Spatiotemporal Mobility Research Articles

Modeling Spatio-Temporal Mobility Across Data Silos via Personalized Federated Learning

Modeling Spatio-Temporal Mobility Across Data Silos via Personalized Federated Learning

Combining the spatiotemporal mobility patterns and MMC for next location prediction of fake base stations

The spatiotemporal mobility patterns and next location prediction of fake base stations (FBS) provide important technical support for the police to prevent spam messages from FBS. However, due to the difficulty in locating their real-time locations, our understanding of the mobility patterns and predictability of FBS is still limited. Based on the crowdsourced spam data, we extract the time and potential locations of FBS and propose a Tucker-MMC method that combines Tucker decomposition with a Mobility Markov Chain (MMC) model to investigate the mobility patterns and predictability of FBS sending spam messages. First, we utilize Tucker decomposition to reflect the spatial and temporal preferences during the movement of the corresponding FBS. Then the mobility regularity and the theoretical maximum predictability of the FBS trajectories with similar mobility preferences are analyzed by entropy and Fano's inequality. A Tucker-MMC is also established for the next location prediction. The results using the spam dataset in Beijing show that the accuracy of Tucker-MMC is more than double that of the MMC. The accuracy of the actual location prediction model is more likely to approach the theoretical maximum predictability when FBS send spam messages in a shorter time, shorter transfer distance, and smaller access range.

Unveiling the daily rhythm of urban space: Exploring the influence of built environment on spatiotemporal mobility patterns

Urban mobility research is crucial due to the complex and dynamic nature of cities. Traditional zoning methods often overlook the temporal dynamics of urban space usage. This paper aims to investigate the daily rhythm of urban space usage and how built environmental features affect spatiotemporal mobility. The methodology integrates various urban data sources, including street and building vectors and points of interest (POI). In Ankara, Türkiye, temporal usage types were identified using principle component analysis and k-means algorithms via Google Maps location-based service data. Multinomial logistic regression model was used to examine the impact of built-environment factors on daily mobility patterns. Results reveal distinct daily usage rhythms, categorizing busy areas into morning, noon, early evening, late evening, diurnal, and nocturnal zones. The study finds: (1) temporal usage is closely associated with spatial characteristics and resident income; (2) work-related activities drive morning mobility, while nighttime mobility relates to residence, income, and accessibility; and (3) population density alone does not guarantee continuous activities; diverse POIs alongside high density are crucial. The identified relationship between mobility measures and urban built environment indicators provides a comprehensive understanding of spatiotemporal variations, offering insights for critical policy evaluations and proposals for the future of urban areas.

A GIS-Based Framework for Synthesizing City-Scale Long-Term Individual-Level Spatial–Temporal Mobility

Human mobility data are crucial for transportation planning and congestion management. However, challenges persist in accessing and using raw mobility data due to privacy concerns and data quality issues such as redundancy, missing values, and noise. This research introduces an innovative GIS-based framework for creating individual-level long-term spatio-temporal mobility data at a city scale. The methodology decomposes and represents individual mobility by identifying key locations where activities take place and life patterns that describe transitions between these locations. Then, we present methods for extracting, representing, and generating key locations and life patterns from large-scale human mobility data. Using long-term mobility data from Shanghai, we extract life patterns and key locations and successfully generate the mobility of 30,000 virtual users over seven days in Shanghai. The high correlation (R² = 0.905) indicates a strong similarity between the generated data and ground-truth data. By testing the combination of key locations and life patterns from different areas, the model demonstrates strong transferability within and across cities, with relatively low RMSE values across all scenarios, the highest being around 0.04. By testing the representativeness of the generated mobility data, we find that using only about 0.25% of the generated individuals’ mobility is sufficient to represent the dynamic changes of the entire urban population on a daily and hourly resolution. The proposed methodology offers a novel tool for generating long-term spatiotemporal mobility patterns at the individual level, thereby avoiding the privacy concerns associated with releasing real data. This approach supports the broad application of individual mobility data in urban planning, traffic management, and other related fields.

