Multivariate count time series segmentation with "sums and shares” and Poisson lognormal mixture models: a comparative study using pedestrian flows within a multimodal transport hub

This paper deals with a clustering approach based on mixture models to analyze multidimensional mobility count time-series data within a multimodal transport hub. These time series are very likely to evolve depending on various periods characterized by strikes, maintenance works, or health measures against the Covid19 pandemic. In addition, exogenous one-off factors, such as concerts and transport disruptions, can also impact mobility. Our approach flexibly detects time segments within which the very noisy count data is synthesized into regular spatio-temporal mobility profiles. At the upper level of the modeling, evolving mixing weights are designed to detect segments properly. At the lower level, segment-specific count regression models take into account correlations between series and overdispersion as well as the impact of exogenous factors. For this purpose, we set up and compare two promising strategies that can address this issue, namely the "sums and shares” and "Poisson log-normal” models. The proposed methodologies are applied to actual data collected within a multimodal transport hub in the Paris region. Ticketing logs and pedestrian counts provided by stereo cameras are considered here. Experiments are carried out to show the ability of the statistical models to highlight mobility patterns within the transport hub. One model is chosen based on its ability to detect the most continuous segments possible while fitting the count time series well. An in-depth analysis of the time segmentation, mobility patterns, and impact of exogenous factors obtained with the chosen model is finally performed. © 2023, Springer-Verlag GmbH Germany, part of Springer Nature.

Disruptions to in-person medical visits across the United States during the COVID-19 pandemic: evolving disparities by medical specialty and socio-economic status.

OBJECTIVES: This study aimed to investigate how people's health-seeking behaviors evolve in the COVID-19 pandemic by community and medical service category. STUDY DESIGN: This is a longitudinal study using mobility data from 19 million mobile devices of visits to all types of health facility locations for all US states. METHODS: We examine the variations in weekly in-person medical visits across county, neighborhood, and specialty levels. Different regression models are used for each level to investigate factors that influence the disparities in medical visits. County-level analysis explores associations between county medical visit patterns, political orientation, and COVID-19 infection rate. Neighborhood-level analysis focuses on neighborhood socio-economic compositions as potential determinants of medical visit levels. Specialty-level analysis compares the evolution of visit disruptions in different specialties. RESULTS: A more left-leaning political orientation and a higher local infection rate were associated with larger decreases in in-person medical visits, and these associations became stronger, moving from the initial period of stay-at-home orders into the post-lockdown period. Initial reactions were strongest for seniors and those of high socio-economic status, but this reversed in post-lockdown period where socio-economically disadvantaged communities stabilized at a lower level of medical visits. Neighborhoods with more female and young people exhibited larger decreases in in-person medical visits throughout the initial and post-lockdown periods. The evolution of disruptions diverges across medical specialties, from only short-term disruption in specialties such as dentistry to increasing disruption, as in cardiology. CONCLUSIONS: Given distinct patterns in visit between communities, medical service categories, and between different periods in the pandemic, policy makers, and providers should concentrate on monitoring patients in disrupted specialties who overlap with the at-risk contexts and socio-economic factors in future health emergencies.

Modeling COVID-19 with big mobility data: Surveillance and reaffirming the people in the data

To better understand the COVID-19 pandemic, public health researchers turned to "big mobility data”—location data collected from mobile devices by companies engaged in surveillance capitalism. Publishing formerly private big mobility datasets, firms trumpeted their efforts to "fight” COVID-19 and researchers highlighted the potential of big mobility data to improve infectious disease models tracking the pandemic. However, these collaborations are defined by asymmetries in information, access, and power. The release of data is characterized by a lack of obligation on the part of the data provider towards public health goals, particularly those committed to a community-based, participatory model. There is a lack of appropriate reciprocities between data company, data subject, researcher, and community. People are de-centered, surveillance is de-linked from action while the agendas of public health and surveillance capitalism grow closer. This article argues that the current use of big mobility data in the COVID-19 pandemic represents a poor approach with respect to community and person-centered frameworks. © The Author(s) 2023.

Joint Analysis of the Epidemic Evolution and Human Mobility During the First Wave of COVID-19 in Spain: Retrospective Study.

BACKGROUND: The initial wave of the COVID-19 pandemic placed a tremendous strain on health care systems worldwide. To mitigate the spread of the virus, many countries implemented stringent nonpharmaceutical interventions (NPIs), which significantly altered human behavior both before and after their enactment. Despite these efforts, a precise assessment of the impact and efficacy of these NPIs, as well as the extent of human behavioral changes, remained elusive. OBJECTIVE: In this study, we conducted a retrospective analysis of the initial wave of COVID-19 in Spain to better comprehend the influence of NPIs and their interaction with human behavior. Such investigations are vital for devising future mitigation strategies to combat COVID-19 and enhance epidemic preparedness more broadly. METHODS: We used a combination of national and regional retrospective analyses of pandemic incidence alongside large-scale mobility data to assess the impact and timing of government-implemented NPIs in combating COVID-19. Additionally, we compared these findings with a model-based inference of hospitalizations and fatalities. This model-based approach enabled us to construct counterfactual scenarios that gauged the consequences of delayed initiation of epidemic response measures. RESULTS: Our analysis demonstrated that the pre-national lockdown epidemic response, encompassing regional measures and heightened individual awareness, significantly contributed to reducing the disease burden in Spain. The mobility data indicated that people adjusted their behavior in response to the regional epidemiological situation before the nationwide lockdown was implemented. Counterfactual scenarios suggested that without this early epidemic response, there would have been an estimated 45,400 (95% CI 37,400-58,000) fatalities and 182,600 (95% CI 150,400-233,800) hospitalizations compared to the reported figures of 27,800 fatalities and 107,600 hospitalizations, respectively. CONCLUSIONS: Our findings underscore the significance of self-implemented prevention measures by the population and regional NPIs before the national lockdown in Spain. The study also emphasizes the necessity for prompt and precise data quantification prior to enacting enforced measures. This highlights the critical interplay between NPIs, epidemic progression, and human behavior. This interdependence presents a challenge in predicting the impact of NPIs before they are implemented.

