Human Mobility Data Research Articles

Editor’s note: Special issue on Deep Modeling and Understanding of Big Human Mobility Data

Editor’s note: Special issue on Deep Modeling and Understanding of Big Human Mobility Data

Unveiling realistic mobility patterns with home–origin–destination data aggregation

The availability of increasingly abundant mobility data in recent years has opened up new avenues for researchers to unravel human mobility patterns. Data aggregation methods have been introduced to gain a quantitative understanding of collective individual movements using these data. Nevertheless, the widely adopted origin–destination (OD) aggregation method for human mobility data lacks an essential piece of information: home location, which plays a vital role in characterizing individual movement patterns. In this study, we propose a novel data aggregation approach called home–origin–destination (HOD) with the aim of improving the accuracy of human mobility estimation. We compare the performance of various data aggregation methods for estimating population distribution. Our experimental results reveal more realistic mobility patterns when incorporating estimated home information, where individuals move out in the morning and return home before midnight. To further evaluate the effectiveness of the HOD approach, we conduct an entropy analysis to measure the unpredictability of human mobility. The HOD results exhibit lower entropy values than those in the other two cases, OD and home–destination (HD). These findings underscore the importance of incorporating home information in understanding and modeling human mobility. By leveraging the HOD data aggregation method, we can achieve more accurate population distribution estimates and capture the inherent dynamics of human movement

Inference of dynamic hypergraph representations in temporal interaction data.

A range of systems across the social and natural sciences generate data sets consisting of interactions between two distinct categories of items at various instances in time. Online shopping, for example, generates purchasing events of the form (user, product, time of purchase), and mutualistic interactions in plant-pollinator systems generate pollination events of the form (insect, plant, time of pollination). These data sets can be meaningfully modeled as temporal hypergraph snapshots in which multiple items within one category (i.e., online shoppers) share a hyperedge if they interacted with a common item in the other category (i.e., purchased the same product) within a given time window, allowing for the application of hypergraph analysis techniques. However, it is often unclear how to choose the number and duration of these temporal snapshots, which have a strong influence on the final hypergraph representations. Here we propose a principled nonparametric solution to this problem by extracting temporal hypergraph snapshots that optimally capture structural regularities in temporal event data according to the minimum description length principle. We demonstrate our methods on real and synthetic data sets, finding that they can recover planted artificial hypergraph structure in the presence of considerable noise and reveal meaningful activity fluctuations in human mobility data.

The spatial dimensions of cultural consumption: how distance influences consumption levels in a spatial setting

AbstractCultural consumption has increasingly acquired a fundamental role in urban policy frameworks, thanks to its empirically proven positive effects on individuals and on societies. Although several theoretical and empirical contributions have examined the main socio-economic determinants that explain cultural consumption; its spatial dimensions remain significantly under-considered and require further analysis. The aim of this paper is to analyse the factors influencing cultural consumption with a focus on spatial distance and spatial dependence. Specifically, it seeks to inquire into the extent to which spatial distance between consumers and cultural institutions plays a role in neighbourhood’s levels of cultural consumption. To do this, human mobility data towards cultural institutions are used as a proxy for individual cultural consumption levels in six French cities. Results show that spatial proximity with the cultural offer matters in explaining consumption patterns, but that traditional socioeconomic determinants have a higher explanatory value.

Mobility census for monitoring rapid urban development.

Monitoring urban structure and development requires high-quality data at high spatio-temporal resolution. While traditional censuses have provided foundational insights into demographic and socio-economic aspects of urban life, their pace may not always align with the pace of urban development. To complement these traditional methods, we explore the potential of analysing alternative big-data sources, such as human mobility data. However, these often noisy and unstructured big data pose new challenges. Here, we propose a method to extract meaningful explanatory variables and classifications from such data. Using movement data from Beijing, which are produced as a by-product of mobile communication, we show that meaningful features can be extracted, revealing, for example, the emergence and absorption of subcentres. This method allows the analysis of urban dynamics at a high-spatial resolution (here 500 m) and near real-time frequency, and high computational efficiency, which is especially suitable for tracing event-driven mobility changes and their impact on urban structures.