Modeling Multimodal Curbside Usage in Dynamic Networks

The proliferation of emerging mobility technology has led to a significant increase in demand for ride-hailing services, on-demand deliveries, and micromobility services, transforming curb spaces into valuable public infrastructure for which multimodal transportation competes. However, the increasing utilization of curbs by different traffic modes has substantial societal impacts, further altering travelers’ choices and polluting the urban environment. Integrating the spatiotemporal characteristics of various behaviors related to curb utilization into general dynamic networks and exploring mobility patterns with multisource data remain a challenge. To address this issue, this study proposes a comprehensive framework of modeling curbside usage by multimodal transportation in a general dynamic network. The framework encapsulates route choices, curb space competition, and interactive effects among different curb users, and it embeds the dynamics of curb usage into a mesoscopic dynamic network model. Furthermore, a curb-aware dynamic origin-destination demand estimation framework is proposed to reveal the network-level spatiotemporal mobility patterns associated with curb usage through a physics-informed data-driven approach. The framework integrates emerging real-world curb use data in conjunction with other mobility data represented on computational graphs, which can be solved efficiently using the forward-backward algorithm on large-scale networks. The framework is examined on a small network as well as a large-scale real-world network. The estimation results on both networks are satisfactory and compelling, demonstrating the capability of the framework to estimate the spatiotemporal curb usage by multimodal transportation. History: This paper has been accepted for the Transportation Science Special Issue on ISTTT25. Funding: This material is based upon work supported by the Office of Energy Efficiency and Renewable Energy, U.S. Department of Energy [Award DE-EE0009659]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2024.0522 .

Multiple GRAphs-oriented Random wAlk (MulGRA2) for social link prediction

Current link prediction methods in Location-Based Social Networks (LBSNs) fuse graphs derived from users' check-in data and their social links to form a single graph or network. Then, they learn node representations and link probabilities from a fused graph that undermines the distinctive characteristics of each user's spatiotemporal mobility and social links. Consequently, the input datasets are heavily contaminated with noise, which makes it challenging for these algorithms to make accurate predictions. Our study employs the proposed Multiple GRAphs-oriented Random wAlk (MulGRA2) to model graphs while maintaining the distinctive characteristics of the data to address the issue of noisy data in the learning process. Specifically, we use three graphs: a social graph constructed from social links data, a user co-occurrence graph derived from users' check-in data to capture spatiotemporal co-occurrence, and a user-location bipartite graph that links users to specific locations based on the same check-in data. After traversing all three graphs, it learns node representation and infers links effectively. Extensive experiments on both Foursquare and synthetic datasets demonstrate that our algorithm significantly improves link prediction performance. Furthermore, sensitivity analysis on various datasets confirms the robustness of our algorithm.

Finding Spatiotemporal Patterns of Mobile Application Usage

Understanding mobile application usage patterns is significant for producing better services and enriching user experience. The understanding of spatiotemporal patterns of application usage is still limited. In this paper, we aim at finding spatiotemporal mobile app usage patterns and propose a framework to capture who, when, where, and what applications are used. We first collect a large-scale and real-world application usage dataset covering over 400 thousand active users and 600 million records. In order to introduce spatial features, we partition the collection area into small regions. By grouping regions of similar point-of-interest attributes, we then map 796 regions onto 13 region clusters with semantic meanings. As a result, the original data is reformed as a tensor of four dimensions, i.e., users, application categories, region clusters, and time-slots. We then leverage a multi-way clustering algorithm on the tensor to extract coupling relations between different dimensions. Finally, we discover 508 distinct spatiotemporal application usage patterns with meaningful labels, including E- readers, Digital payers, Uber/DiDi drivers, Young parents, Travellers and Travel planners. The results produced by our framework can serve a series of applications, e.g., identifying user habits and inferring user demographics, which are helpful in customized services like personalized recommendations.

Colossal Trajectory Mining: A unifying approach to mine behavioral mobility patterns

Spatio-temporal mobility patterns are at the core of strategic applications such as urban planning and monitoring. Depending on the strength of spatio-temporal constraints, different mobility patterns can be defined. While existing approaches work well in the extraction of groups of objects sharing fine-grained paths, the huge volume of large-scale data asks for coarse-grained solutions. In this paper, we introduce Colossal Trajectory Mining (CTM) to efficiently extract heterogeneous mobility patterns out of a multidimensional space that, along with space and time dimensions, can consider additional trajectory features (e.g., means of transport or activity) to characterize behavioral mobility patterns. The algorithm is natively designed in a distributed fashion, and the experimental evaluation shows its scalability with respect to the involved features and the cardinality of the trajectory dataset.

Robust Location Prediction over Sparse Spatiotemporal Trajectory Data: Flashback to the Right Moment!

