Search

The spread of COVID-19 revealed that transmission risk patterns are not homogenous across different cities and communities, and various heterogeneous features can influence the spread trajectories. Hence, for predictive pandemic monitoring, it is essential to explore latent heterogeneous features in cities and communities that distinguish their specific pandemic spread trajectories. To this end, this study creates a network embedding model capturing cross-county visitation networks, as well as heterogeneous features related to population activities, human mobility, socio-demographic features, disease attribute, and social interaction to uncover clusters of counties in the United States based on their pandemic spread transmission trajectories. We collected and computed location intelligence features from 2,787 counties from March 3 to June 29, 2020 (initial wave). Second, we constructed a human visitation network, which incorporated county features as node attributes, and visits between counties as network edges. Our attributed network embeddings approach integrates both typological characteristics of the cross-county visitation network, as well as heterogeneous features. We conducted clustering analysis on the attributed network embeddings to reveal four archetypes of spread risk trajectories corresponding to four clusters of counties. Subsequently, we identified four features—population density, GDP, minority status, and POI visits—as important features underlying the distinctive transmission risk patterns among the archetypes. The attributed network embedding approach and the findings identify and explain the non-homogenous pandemic risk trajectories across counties for predictive pandemic monitoring. The study also contributes to data-driven and deep learning-based approaches for pandemic analytics to complement the standard epidemiological models for policy analysis in pandemics.

Supplemental Material for Spatial model for predictive recovery monitoring based on hazard, built environment, and population features and their spillover effects by Flavia Ioana Patrascu and Ali Mostafavi in Environment and Planning B: Urban Analytics and City Science.

Effective climate mitigation strategies in cities rely on understanding and mapping urban carbon footprints. One significant source of carbon is a product of lifestyle choices and travel behaviors of urban residents. Although previous research addressed consumption- and home-related footprints, activity-based footprints of urban dwellers have garnered less attention. This study relies on deidentified human trajectory data from 5 million devices to examine the activity-based carbon footprint in Harris County, Texas. Our analysis of the heterogeneity of footprints based on places visited and distance traveled reveals significant inequality: 10% of users account for 88% of visitation-based footprints and 71% of distance-traveled footprints. We also identify the influence of income on activity-based carbon footprint gap of users related to their travel behavior and lifestyle choices, with high-income users having larger footprints due to lifestyle choices, while low- to medium-income users' footprints are due to limited access. Our findings underscore the need for urban design adjustments to reduce carbon-intensive behaviors and to improve facility distribution. Our conclusions highlight the importance of addressing urban design parameters that shape carbon-intensive lifestyle choices and facility distribution, decisions which have implications for developing interventions to reduce carbon footprints caused by human activities., Comment: 15 pages, 6 figures, 1 table

Generating realistic human flows across regions is essential for our understanding of urban structures and population activity patterns, enabling important applications in the fields of urban planning and management. However, a notable shortcoming of most existing mobility generation methodologies is neglect of prediction fairness, which can result in underestimation of mobility flows across regions with vulnerable population groups, potentially resulting in inequitable resource distribution and infrastructure development. To overcome this limitation, our study presents a novel, fairness-aware deep learning model, FairMobi-Net, for inter-region human flow prediction. The FairMobi-Net model uniquely incorporates fairness loss into the loss function and employs a hybrid approach, merging binary classification and numerical regression techniques for human flow prediction. We validate the FairMobi-Net model using comprehensive human mobility datasets from four U.S. cities, predicting human flow at the census-tract level. Our findings reveal that the FairMobi-Net model outperforms state-of-the-art models (such as the DeepGravity model) in producing more accurate and equitable human flow predictions across a variety of region pairs, regardless of regional income differences. The model maintains a high degree of accuracy consistently across diverse regions, addressing the previous fairness concern. Further analysis of feature importance elucidates the impact of physical distances and road network structures on human flows across regions. With fairness as its touchstone, the model and results provide researchers and practitioners across the fields of urban sciences, transportation engineering, and computing with an effective tool for accurate generation of human mobility flows across regions.