Using human mobility data to detect evacuation patterns in hurricane Ian

ABSTRACT Hurricane Ian in 2022 was a destructive category 4 Atlantic hurricane striking the state of Florida, which caused hundreds of deaths and injuries, catastrophic property damage, and an economic loss of more than $112 billion. Before the landfall of Ian in Florida, the state government issued evacuation orders in high-risk zones to reduce casualties and injuries. However, there is limited data available to monitor the actual evacuation patterns and compliance with the evacuation orders at a large geographic scale. This study utilizes human mobility data (i.e. SafeGraph Weekly Pattern) to analyse the spatial patterns of evacuation during Hurricane Ian in 2022. The objectives of the study include three key aspects: 1) proposing an analytical workflow that utilizes human mobility data to detect mobility patterns in disasters and other emergency events; 2) identifying significant evacuation patterns, and 3) revealing the spatial variations in the compliance with evacuation orders in the affected areas. Using data science and spatial analysis techniques, this study detected notable changes in population movements, both within Florida and nationwide, which are potentially linked to the hurricane-induced population evacuation. The distance decay pattern of population flows from Florida demonstrates a propensity for individuals to relocate to nearby areas during the hurricane. Furthermore, the increase in population outflows from the impacted areas suggests the effectiveness of mandatory evacuation orders. A more pronounced increase in outflows from designated mandatory evacuation areas points to the public awareness of the evacuation zone designation. This study provides large-scale, fine-resolution analysis of evacuation behaviours in natural disasters which cannot be easily detected in traditional data sources. The analytical workflows provide actionable tools for government agencies and policymakers to evaluate the effectiveness of evacuation orders and improve evacuation plans in future disasters.

Community resilience to wildfires: A network analysis approach by utilizing human mobility data

Disasters have been a long-standing concern to societies at large. With growing attention being paid to resilient communities, such concern has been brought to the forefront of resilience studies. However, there is a wide variety of definitions with respect to resilience, and a precise definition has yet to emerge. Moreover, much work to date has often focused only on the immediate response to an event, thus investigating the resilience of an area over a prolonged period of time has remained largely unexplored. To overcome these issues, we propose a novel framework utilizing network analysis and concepts from disaster science (e.g., the resilience triangle) to quantify the long-term impacts of wildfires. Taking the Mendocino Complex and Camp wildfires - the largest and most deadly wildfires in California to date, respectively - as case studies, we capture the robustness and vulnerability of communities based on human mobility data from 2018 to 2019. The results show that demographic and socioeconomic characteristics alone only partially capture community resilience, however, by leveraging human mobility data and network analysis techniques, we can enhance our understanding of resilience over space and time, providing a new lens to study disasters and their long-term impacts on society.

Urban Region Embedding via Multi-View Contrastive Prediction

Recently, learning urban region representations utilizing multi-modal data (information views) has become increasingly popular, for deep understanding of the distributions of various socioeconomic features in cities. However, previous methods usually blend multi-view information in a posteriors stage, falling short in learning coherent and consistent representations across different views. In this paper, we form a new pipeline to learn consistent representations across varying views, and propose the multi-view Contrastive Prediction model for urban Region embedding (ReCP), which leverages the multiple information views from point-of-interest (POI) and human mobility data. Specifically, ReCP comprises two major modules, namely an intra-view learning module utilizing contrastive learning and feature reconstruction to capture the unique information from each single view, and inter-view learning module that perceives the consistency between the two views using a contrastive prediction learning scheme. We conduct thorough experiments on two downstream tasks to assess the proposed model, i.e., land use clustering and region popularity prediction. The experimental results demonstrate that our model outperforms state-of-the-art baseline methods significantly in urban region representation learning.

Assessing the 2023 Canadian wildfire smoke impact in Northeastern US: Air quality, exposure and environmental justice

The Canadian wildfires in June 2023 significantly impacted the northeastern United States, particularly in terms of worsened air pollution and environmental justice concerns. While advancements have been made in low-cost sensor deployments and satellite observations of atmospheric composition, integrating dynamic human mobility with wildfire PM2.5 exposure to fully understand the environmental justice implications remains underinvestigated. This study aims to enhance the accuracy of estimating ground-level fine particulate matter (PM2.5) concentrations by fusing chemical transport model outputs with empirical observations, estimating exposures using human mobility data, and evaluating the impact of environmental justice. Employing a novel data fusion technique, the study combines the Weather Research and Forecasting model with Chemistry (WRF-Chem) outputs and surface PM2.5 measurements, providing a more accurate estimation of PM2.5 distribution. The study addresses the gap in traditional exposure assessments by incorporating human mobility data and further investigates the spatial correlation of PM2.5 levels with various environmental and demographic factors from the US Environmental Protection Agency (EPA) Environmental Justice Screening and Mapping Tool (EJScreen). Results reveal that despite reduced mobility during high PM2.5 levels from wildfire smoke, exposure for both residents and individuals on the move remains high. Regions already burdened with high environmental pollution levels face amplified PM2.5 effects from wildfire smoke. Furthermore, we observed mixed correlations between PM2.5 concentrations and various demographic and socioeconomic factors, indicating complex exposure patterns across communities. Urban areas, in particular, experience persistent high exposure, while significant correlations in rural areas with EJScreen factors highlight the unique vulnerabilities of these populations to smoke exposure. These results advocate for a comprehensive approach to environmental health that leverages advanced models, integrates human mobility data, and addresses socio-demographic disparities, contributing to the development of equitable strategies against the growing threat of wildfires.

