As a hot research topic in urban geography, spatiotemporal interaction analysis has been used to detect the hotspot mobility patterns of crowds and urban structures based on the origin-destination (OD) flow data, which provide useful information for urban planning and traffic management applications. However, existing methods mainly focus on the detection of explicit spatial interaction patterns (such as spatial flow clusters) in OD flow data, with less attention to the discovery of underlying crowd travel demands. Therefore, this paper proposes a framework to discover the crowd travel demands by associating the dynamic spatiotemporal interaction patterns and the contextual semantic features of the geographical environment. With urban functional zones (UFZs) as the basic units of human mobility in urban spaces, this paper gives a case study in Wuhan, China, to detect and interpret the human mobility patterns based on the characteristics of spatiotemporal interaction between UFZs. Firstly, we build the spatiotemporal interaction matrix based on the OD flows of different UFZs and analyze the characteristics of the interaction matrix. Then, hotspot poles, defined as the local areas where people gather significantly, are extracted using the Gi-statistic-based spatial hotspot detection algorithm. Next, we develop a frequent interaction pattern mining method to detect the frequent interaction patterns of the hotspot poles. Finally, based on the detected frequent interaction patterns, we discover the travel demands of crowds with semantic features of corresponding urban functional zones. The characteristics of crowd travel distance and travel time are further discussed. Experiments with floating car data, road networks, and POIs in Wuhan were conducted, and results show that the underlying travel demands can be better discovered and interpreted by the proposed framework and methods in this paper. This study helps to understand the characteristics of human movement and can provide support for applications such as urban planning and facility optimization.

Dynamic origin–destination flow estimation for urban road network solely using probe vehicle trajectory data

Dynamic origin–destination (OD) flow is a fundamental input for dynamic network models and simulators. Numerous studies have conducted dynamic OD estimations based on fixed detectors, where a high device coverage rate and data quality are often required to accomplish the desired results. Several existing methods have used probe vehicle trajectories as an additional data source, and generalized least squares (GLS) is commonly recognized as an effective framework. However, the prior matrices used in these models either came from historical data or data obtained by uniform scaling that neglected the variation in penetration rates and suffer from sparsity issues. Moreover, the microscopic information contained in the high-resolution probe vehicle trajectories has not been fully utilized. The possibility of estimating OD flows using only vehicle trajectories without external information is rarely discussed in current literature. Therefore, this paper introduces a dynamic OD flow estimation model solely using probe vehicle trajectories. In the proposed model, two methods based on probe OD pair distribution are proposed to infer prior OD flows. Then the GLS framework is extended by including link travel times as another objective term, and the solution algorithm is adapted to deal with uncertain priors. To validate the proposed model, extensive experiments were conducted on a simulation network. The results show that the proposed model could reliably estimate dynamic OD flows and showed superiority to two existing models. In sensitivity analysis concerning the penetration rate and degree of saturation, the proposed model presented satisfactory performance and could adapt to various conditions.

Adaptive Feature Fusion Networks for Origin-Destination Passenger Flow Prediction in Metro Systems

Accurately predicting Origin-Destination (OD) passenger flow can help metro service quality and efficiency. Existing works have focused on predicting incoming and outgoing flows for individual stations, while little attention was paid to OD prediction in metro systems. The challenges are that OD flows 1) have high temporal dynamics and complex spatial correlations, 2) are affected by external factors, and 3) have sparse and incomplete data slices. In this paper, we propose an Adaptive Feature Fusion Network (AFFN) to a) adaptively fuse spatial dependencies from multiple knowledge-based graphs and even hidden correlations between stations and b) accurately capture the periodic patterns of passenger flows based on the auto-learned impact from external factors. To deal with the incompleteness and sparsity of OD matrices, we extend AFFN to multi-task AFFN to predict the inflow and outflow of each station as a side-task to further improve OD prediction accuracy. We conducted extensive experiments on two real-world metro trip datasets collected in Nanjing and Xi’an, China. Evaluation results show that our AFFN and multi-task AFFN outperform the state-of-the-art baseline techniques and AFFN variants in various accuracy metrics, demonstrating the effectiveness of AFFN and each of its key components in OD prediction.

Designing a Novel Two-Stage Fusion Framework to Predict Short-Term Origin–Destination Flow

Short-term origin-destination (OD) demand predicting plays an indispensable role in intelligent transportation systems and ride-hailing service operations. However, most studies are carried out in trip ends travel demand prediction, i.e., trip generation/attraction, while paying less attention to predicting OD flows in citywide traffic management. To this end, a novel generalized framework is proposed, named two-stage fusion framework (TFF). TFF consists of two stages, where the first stage utilizes an attention-based spatio-temporal graph convolutional network (AST-GCN) to predict the trip generation/attraction, and the second stage develops a modified Kalman filter (KF) to predict OD flow which is converted into a coefficient matrix. Lastly, the final predicted OD can be obtained by integrating the trip generation/attraction and the coefficient matrix. In AST-GCN, a gated fusion mechanism and dynamical zone proximity matrix are applied to improve the capacity of capturing the spatio-temporal interdependence among traffic analysis zones. In KF, we redefine the state vector and observed vector and their covariance matrixes, and then introduce the Box-Cox technique to standardize the deviation matrix to adapt to KF. The proposed model is tested on a large-scale real-world data set from Chongqing, China, and the results indicate that TFF can achieve a satisfactory performance of short-term OD prediction. Moreover, the proposed framework has the convenient scalability, because either of the two stages is replaceable by other predictors.

Ranking Spatial Units with Structural Property and Traffic Distributions for Uncovering Spatial Interaction Patterns in a City

Travel activity data mining is critical to numerous urban applications such as transportation and location‐based services. This article studies the spatial units ranking algorithm for uncovering spatial interaction patterns based on the flow properties of people's travel trajectories. For example, using a taxi origin–destination flow database, a user may want to rank the origin and destination with respect to their functional importance within the urban activity space. In the literature, such an importance concept is usually specified via the frequency function of trip flows. Considering the case that the less frequently visited place in reality may still be an important origin or an important destination, we propose a different method for the ranking of spatial units by introducing the structural property of trip network. The proposed method is inspired from the mutual reinforcing relationship between the trip origins and destinations: important destinations attract travel flows from important origins and at the same time important origins have many flows toward important destinations. Our experimental results show that the proposed method is effective in uncovering spatial interaction patterns of urban activities.

Multi-period single-allocation hub location-routing: Models and heuristic solutions

This work investigates the use of time-dependent decisions in the context of hub-location routing. Instead of setting up the entire system at once, a planning horizon partitioned into several periods is considered during which the system is to be phased-in. In addition to installing the hubs, decisions are also to be made concerning the hub-level network, namely, the hub edges to use. The origin-destination flows are assumed to be time-dependent as well as the costs underlying the problem which include, set up costs for hubs and hub edges and variable operational costs at the hubs. A mathematical model is developed for the problem that can be solved up to proven optimality with a general-purpose solver for small instances of the problem. For larger instances, a four-phase matheuristic that combines principles of relax-and-fix, variable neighborhood descent and local branching schemes is proposed. In addition, two variants of the matheuristic have been developed. The above model and methodology are tested using data generated by extending existing hub location instances to our problem. The obtained results are detailed and analyzed in depth. The major conclusion is that by capturing time in the decision-making process, one may find solutions that better hedge against parameter changes throughout time. Furthermore, the overall procedure presented in this work is quite general in the sense that it can be easily adapted to other multi-period decision making problems and different objective functions.