This study investigates the interplay among social demographics, built environment characteristics, and environmental hazard exposure features in determining community level cancer prevalence. Utilizing data from five Metropolitan Statistical Areas in the United States: Chicago, Dallas, Houston, Los Angeles, and New York, the study implemented an XGBoost machine learning model to predict the extent of cancer prevalence and evaluate the importance of different features. Our model demonstrates reliable performance, with results indicating that age, minority status, and population density are among the most influential factors in cancer prevalence. We further explore urban development and design strategies that could mitigate cancer prevalence, focusing on green space, developed areas, and total emissions. Through a series of experimental evaluations based on causal inference, the results show that increasing green space and reducing developed areas and total emissions could alleviate cancer prevalence. The study and findings contribute to a better understanding of the interplay among urban features and community health and also show the value of interpretable machine learning models for integrated urban design to promote public health. The findings also provide actionable insights for urban planning and design, emphasizing the need for a multifaceted approach to addressing urban health disparities through integrated urban design strategies.

Evaluating human exposure to environmental hazards is crucial for identifying susceptible communities and devising targeted health policies. Standard environmental hazard exposure assessment methods have been primarily based on place of residence, an approach which neglect individuals hazard exposures due to the daily life activities and mobility outside home neighborhood. To address this limitation, this study proposes a novel mobility-based index for hazard exposure evaluation. Using large-scale and fine-grained human mobility data, we quantify the extent of population dwell time in high-environmental-hazard places in 239 U.S. counties for three major environmental hazards: air pollution, heat, and toxic sites. Subsequently we explore the extent to which human mobility extends the reach of environmental hazards and also lead to the emergence of latent exposure for populations living outside high hazard areas with relatively considerable dwell time in high hazard areas. The findings help quantify environmental hazard exposure more reliably, considering the role of human mobility and activities. The interplay of spatial clustering in high-hazard regions and human movement trends creates environmental hazard traps intensifying exposure. Poor and ethnic minority residents disproportionately face multiple types of environmental hazards, aggravating potential health impacts. This data-driven evidence supports the severity of these injustices. We also studied latent exposure arising from visits outside residents' home areas, revealing millions population having 5% to10% of daily activities occur in high-exposure zones. Despite living in perceived safe areas, human mobility could expose millions of residents to different hazards. These findings provide crucial insights for targeted policies to mitigate these severe environmental injustices

Global sea-level rise causes increasing threats of coastal flood and subsequent pollutant dispersion. However, there are still few studies on the disparity arising from such threats and the extent to which different communities could be exposed to flood-induced pollution dispersion from toxic sites under future sea level rise. To address this gap, this study selects Texas (a U.S. state with a large number of toxic sites and significant flood hazards) as the study area and investigates impacts of flood-induced pollutant dispersion on different communities under current (2018) and future (2050) flood hazard scenarios.The results show, currently, north coastline in Texas bears higher threats and vulnerable communities (i.e., low income, minorities and unemployed) are disproportionally exposed to these threats. In addition, the future sea-level rise and the exacerbated flood hazards will put additional threats on more (about 10%) Texas residents, among which vulnerable communities will still be disproportionately exposed to the increased threats. Our study reveals the facts that potential coastal pollutant dispersion will further aggravate the environmental injustice issues at the intersection of toxic sites and flood hazards for vulnerable populations and exacerbate risk inequalities. Given the dire impacts of flood-induced pollution dispersion on public health, the findings have important implications for specific actions from the policy makers to mitigate the inequitable risks.

The objectives of this study are: (1) to specify evacuation return and home-switch stability as two critical milestones of short-term recovery during and in the aftermath of disasters; and (2) to understand the disparities among subpopulations in the duration of these critical recovery milestones. Using privacy-preserving fine-resolution location-based data, we examine evacuation and home move-out rates in Harris County, Texas in the context of the 2017 Hurricane Harvey. For each of the two critical recovery milestones, the results reveal the areas with short- and long-return durations and enable evaluating disparities in evacuation return and home-switch stability patterns. In fact, a shorter duration of critical recovery milestone indicators in flooded areas is not necessarily a positive indication. Shorter evacuation return could be due to barriers to evacuation and shorter home move-out rate return for lower-income residents is associated with living in rental homes. In addition, skewed and non-uniform recovery patterns for both the evacuation return and home-switch stability were observed in all subpopulation groups. All return patterns show a two-phase return progress pattern. The findings could inform disaster managers and public officials to perform recovery monitoring and resource allocation in a more proactive, data-driven, and equitable manner.