As a fundamental problem in human mobility modeling, location prediction forecasts a user’s next location based on historical user mobility trajectories. Recurrent neural networks (RNNs) have been widely used to capture sequential patterns of user visited locations for solving location prediction problems. Due to the sparse nature of real-world user mobility trajectories, existing techniques strive to improve RNNs by incorporating spatiotemporal contexts into the recurrent hidden state passing process of RNNs using context-parameterized transition matrices or gates. However, such a scheme mismatches universal spatiotemporal mobility laws and thus cannot fully benefit from rich spatiotemporal contexts encoded in user mobility trajectories. Against this background, we propose Flashback++, a general RNN architecture designed for modeling sparse user mobility trajectories. It not only leverages rich spatiotemporal contexts to search past hidden states with high predictive power but also learns to optimally combine them via a hidden state re-weighting mechanism, which significantly improves the robustness of the models against different settings and datasets. Our extensive evaluation compares Flashback++ against a sizable collection of state-of-the-art techniques on two real-world location-based social networks datasets and one on-campus mobility dataset. Results show that Flashback++ not only consistently and significantly outperforms all baseline techniques by 20.56% to 44.36% but also achieves better robustness of location prediction performance against different model settings (different RNN architectures and numbers of hidden states to flash back), different levels of trajectory sparsity, and different train-testing splitting ratios than baselines, yielding an improvement of 31.05% to 94.60%.

You Are How You Use Apps: User Profiling Based on Spatiotemporal App Usage Behavior

Mobile apps have become an indispensable part of people’s daily lives. Users determine what apps to use and when and where to use them based on their tastes, interests, and personal demands, depending on their personality traits. This article aims to infer user profiles from their spatiotemporal mobile app usage behavior. Specifically, we first transform mobile app usage records into a heterogeneous graph. On the graph, nodes represent users, apps, locations, and time slots. Edges describe the co-occurrence of entities in usage records. We then develop a multi-relational heterogeneous graph attention network (MRel-HGAN), an end-to-end system for user profiling. MRel-HGAN first adopts a neighbor sampling strategy based on bootstrapping to sample heavily connected neighbors of a fixed size for each node. Next, we design a relational graph convolutional operation and a multi-relational attention operation. Through such modules, MRel-HGAN can generate node embedding by sufficiently leveraging the rich semantic information of the multi-relational structure in the mobile app usage graph. Experimental results on real-world mobile app usage datasets show the effectiveness and superiority of our MRel-HGAN in the user profiling task for attributes of gender and age.

Measuring visitor flows using mobile positioning data in three Hungarian second-tier cities

PurposeThe research analyses the spatial-temporal behaviour of international visitors using mobile positioning data (MPD) in three second-tier cities in Hungary: Szeged, Debrecen and Pécs. The purpose of this study is to identify the origins of visitors, length of stay, seasonal concentrations and mobility between cities.Design/methodology/approachA large volume of data generated by foreign mobile phone users was processed and analysed for six consecutive months in 2018. The movements of around 3.5 million foreigners visiting Hungary were captured.FindingsThe data showed significant differences in tourist turnover, mobility patterns and flows indicating different levels of tourism activity and potential in the three cities. This included day trips, cross-border tourism, seasonal fluctuations and activity-driven demand (e.g. special events and cultural tourism).Research limitations/implicationsMPD cannot fully explain or predict drivers of visitor behaviour, such as purpose of visit, the precise activities that they undertake there and the experiences that they gain. It can, however, provide information on spatial and temporal flows, patterns and concentrations of visitors.Practical implicationsThe investigated cities should follow distinct tourism development policies to attract more tourists and strengthen the links with their neighbouring destinations at the same time as differentiating themselves through marketing as competitive alternative destinations.Social implicationsAugmenting tourism has socio-economic implications for residents and communities. The development of cultural tourism and local event-based tourism must incorporate community needs.Originality/valueThe paper analyses the extent to which MPD can provide insights into visitors’ spatio-temporal mobility and flows in relatively under-visited second-tier cities and it highlights opportunities and gaps for big data research in an urban context.