Correcting missingness in passively-generated mobile data with Multi-Task Gaussian Processes

The prevalence of mobile devices and the ubiquity of network connectivity have generated a massive amount of temporally- and spatially-stamped data. A key characteristic of this mobile data is the prevalence of sparsity—for every recorded user, there is a significant amount of missing data. Sparsity leads to bias in the inferred mobility patterns and thus, correcting bias by imputing the missing data potentially creates opportunities for directly using the corrected mobile trajectory data for large-scale simulations in various applications. We propose a multi-task Gaussian process regression model to correct missingness in mobile data. Gaussian processes (GPs) allow for flexible modeling of diverse (i.e., non-linear, locally periodic) data patterns and quantify prediction uncertainty in an interpretable manner. We develop a methodological framework for applying GPs to mobile data. In doing so, we consider the correlations between users’ coordinates (latitudes and longitudes) through multi-task learning and adjust for individual-level differences in data characteristics through parameter initialization and optimization. We introduce and demonstrate the use of smooth (i.e., rational quadratic) and periodic kernels in modeling human mobility data. Relatedly, we analyze our model’s parameters and imputation accuracy with respect to different types of trips (e.g. slower vs faster trips). We also demonstrate our model’s performance in two experiments with real app-based data, in which it outperforms alternative imputation methods. Our implementation is open-source at https://github.com/ekinugurel/GPSImpute.

Leveraging big data for outdoor recreation management: A case study from the York river in Virginia

Outdoor recreation is important for improving quality of life, well-being, and local economies, but quantifying its value without direct monetary transactions can be challenging. This study explores combining non-market valuation techniques with emerging big data sources to estimate the value of recreation for the York River and surrounding parks in Virginia. By applying the travel cost method to anonymous human mobility data, we gain deeper insights into the significance of recreational experiences for visitors and the local economy. Results of a zero-inflated Negative Binomial model show a mean consumer surplus value of $26.91 per trip, totaling $15.5 million across nearly 600,000 trips observed in 2022. Further, weekends, holidays, and the summer and fall months are found to be peak visitation times, whereas those with young children and who are Hispanic or over 64 years old are less likely to visit. These findings shed light on various factors influencing visitation patterns and recreation values, including temporal effects and socio-demographics, revealing disparities that warrant targeted efforts for inclusivity and accessibility. Policymakers can use these insights to make informed and sustainable choices in outdoor recreation management, fostering the preservation of natural resources for the benefit of both visitors and the environment.

COVID-19 control measures unexpectedly increased the duration of stay at High Speed Rail stations during the first community outbreak in Taiwan

During the COVID-19 pandemic, Taiwan has implemented strict border controls and community spread prevention measures. As part of these efforts, the government also implemented measures for public transportation. In Taiwan, there are two primary public transportation systems: Taiwan Railways (TR) is commonly utilized for local travel, while the Taiwan High-Speed Rail (THSR) is preferred for business trips and long-distance journeys due to its higher speed. In this study, we examined the impact of these disease prevention measures on the number of passengers and duration of stay in two major public transportation systems during the first community outbreak from April 29th to May 29th, 2021. Using data from a local telecommunications company, our study observed an expected decrease in the number of passengers after the cancellation of non-reserved seats at both TR and THSR stations across all 19 cities in the main island of Taiwan. Surprisingly, however, the duration of stay in some of the cities unexpectedly increased, especially at THSR stations. This unanticipated rise in the duration of stay has the potential to elevate contact probability among passengers and, consequently, the transmission rate. Our analysis shows that intervention policies may result in unforeseen outcomes, highlighting the crucial role of human mobility data as a real-time reference for policymakers. It enables them to monitor the impact of disease prevention measures and facilitates informed, data-driven decision-making.