Hurricanes are one of the most catastrophic natural hazards faced by residents of the United States. Improving the public’s hurricane preparedness is essential to reduce the impact and disruption of hurricanes on households. Inherent in traditional methods for quantifying and monitoring hurricane preparedness are significant lags, which hinder effective monitoring of residents’ preparedness in advance of an impending hurricane. This study establishes a methodological framework to quantify the extent, timing, and spatial variation of hurricane preparedness at the census block group level using high-resolution location intelligence data. Anonymized cell phone data on visits to points-of-interest for each census block group in Harris County before 2017 Hurricane Harvey were used to examine residents’ hurricane preparedness. Four categories of points-of-interest, grocery stores, gas stations, pharmacies and home improvement stores, were identified as they have close relationship with hurricane preparedness, and the daily number of visits from each CBG to these four categories of POIs were calculated during preparation period. Two metrics, extent of preparedness and proactivity, were calculated based on the daily visit percentage change compared to the baseline period. The results show that peak visits to pharmacies often occurred in the early stage of preparation, whereas the peak of visits to gas stations happened closer to hurricane landfall. The spatial and temporal patterns of visits to grocery stores and home improvement stores were quite similar. However, correlation analysis demonstrates that extent of preparedness and proactivity are independent of each other. Combined with synchronous evacuation data, CBGs in Harris County were divided into four clusters in terms of extent of preparedness and evacuation rate. The clusters with low preparedness and low evacuation rate were identified as hotspots of vulnerability for shelter-in-place households that would need urgent attention during response. Hence, the research findings provide a new data-driven approach to quantify and monitor the extent, timing, and spatial variations of hurricane preparedness. Accordingly, the study advances data-driven understanding of human protective actions during disasters. The study outcomes also provide emergency response managers and public officials with novel data-driven insights to more proactively monitor residents’ disaster preparedness, making it possible to identify under-prepared areas and better allocate resources in a timely manner.

Natural hazards cause disruptions in access to critical facilities, such as grocery stores, impeding residents ability to prepare for and cope with hardships during the disaster and recovery; however, disrupted access to critical facilities is not equal for all residents of a community. In this study, we examine disparate access to grocery stores in the context of the 2017 Hurricane Harvey in Harris County, Texas. We utilized high-resolution location-based datasets in implementing spatial network analysis and dynamic clustering techniques to uncover the overall disparate access to grocery stores for socially vulnerable populations during different phases of the disaster. Three access indicators are examined using network-centric measures: number of unique stores visited, average trip time to stores, and average distance to stores. These access indicators help us capture three dimensions of access: redundancy, rapidity, and proximity. The findings show the insufficiency of focusing merely on the distributional factors, such as location in a food desert and number of facilities, to capture the disparities in access, especially during the preparation and impact/short-term recovery periods. Furthermore, the characterization of access by considering combinations of access indicators reveals that flooding disproportionally affects socially vulnerable populations. High-income areas have better access during preparation as they are able to visit a greater number of stores and commute farther distances to obtain supplies. The conclusions of this study have important implications for urban development (facility distribution), emergency management, and resource allocation by identifying areas most vulnerable to disproportionate access impacts using more equity-focused and data-driven approaches., Comment: 22 pages, 7 figures

Despite recent advances in achieving fair representations and predictions through regularization, adversarial debiasing, and contrastive learning in graph neural networks (GNNs), the working mechanism (i.e., message passing) behind GNNs inducing unfairness issue remains unknown. In this work, we theoretically and experimentally demonstrate that representative aggregation in message-passing schemes accumulates bias in node representation due to topology bias induced by graph topology. Thus, a \textsf{F}air \textsf{M}essage \textsf{P}assing (FMP) scheme is proposed to aggregate useful information from neighbors but minimize the effect of topology bias in a unified framework considering graph smoothness and fairness objectives. The proposed FMP is effective, transparent, and compatible with back-propagation training. An acceleration approach on gradient calculation is also adopted to improve algorithm efficiency. Experiments on node classification tasks demonstrate that the proposed FMP outperforms the state-of-the-art baselines in effectively and efficiently mitigating bias on three real-world datasets.