Towards Robust Task Assignment in Mobile Crowdsensing Systems

Mobile Crowdsensing (MCS), which assigns outsourced sensing tasks to volunteer workers, has become an appealing paradigm to collaboratively collect data from surrounding environments. However, during actual task implementation, various unpredictable disruptions are usually inevitable, which might cause a task execution failure and thus impair the benefit of MCS systems. Practically, via reactively shifting the pre-determined assignment scheme in real time, it is usually impossible to develop reassignment schemes without a sacrifice of the system performance. Against this background, we turn to an alternative solution, i.e., proactively creating a robust task assignment scheme offline. In this work, we provide the first attempt to investigate an important and realistic RoBust Task Assignment (RBTA) problem in MCS systems, and try to strengthen the assignment scheme's robustness while minimizing the workers' traveling detour cost simultaneously. By leveraging the workers' spatiotemporal mobility, we propose an assignment-graph-based approach. Firstly, an assignment graph is constructed to locally model the assignment relationship between the released MCS tasks and available workers. And then, under the framework of evolutionary multi-tasking, we devise a population-based optimization algorithm, namely EMTRA, to effectively achieve adequate Pareto-optimal schemes. Comprehensive experiments on two real-world datasets clearly validate the effectiveness and applicability of our proposed approach.

“You hold your life in your hands until you arrive in another country”: young Afghans seeking onward mobility from Greece

ABSTRACT This article considers the interplay between mobility and immobility in the everyday lives of young people on the move. It looks at the ways interactions with and categorisations by protection structures and restrictive border and migration regimes lead to diverse trajectories. The article is based on research with young men from Afghanistan mostly classified as unaccompanied minors. Some of the young men were seeking to continue their journeys from Greece and others had managed and had arrived in Norway. The young people’s trajectories were marked by uneven rhythms and multiple forms of movement and stasis with various effects on the body and the intimate. Whether they were categorised as accompanied or unaccompanied children or as adults also governed their spatiotemporal mobility and led to different, partly contradictory, temporalities. Moreover, imagination, desire, and conditions endured in the places they had left and moved through interacted and encouraged onward mobility.

Time sequence three-phase probabilistic power flow calculation for power system including traction station load of high-speed railway

The increasing traction station load of high-speed railway with single-phase, high-power, spatiotemporal mobility, and uncertainty has brought major impacts and challenges to the power system. The non-negligible characteristics are the spatial distribution of traction stations on high-speed railway lines, the time sequence of traction load moving with EMUs, as well as the nonparametric probabilistic features and correlation of traction load. A method of time sequence three-phase probabilistic power flow (3PPF) calculation for power system including traction station load of high-speed railway is proposed in this paper. Firstly, through the port transformation of traction power supply system (TPSS), the three-phase equivalent model of TPSS is established to construct an unbalanced three-phase power flow calculation model of grid with traction station load. Secondly, considering the spatial correlation, time sequence and non-parametric probabilistic feature of traction load, the time sequence probabilistic models of multiple traction station loads are built based on diffusion-based kernel density estimator (DKDE). Then, the algorithm of time sequence 3PPF calculation based on three-point estimation method (3PEM) is applied to deal with the computational efficiency and accuracy problems of 3PPF considering correlation and timing. Finally, the two modified three-phase power systems are employed for case studies in combination with the measured data of traction station of a high-speed railway. The validity and computing efficiency of the proposed method are verified.

Spatiotemporal Flow L-function: a new method for identifying spatiotemporal clusters in geographical flow data

A geographical flow (hereafter flow) is defined as a movement between locations at two different times. A group of spatiotemporal flows can be viewed as a cluster if their origins and destinations are both spatiotemporally concentrated. Identifying spatiotemporal flow clusters may help reveal underlying spatiotemporal mobility trends or intensive relationships between regions. Despite recent advances in flow clustering methods, most only consider spatial attributes and ignore temporal information, and may fail to differentiate space-close but time-separated clusters. To this end, we derive global and local versions of the Spatiotemporal Flow L-function, extended from the classical L-function for points, and thereby construct a clustering method. First, the global version is utilized to check whether flow data contain clusters and estimate the spatial and temporal scales of the clusters. The local version is then employed to extract the clusters with the estimated scales. Experiments of simulated data demonstrate that our method outperforms three state-of-the-art methods in identifying spatiotemporal flow clusters with arbitrary shapes and different densities and reducing subjectivity in the parameter selection process. A case study with taxi data shows that our method reveals residents’ spatiotemporal moving patterns, including rush-hour commuting and whole-daytime transferring among railway stations.