Human mobility data demonstrates increase in park visitation since start of COVID-19 pandemic in Buffalo, New York

BackgroundThe COVID-19 pandemic highlighted the importance of urban parks to provide safe places to visit and recreate. Recent research has suggested that park visitation over this time may not have occurred equitably, which may exacerbate existing health disparities. However, usual methods of estimating park visitation are labor intensive, requiring better solutions.. The objective of this study was to assess how park visitation changed in Buffalo, New York after the start of the COVID-19 pandemic utilizing human mobility data. MethodsMonthly mobile phone location data from January 2018 through October of 2021 from residents of Buffalo were analyzed to estimate total park visits for each census tract. A generalized linear mixed effect model was utilized to examine if selected factors affected park visitation. Factors examined included demographic, health, park, and crime data at the census tract level. ResultsAcross 587,487 park visits that were captured in the 79 census tracts, park visitation increased by 25% since March 2020. In our regression model, having cancer and currently smoking had negative effects on park visitation. The start of the COVID-19 pandemic positively affected park visitation. Season (of the year), was the other statistically significant variable that affected park visitation. ConclusionsAnonymous mobile phone data demonstrated that park visitation has increased by 25% since the beginning of the pandemic when we looked at census tract level data. While some data limitations must be addressed, mobile phone data is a novel method that can be used to understand behavioral and public health trends.

The 15-minute city quantified using human mobility data.

Amid rising congestion and transport emissions, policymakers are embracing the '15-minute city' model, which envisions neighbourhoods where basic needs can be met within a short walk from home. Prior research has primarily examined amenity access without exploring its relationship to behaviour. We introduce a measure of local trip behaviour using GPS data from 40 million US mobile devices, defining '15-minute usage' as the proportion of consumption-related trips made within a 15-minute walk from home. Our findings show that the median resident makes only 14% of daily consumption trips locally. Differences in access to local amenities can explain 84% and 74% of the variation in 15-minute usage across and within urban areas, respectively. Historical data from New York zoning policies suggest a causal relationship between local access and 15-minute usage. However, we find a trade-off: increased local usage correlates with higher experienced segregation for low-income residents, signalling potential socio-economic challenges in achieving local living.

Using Spatial Scan Statistics and Geographic Information Systems to Detect Monthly Human Mobility Clusters and Analyze Cluster Area Characteristics.

This study evaluated the detection of monthly human mobility clusters and characteristics of cluster areas before the coronavirus disease 2019 (COVID-19) outbreak using spatial epidemiological methods, namely, spatial scan statistics and geographic information systems (GIS). The research area covers approximately 10.3 km2, with a population of about 350,000 people. Analysis was conducted using open data, with the exception of one dataset. Human mobility and population data were used on a 1-km mesh scale, and business location data were used to examine the area characteristics. Data from January to December 2019 were utilized to detect human mobility clusters before the COVID-19 pandemic. Spatial scan statistics were performed using SaTScan to calculate relative risk (RR). The detected clusters and other data were visualized in QGIS to explore the features of the cluster areas. Spatial scan statistics identified 33 clusters. The detailed analysis focused on clusters with an RR exceeding 1.5. Meshes with an RR over 1.5 included one with clusters for 1 year which is identified in all months of the year, one with clusters for 9 months, three with clusters for 6 months, three with clusters for 3 months, and four with clusters for 1 month. September had the highest number of clusters (eight), followed by April and November (seven each). The remaining months had five or six clusters. Characteristically, the cluster areas included the vicinity of railway stations, densely populated business areas, ball game fields, and large-scale construction sites. Statistical analysis of human mobility clusters using open data and open-source tools is crucial for the advancement of evidence-based policymaking based on scientific facts, not only for novel infectious diseases but also for existing ones, such as influenza.

Income estimation based on human mobility patterns and machine learning models

Sustainable and inclusive urban development requires a thorough understanding of income distribution and poverty. Recent related research has extensively explored the use of automatically generated sensor data to proxy economic activities. Notably, human mobility patterns have been found to exhibit strong associations with socioeconomic attributes and great potential for income estimation. However, the representation of complex human mobility patterns and their effectiveness in income estimation needs further investigation. To address this, we propose three representations of human mobility: mobility indicators, activity footprints, and travel graphs. These representations feed into various models, including XGBoost, a traditional machine learning model, a convolutional neural network (CNN), and a time-series graph neural network (GCRN). By leveraging public transit data from Shenzhen, our study demonstrates that graph-based representations and deep learning models outperform other approaches in income estimation. They excel in minimising information loss and handling complex data structures. Spatial contextual attributes, such as transport accessibility, are the most influential factors, while indicators related to activity extent, temporal rhythm, and intensity contribute comparatively less. In summary, this study highlights the potential of cutting-edge artificial intelligence tools and emerging human mobility data as an alternative approach to estimating income distribution and addressing poverty-related concerns.