Urban flooding disrupts traffic networks, affecting the mobility and disrupting access of residents. Since flooding events are predicted to increase due to climate change, and given the criticality of traffic networks, understanding the flood-caused disruption of traffic networks is critical to improve emergency planning and city resilience. Leveraging high-resolution traffic network data from a major flood event and advanced high-order network analysis, this study reveals characteristics of the anatomy of perturbed traffic networks. First, the findings show network-wide persistent increased travel times could last for weeks after flood water has receded, even after modest flood failure. During disaster event period, modest flooding of 1.3% road segments caused 8% temporal expansion of the entire traffic network. The results also show distant trips would experience a greater percentage increase in travel time. Also, the extent of increase in travel time does not decay with distance from inundated areas, suggesting that the spatial reach of flood impacts extends beyond flooded areas. Departing from the existing literature, which primarily informs about physical vulnerability in road networks to floods, the findings of this study provide important novel understanding of floods impacts on the functioning of traffic networks in terms of travel time and traffic network geometry. The persistent travel time increase in the entire network can translate to significant social and economic impacts in terms of user costs, additional CO2 emissions, and lost productivity. Due to the importance of traffic networks functioning for the operation of cities, the results have significance implications for city managers, transportation planners, and emergency managers to deal with the impacts of urban flooding., Comment: 14 Pages, 7 figures

In studying resilience in temporal human networks, relying solely on global network measures would be inadequate; latent sub-structural network mechanisms need to be examined to determine the extent of impact and recovery of these networks during perturbations, such as urban flooding. In this study, we utilized high-resolution aggregated location-based disaster related data to construct temporal human mobility networks. Using the constructed temporal network models, we examined characteristics such as motif distribution, motif persistence and temporal stability, and motif attributes to reveal latent sub-structural mechanisms related to the resilience of human mobility networks during disaster-induced perturbations. The results show that urban flood impacts persists in human mobility networks at the sub-structure level for several weeks. The impact extent and recovery duration is heterogeneous across different network types. Also, perturbation impacts persist at the sub-structure level while global topological network properties might indicate the network has recovered. The findings highlight the importance of examining the microstructures and their dynamic processes and attributes in understanding the resilience of temporal human mobility networks (and other temporal networks), it is essential to examine the microstructures and their perturbation impacts and recovery. The findings can also provide disaster managers, public officials, and transportation planners with insights to better evaluate impacts and to monitor recovery in affected communities based on the patterns of impact and recovery in human mobility networks at both sub-structure and global-network levels.

Ambient exposure to fine particulate matters of diameters smaller than 2.5{\mu}m (PM2.5) has been identified as one critical cause for respiratory disease. Disparities in exposure to PM2.5 among income groups at individual residences are known to exist and are easy to calculate. Existing approaches for exposure assessment, however, do not capture the exposure implied by the dynamic mobility of city dwellers that accounts for a large proportion of the exposure outside homes. To overcome the challenge of gauging the exposure to PM2.5 for city dwellers, we analyzed billions of anonymized and privacy-enhanced location-based data generated by mobile phone users in Harris County, Texas, to characterize the mobility patterns of the populations and associated exposure. We introduce the metric for exposure extent based on the time people spent at places with the air pollutant and examine the disparities in mobility-based exposure across income groups. Our results show that PM2.5 emissions disproportionately expose low-income populations due to their mobility activities. People with higher-than-average income are exposed to lower levels of PM2.5 emissions. These disparities in mobility-based exposure are the result of frequent visits of low-income people to the industrial sectors of urban areas with high PM2.5 emissions, and the larger mobility scale of these people for life needs. The results inform about environmental justice and public health strategies, not only to reduce the overall PM2.5 exposure but also to mitigate the disproportional impacts on low-income populations. The findings also suggest that an integration of extensive fine-scale population mobility and pollution emissions data can unveil new insights into inequality in air pollution exposures at the urban scale., Comment: 13 pages, 5 figures