Integrated design framework for on-demand transit system based on spatiotemporal mobility patterns

On-demand transit is a flexible transit service designed to adjust the service schedule and route based on passengers’ dynamic demand. The operation of on-demand transit operates in accordance with physical and socioeconomic environments, and demand patterns. In order to meet the diverse mobility needs in urban areas, integrating different transit services is essential to improve both passenger convenience and operational efficiency simultaneously. We propose a data-driven design framework for an on-demand transit system that operates three types of services: planned-and-inflexible (PI), planned-and-flexible (PF), and unplanned-and-flexible (UF), each with varying levels of responsiveness to real-time demand. We classify historical demand data into three classes based on their spatiotemporal density. Then, we use the trip data of each class to plan and operate the PI, PF, and UF services. The performance of the proposed system is evaluated using real public transit data from Sejong city. Simulation studies reveal that the proposed system outperforms the existing on-demand transit system. Specifically, we observe that the PI and PF services, which are planned based on the historical spatiotemporal mobility patterns, highly compatible with requests that follow the major mobility patterns. At the same time, the UF service, which offers real-time routing without prior planning, covers areas and times beyond those served by the PI and PF services that do not correspond to major mobility patterns. Furthermore, we found that the proposed system is flexible enough to accommodate various real-world demand patterns by proving suggestions on the optimal vehicle operation for each service.

How does socioeconomic status influence social relations? A perspective from mobile phone data

Socioeconomic status (SES) and social relations are two important aspects of human social life. Does socioeconomic status influence social relations? If some relationship exists, it will help us understand various social issues such as economic mobility, social segregation, and disparity in health outcomes. Despite long-term efforts, our knowledge about how SES influences the strength and types of social relations is still limited. In this study, we used a large mobile phone dataset in Beijing, China, to study the relationship between SES and the strength and types of social relations at an urban population level. Specifically, we divided the social relations into three types based on users’ spatiotemporal mobility similarity: (1) family members with high similarity on weekday nights and weekends; (2) coworkers with high similarity on weekdays during the daytime; (3) friends with low similarity all the time. An individual’s SES was represented by the housing price in the home location. The results showed that people of higher SES (living in areas with higher housing prices) tend to interact less with others and allocate more time with friends but less time with family and coworkers than people of lower SES. Besides, people of higher SES split their time more unevenly to different social relationships. These findings shed light on solutions related to SES and inequality. For example, people of low SES could learn to expand their social circles by connecting with people who are different from their daily environment, which may bring upward social mobility and improve their well-being.

Using unstable data from mobile phone applications to examine recent trajectories of retail centre recovery

The COVID-19 pandemic has changed the ways in which we shop, with significant impacts on retail and consumption spaces. Yet, empirical evidence of these impacts, specifically at the national level, or focusing on latter periods of the pandemic remain notably absent. Using a large spatio-temporal mobility dataset, which exhibits significant temporal instability, we explore the recovery of retail centres from summer 2021 to 2022, considering in particular how these responses are determined by the functional and structural characteristics of retail centres and their regional geography. Our findings provide important empirical evidence of the multidimensionality of retail centre recovery, highlighting in particular the importance of composition, e-resilience and catchment deprivation in determining such trajectories, and identifying key retail centre functions and regions that appear to be recovering faster than others. In addition, we present a use case for mobility data that exhibits temporal stability, highlighting the benefits of viewing mobility data as a series of snapshots rather than a complete time series. It is our view that such data, when controlling for temporal stability, can provide a useful way to monitor the economic performance of retail centres over time, providing evidence that can inform policy decisions, and support interventions to both acute and longer-term issues in the retail sector.

Combining heterogeneous data sources for spatio-temporal mobility demand forecasting

There is a growing need to optimize mobility in medium to large-size cities. The use of a car for one-person trips is widely established as a common trend, which combined with the age of the vehicle fleet from many countries leads to high levels of pollution. Besides, the time wasted on commuting is more than significant for many people. Under these premises, it is paramount to understand the dynamics of mobility in every city. In this work, the problem of modeling and predicting transport demand in large cities with high spatio-temporal resolution is tackled. The city studied and its metropolitan area are subdivided into a new mobility mesh-grid, and transport demand is binned into short time intervals. The proposed Spatio-Temporal Mobility Demand Forecaster (ST-MDF) model is trained with real mobility demand data (such as taxi and bicycle rental), historical weather data (e.g., temperature, precipitation, and wind speed), and temporal information (e.g., weekday, time, and holiday) to predict mobility demand in every region of the mesh, for several forecast horizons.The experiments show that the ST-MDF model exhibits flexibility and robustness, while at the same time it outperforms the baseline models, such as a Long Short-Term Memory (LSTM) network, or the persistence and naive models.

Combining heterogeneous data sources for spatio-temporal mobility demand forecasting

Combining heterogeneous data sources for spatio-temporal mobility demand forecasting