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.

Analysis of Performance Improvements and Bias Associated with the Use of Human Mobility Data in COVID-19 Case Prediction Models

The COVID-19 pandemic has mainstreamed human mobility data into the public domain, with research focused on understanding the impact of mobility reduction policies as well as on regional COVID-19 case prediction models. Nevertheless, current research on COVID-19 case prediction tends to focus on performance improvements, masking relevant insights about when mobility data does not help, and more importantly, why, so that it can adequately inform local decision making. In this article, we carry out a systematic analysis to reveal the conditions under which human mobility data provides (or not) an enhancement over individual regional COVID-19 case prediction models that do not use mobility as a source of information. Our analysis—focused on U.S. county-based COVID-19 case prediction models—shows that (1) at most, 60% of counties improve their performance after adding mobility data; (2) the performance improvements are modest, with median correlation improvements of approximately 0.13; (3) improvements were lower for counties with higher Black, Hispanic, and other non-White populations as well as low-income and rural populations, pointing to potential bias in the mobility data negatively impacting predictive performance; and (4) different mobility datasets, predictive models, and training approaches bring about diverse performance improvements.

Using cellular device location data to estimate visitation to public lands: Comparing device location data to U.S. National Park Service's visitor use statistics.

Understanding human use of public lands is essential for management of natural and cultural resources. However, compiling consistently reliable visitation data across large spatial and temporal scales and across different land managing entities is challenging. Cellular device locations have been demonstrated as a source to map human activity patterns and may offer a viable solution to overcome some of the challenges that traditional on-the-ground visitation counts face on public lands. Yet, large-scale applicability of human mobility data derived from cell phone device locations for estimating visitation counts to public lands remains unclear. This study aims to address this knowledge gap by examining the efficacy and limitations of using commercially available cellular data to estimate visitation to public lands. We used the United States' National Park Service's (NPS) 2018 and 2019 monthly visitor use counts as a ground-truth and developed visitation models using cellular device location-derived monthly visitor counts as a predictor variable. Other covariates, including park unit type, porousness, and park setting (i.e., urban vs. non-urban, iconic vs. local), were included in the model to examine the impact of park attributes on the relationship between NPS and cell phone-derived counts. We applied Pearson's correlation and generalized linear mixed model with adjustment of month and accounting for potential clustering by the individual park units to evaluate the reliability of using cell data to estimate visitation counts. Of the 38 parks in our study, 20 parks had a correlation of greater than 0.8 between monthly NPS and cell data counts and 8 parks had a correlation of less than 0.5. Regression modeling showed that the cell data could explain a great amount of the variability (conditional R-squared = 0.96) of NPS counts. However, these relationships varied across parks, with better associations generally observed for iconic parks. While our study increased our confidence in using cell phone data to estimate visitation, we also became aware of some of the limitations and challenges which we present in the Discussion.

Graph-Based Approach for Personalized Travel Recommendations

Abstract In the evolving domain of urban mobility systems, the integration of technology with user-centric strategies is pivotal. This research stands on the foundational concept of Mobility-as-a-Service, a user-centric intelligent mobility management distribution system that seeks to prioritize human needs over mere technological infrastructure. The study delves deep into the wealth of data available through mobile sensing technologies, highlighting the unprecedented understanding it offers into human mobility patterns, thus facilitating personalized route recommendations. The literature categorizes the study area into three interlinked categories: point-of-interest (POI) recommendation, travel planning, and trajectory modelling. In a significant stride, this research introduces a comprehensive understanding of hu-man mobility data and proposes a novel framework designed to tender personalized recommendations to travel planner users. The innovative framework employs a graph-based approach rooted in the Sussex-Huawei Locomotion dataset, leveraging an adaptation of Bellman-Ford’s algorithm. This modification considers factors such as perceived fatigue, frequency of trips to specific locations, and proximity to POIs, promising a path routed in past user experiences and preferences.