Human mobility networks can reveal insights into resilience phenomena, such as population response to, impacts on, and recovery from crises. The majority of human mobility network resilience characterizations, however, focus mainly on macroscopic network properties; little is known about variation in measured resilience characteristics (i.e., the extent of impact and recovery duration) across macroscopic, substructure (motif), and microscopic mobility scales. To address this gap, in this study, we examine the human mobility network in eight parishes in Louisiana (USA) impacted by the 2021 Hurricane Ida. We constructed human mobility networks using location-based data and examined three sets of measures: (1) macroscopic measures, such as network density, giant component size, and modularity; (2) substructure measures, such motif distribution; and (3) microscopic mobility measures, such as the radius of gyration and average travel distance. To determine the extent of impact and duration of recovery, for each measure, we established the baseline values and examined the fluctuation of measures during the perturbation caused by Hurricane Ida. The results reveal the variation of impact extent and recovery duration obtained from different sets of measures at different scales. Macroscopic measures, such as giant components, tend to recover more quickly than substructure and microscopic measures. In fact, microscopic measures tend to recover more slowly than measures in other scales. These findings suggest that resilience characteristics in human mobility networks are scale-variant, and thus, a single measure at a particular scale may not be representative of the perturbation impacts and recovery duration in the network as a whole. These results spotlight the need to use measures at different scales to properly characterize resilience in human mobility networks., Comment: 15 pages, 13 figures. arXiv admin note: text overlap with arXiv:2204.09915

We present a latent characteristic in socio-spatial networks, hazard-exposure heterophily, to capture the extent to which populations with similar hazard exposure could assist each other through social ties. Heterophily is the tendency of unlike individuals to form social ties. Conversely, populations in spatial areas with significant hazard exposure similarity, homophily, would lack sufficient resourcefulness to aid each other to lessen the impact of hazards. In the context of the Houston metropolitan area, we use Meta's Social Connectedness data to construct a socio-spatial network in juxtaposition with flood exposure data from National Flood Hazard Layer to analyze flood hazard exposure of spatial areas. The results reveal the extent and spatial variation of hazard-exposure heterophily in the study area. Notably, the results show that lower-income areas have lower hazard-exposure heterophily possibly caused by income segregation and the tendency of affordable housing development to be located in flood zones. Less resourceful social ties due to high hazard-exposure homophily may inhibit low-income areas from better coping with hazard impacts and could contribute to their slower recovery. Overall, the results underscore the significance of characterizing hazard-exposure heterophily in socio-spatial networks to reveal community vulnerability and resilience to hazards., Comment: 14 pages, 6 figures

The return of normalcy to the population's lifestyle is a critical recovery milestone in the aftermath of disasters, and delayed lifestyle recovery could lead to significant well-being impacts. Lifestyle recovery captures the collective effects of population activities and the restoration of infrastructure and business services. This study uses a novel approach to leverage privacy-enhanced location intelligence data to characterize distinctive lifestyle patterns and to unveil recovery trajectories after a disaster in the context of 2017 Hurricane Harvey in Harris County, Texas. The analysis integrates multiple data sources to record the number of visits from home census block groups (CBGs) to different points of interest during the baseline period and disruptive period. First, primary clustering using k-means characterized four distinct essential and non-essential lifestyle patterns. Then, secondary clustering characterized the impact of the hurricane into three recovery trajectories based on the severity of maximum disruption and duration of recovery. The results reveal multiple recovery trajectories and durations within each lifestyle cluster, which imply differential recovery rates among similar lifestyle and demographic groups. The findings offer a twofold theoretical significance: (1) lifestyle recovery is a critical milestone that needs to be examined, quantified, and monitored in the aftermath of disasters; (2) the spatial structures of cities formed by human mobility and distribution of facilities and extends the spatial reach of flood impacts on population lifestyles. The analysis and findings also provide novel data-driven insights for public official and emergency managers to examine, measure, and monitor a critical milestone in community recovery trajectory based on the return of lifestyles to normalcy., Comment: 26 pages, 6 figures, and 4 tables

Despite the criticality of dialysis facilities, limited knowledge exists regarding the extent and inequality of disrupted access caused by weather events. This study uses mobility data in the context of the 2017 Hurricane Harvey in Harris County to examine the impact of flooding on access to dialysis centers. We examined access dimensions using multiple static and dynamic metrics. By analyzing fluctuations in dynamic metrics during the flood event, we derived spatiotemporal patterns of access disruptions and inequity in mobility from CBGs to dialysis centers. The results show that: (1) the extent of dependence of CBGs on dialysis centers varies; (2) flooding significantly reduces access redundancy and frequency of dialysis center visits; access disruptions persist for more than one month after the flood event; (3) CBGs with a greater minority percentage and lower household income were more likely to experience more extensive access disruptions; (4) high-income CBGs more quickly revert to their pre-disaster levels; (5) larger dialysis centers located in non-flooded areas are critical to absorbing the unmet demand from disrupted facilities; these larger facilities contribute to the absorptive capacity of the network of dialysis facilities in the region.

Supplemental material for Unveiling spatial patterns of disaster impacts and recovery using credit card transaction fluctuations by Faxi Yuan, Amir Esmalian, Bora Oztekin and Ali Mostafavi in Environment and Planning B: Urban Analytics and City Science

We examined the raw daily visits through (1) hikes before the hurricane landfall, (2) maximum drops after the hurricane landfall, (3) and peaks during the system recovery. The exact values are summarized below.

The objective of this study is to predict road flooding risks based on topographic, hydrologic, and temporal precipitation features using machine learning models. Predictive flood monitoring of road network flooding status plays an essential role in community hazard mitigation, preparedness, and response activities. Existing studies related to the estimation of road inundations either lack observed road inundation data for model validations or focus mainly on road inundation exposure assessment based on flood maps. This study addresses this limitation by using crowdsourced and fine-grained traffic data as an indicator of road inundation, and topographic, hydrologic, and temporal precipitation features as predictor variables. Two tree-based machine learning models (random forest and AdaBoost) were then tested and trained for predicting road inundations in the contexts of 2017 Hurricane Harvey and 2019 Tropical Storm Imelda in Harris County, Texas. The findings from Hurricane Harvey indicate that precipitation is the most important feature for predicting road inundation susceptibility, and that topographic features are more essential than hydrologic features for predicting road inundations in both storm cases. The random forest and AdaBoost models had relatively high AUC scores (0.860 and 0.810 for Harvey respectively and 0.790 and 0.720 for Imelda respectively) with the random forest model performing better in both cases. The random forest model showed stable performance for Harvey, while varying significantly for Imelda. This study advances the emerging field of smart flood resilience in terms of predictive flood risk mapping at the road level. For example, such models could help impacted communities and emergency management agencies develop better preparedness and response strategies with improved situational awareness of road inundation likelihood as an extreme weather event unfolds., Comment: 17 pages, 7 figures

The objective of this study is to examine spatial patterns of impacts and recovery of communities based on variances in credit card transactions. Such variances could capture the collective effects of household impacts, disrupted accesses, and business closures, and thus provide an integrative measure for examining disaster impacts and community recovery in disasters. Existing studies depend mainly on survey and sociodemographic data for disaster impacts and recovery effort evaluations, although such data has limitations, including large data collection efforts and delayed timeliness results. In addition, there are very few studies have concentrated on spatial patterns and disparities of disaster impacts and short-term recovery of communities, although such investigation can enhance situational awareness during disasters and support the identification of disparate spatial patterns of disaster impacts and recovery in the impacted regions. This study examines credit card transaction data Harris County (Texas, USA) during Hurricane Harvey in 2017 to explore spatial patterns of disaster impacts and recovery during from the perspective of community residents and businesses at ZIP code and county scales, respectively, and to further investigate their spatial disparities across ZIP codes. The results indicate that individuals in ZIP codes with populations of higher income experienced more severe disaster impact and recovered more quickly than those located in lower-income ZIP codes for most business sectors. Our findings not only enhance the understanding of spatial patterns and disparities in disaster impacts and recovery for better community resilience assessment, but also could benefit emergency managers, city planners, and public officials in harnessing population activity data, using credit card transactions as a proxy for activity, to improve situational awareness and resource allocation., Comment: 31 pages, 20 figures

Listed below are the North American Industry Classification System (NAICS) codes of the filtered data analysis. There was a total of 148 NAICS categories, 103 were deemed irrelevant to the purposes of the research study and filtered out. The remaining 45 NAICS merged into 16 categories and four main groups.

Additional file 1. The results and visualization of statistical tests, metric values and cross-correlation analyses for the top 20 counties.

We examined the effect of social distancing on changes in visits to urban hotspot points of interest. In a pandemic situation, urban hotspots could be potential superspreader areas as visits to urban hotspots can increase the risk of contact and transmission of a disease among a population. We mapped census-block-group to point-of-interest (POI) movement networks in sixteen cities in the United States. We adopted a modified coarse-grain approach to examine patterns of visits to POIs among hotspots and non-hotspots from January to May 2020. Also, we conducted chi-square tests to identify POIs with significant flux-in changes during the analysis period. The results showed disparate patterns across cities in terms of reduction in hotspot POI visitors. Sixteen cities were divided into two categories using a time series clustering method. In one category, which includes the cities of, San Francisco, Seattle and Chicago, we observed a considerable decrease in hotspot POI visitors, while in another category, including the cites of, Austin, Houston and San Diego, the visitors to hotspots did not greatly decrease. While all the cities exhibited overall decreased visitors to POIs, one category maintained the proportion of visitors to hotspot POIs. The proportion of visitors to some POIs (e.g. restaurants) remained stable during the social distancing period, while some POIs had an increased proportion of visitors (e.g. grocery stores). We also identified POIs with significant flux-in changes, indicating that related businesses were greatly affected by social distancing. The study was limited to 16 metropolitan cities in the United States. The proposed methodology could be applied to digital trace data in other cities and countries to study the patterns of movements to POIs during the COVID-19 pandemic.

In this paper, we propose a deep learning model to forecast the range of increase in COVID-19 infected cases in future days and we present a novel method to compute equidimensional representations of multivariate time series and multivariate spatial time series data. Using this novel method, the proposed model can both take in a large number of heterogeneous features, such as census data, intra-county mobility, inter-county mobility, social distancing data, past growth of infection, among others, and learn complex interactions between these features. Using data collected from various sources, we estimate the range of increase in infected cases seven days into the future for all U.S. counties. In addition, we use the model to identify the most influential features for prediction of the growth of infection. We also analyze pairs of features and estimate the amount of observed second-order interaction between them. Experiments show that the proposed model obtains satisfactory predictive performance and fairly interpretable feature analysis results; hence, the proposed model could complement the standard epidemiological models for national-level surveillance of pandemics, such as COVID-19. The results and findings obtained from the deep learning model could potentially inform policymakers and researchers in devising effective mitigation and response strategies. To fast-track further development and experimentation, the code used to implement the proposed model has been made fully open source., Comment: 16 pages, 7 figures, 2 tables

This study aims to quantify community resilience based on fluctuations in the visits to various Point-of-Interest (POIs) locations. Visit to POIs is an essential indicator of human activities and captures the combined effects of perturbations in people lifestyles, built environment conditions, and businesses status. The study utilized digital trace data of unique visits to POIs in the context of the 2017 Hurricane Harvey in Houston (Texas, USA) to examine spatial patterns of impact and total recovery effort and utilized these measures to quantify community resilience. The results showed that certain POI categories such as building materials and supplies dealers and grocery stores were the most resilient elements of the community compared to the other POI categories. On the other hand, categories such as medical facilities and entertainment were found to have lower resilience values. This result suggests that these categories were either not essential for community recovery or that the community was not able to access these services at normal levels immediately after the hurricane. In addition, the spatial analyses revealed that many areas in the community with lower levels of resilience experienced extensive flooding. However, some areas with low resilience were not flooded extensively, suggesting that spatial reach of the impacts goes beyond flooded areas. The results demonstrate the importance of the approach proposed in our study. While this study focused on Houston and only analysed one natural hazard, the approach can be applied to other communities and disaster contexts. Applying this approach, emergency managers and public officials can efficiently monitor the patterns of disaster impacts and recovery across different spatial areas and POI categories and also identify POI categories and areas of their community that need to be prioritized for resource allocation., Comment: 23 pages, 19 figures

The objective of this study is to propose and test an adaptive reinforcement learning model that can learn the patterns of human mobility in a normal context and simulate the mobility during perturbations caused by crises, such as flooding, wildfire, and hurricanes. Understanding and predicting human mobility patterns, such as destination and trajectory selection, can inform emerging congestion and road closures raised by disruptions in emergencies. Data related to human movement trajectories are scarce, especially in the context of emergencies, which places a limitation on applications of existing urban mobility models learned from empirical data. Models with the capability of learning the mobility patterns from data generated in normal situations and which can adapt to emergency situations are needed to inform emergency response and urban resilience assessments. To address this gap, this study creates and tests an adaptive reinforcement learning model that can predict the destinations of movements, estimate the trajectory for each origin and destination pair, and examine the impact of perturbations on humans' decisions related to destinations and movement trajectories. The application of the proposed model is shown in the context of Houston and the flooding scenario caused by Hurricane Harvey in August 2017. The results show that the model can achieve more than 76\% precision and recall. The results also show that the model could predict traffic patterns and congestion resulting from to urban flooding. The outcomes of the analysis demonstrate the capabilities of the model for analyzing urban mobility during crises, which can inform the public and decision-makers about the response strategies and resilience planning to reduce the impacts of crises on urban mobility., Comment: 20 pages, 7 figures

Social cohesion is an important determinant of community well-being, especially in times of distress such as disasters. This study investigates the phenomena of emergent social cohesion, which is characterized by abrupt, temporary and extensive social ties with the goal of sharing and receiving information regarding a particular event influencing a community. In the context of disasters, emergent social cohesion, enabled by social media usage, could play a significant role in improving the ability of communities to cope with disruptions in recent disasters. In this study, we employed a network reticulation framework to examine the underlying mechanisms influencing emergent social cohesion on social media while communities cope with disaster-induced disruptions. We analysed neighbourhood-tagged social media data (social media data whose users are tagged by neighbourhoods) in Houston, TX, USA, during Hurricane Harvey to characterize four modalities of network reticulation (i.e. enactment, activation, reticulation and performance) giving rise to emergent social cohesion. Our results show that, unlike regular social cohesion, communication history and physical proximity do not significantly affect emergent social cohesion. The results also indicate that weak social ties play an important role in bridging different social network communities, and hence reinforce emergent social cohesion. The findings can inform public officials, emergency managers and decision-makers regarding the important role of neighbourhood-tagged social media, as a new form of community infrastructure, for improving the ability of communities to cope with disaster disruptions through enhanced emergent social cohesion.

In the last decade, the Indiana Department of Transportation (INDOT) has experienced an increase in their construction projects (e.g., INDOT’s construction spending was $789 million in 2006 and increased to $1,081.4 million in 2010); while the level of its in-house inspection staff and resources has either remained the same or declined. There are different strategies to deal with the need for construction inspection resources and they may include strategies such as outsourcing the inspection of construction activities and using quality control and quality assurance certification programs to reduce the need for in-process inspection. One strategy that could reduce the inspection workload is prioritizing construction activities for inspection. However, reducing the number of inspections also has risks, such as functional failures and reduced design life, if defects are not identified before the work is covered. Thus, available inspection resources should be allocated to the activities with significant risk consequences due to reduced inspection. The objective of this study was to: (1) evaluate the current inspection practices of INDOT and (2) develop a risk-based inspection protocol to facilitate efficient allocation of available inspection resources to minimize the risks associated with reduced inspection. First, the current inspection practices implemented by INDOT, other State Departments of Transportation, and consulting firms were identified and compared. The comparison between the inspection practices revealed that there is consistency between INDOT’s and consultants’ and other State Departments of Transportation’s inspection practices. To develop a risk-based inspection protocol, first, the risk consequences associated with reduced inspection were identified for different transportation construction activities, based on the data collected from 20 site visits to INDOT projects. These risk consequences include short and long-term functional failures, reduced design life, reduced safety, and increased maintenance cost. Based on data collected from 23 state Departments of Transportation, 58 engineers and inspectors from the Indiana Department of Transportation (INDOT), and 20 inspection consultants in the Midwest, the subjective perceived probabilities associated with the occurrence of each risk consequence were encoded using fuzzy analysis. Using these subjective probabilities, the risk impacts due to reduced inspection were derived. The construction activities subsequently were prioritized based on the risk impacts associated with reduced inspection into five priority levels: high, medium-high, medium, medium-low, and low. The greater the risk impacts were due to reduced inspection, the higher the priority would be for inspection of that activity. The study also included identification of value added of inspection and the critical items to be watched for different activities related to transportation construction. Deliverables of this project include: (1) an inspection protocol, (2) an inspection staffing guide and (3) a list of pay items whose documentation requirements need to be modified to enhance the documentation process. The inspection protocol created in this study could assist INDOT in efficient allocation of inspection resources to construction activities.