Evaluating the effectiveness of lockdowns and restrictions during SARS-CoV-2 variant waves in the Canadian province of Nova Scotia.

Introduction: After the initial onset of the SARS-CoV-2 pandemic, the government of Canada and provincial health authorities imposed restrictive policies to limit virus transmission and mitigate disease burden. In this study, the pandemic implications in the Canadian province of Nova Scotia (NS) were evaluated as a function of the movement of people and governmental restrictions during successive SARS-CoV-2 variant waves (i.e., Alpha through Omicron). Methods: Publicly available data obtained from community mobility reports (Google), the Bank of Canada Stringency Index, the "COVID-19 Tracker" service, including cases, hospitalizations, deaths, and vaccines, population mobility trends, and governmental response data were used to relate the effectiveness of policies in controlling movement and containing multiple waves of SARS-CoV-2. Results: Our results indicate that the SARS-CoV-2 pandemic inflicted low burden in NS in the initial 2 years of the pandemic. In this period, we identified reduced mobility patterns in the population. We also observed a negative correlation between public transport (-0.78), workplace (-0.69), retail and recreation (-0.68) and governmental restrictions, indicating a tight governmental control of these movement patterns. During the initial 2 years, governmental restrictions were high and the movement of people low, characterizing a 'seek-and-destroy' approach. Following this phase, the highly transmissible Omicron (B.1.1.529) variant began circulating in NS at the end of the second year, leading to increased cases, hospitalizations, and deaths. During this Omicron period, unsustainable governmental restrictions and waning public adherence led to increased population mobility, despite increased transmissibility (26.41-fold increase) and lethality (9.62-fold increase) of the novel variant. Discussion: These findings suggest that the low initial burden caused by the SARS-CoV-2 pandemic was likely a result of enhanced restrictions to contain the movement of people and consequently, the spread of the disease. Easing public health restrictions (as measured by a decline in the BOC index) during periods of high transmissibility of circulating COVID-19 variants contributed to community spread, despite high levels of immunization in NS.

Party preferences, individual views and mobility during the pandemic

What is the association between partisanship, individual views and behaviours towards the pandemic? This research note explores this question empirically using two datasets collected before and during the Covid-19 pandemic: a daily survey covering nearly 100,000 individuals and county level mobility matched to UK 2019 general election results. At the individual level, our findings show that partisanship is strongly correlated with differences in both views and behaviours. Conservative voters were less likely to perceive Covid-19 as dangerous and less likely to stay home during the national lockdown. At the county level, the effect of the national lockdown on mobility was negative and statistically significant only in less Conservative counties. Thus, partisanship is associated with different individual views and behaviours towards the pandemic even when there is broad consensus among the main political parties and the government about the nature of a public health problem and the appropriate policy response. © 2023 The Authors. European Journal of Political Research published by John Wiley & Sons Ltd on behalf of European Consortium for Political Research.

Can psychological traits explain mobility behavior during the COVID-19 pandemic?

The current COVID-19 pandemic is a global, exogenous shock, impacting individuals' decision making and behavior allowing researchers to test theories of personality by exploring how traits, in conjunction with individual and societal differences, affect compliance and cooperation. Study 1 used Google mobility data and nation-level personality data from 31 countries, both before and after region-specific legislative interventions, finding that agreeable nations are most consistently compliant with mobility restrictions. Study 2 (N = 105,857) replicated these findings using individual-level data, showing that several personality traits predict sheltering in place behavior, but extraverts are especially likely to remain mobile. Overall, our analyses reveal robust relationships between traits and regulatory compliance (mobility behavior), both before and after region-specific legislative interventions, and the global declaration of the pandemic. Further, we find significant effects on reasons for leaving home, as well as age and gender differences, particularly relating to female agreeableness for previous and future social mobility behaviors. These sex differences, however, are only visible for those living in households with two or more people, suggesting that such findings may be driven by division of labor. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Aggregate Learning for Mixed Frequency Data

Large and acute economic shocks such as the 2007-2009 financial crisis and the current COVID-19 infections rapidly change the economic environment. In such a situation, real-time analysis of regional heterogeneity of economic conditions using alternative data is essential. We take advantage of spatio-temporal granularity of alternative data and propose a Mixed-Frequency Aggregate Learning (MF-AGL) model that predicts economic indicators for the smaller areas in real-time. We apply the model for the real-world problem;prediction of the number of job applicants which is closely related to the unemployment rates. We find that the proposed model predicts (i) the regional heterogeneity of the labor market condition and (ii) the rapidly changing economic status. The model can be applied to various tasks, especially economic analysis. © 2022 IEEE.

Disentangling the rhythms of human activity in the built environment for airborne transmission risk: An analysis of large-scale mobility data.

Background: Since the outset of the COVID-19 pandemic, substantial public attention has focused on the role of seasonality in impacting transmission. Misconceptions have relied on seasonal mediation of respiratory diseases driven solely by environmental variables. However, seasonality is expected to be driven by host social behavior, particularly in highly susceptible populations. A key gap in understanding the role of social behavior in respiratory disease seasonality is our incomplete understanding of the seasonality of indoor human activity. Methods: We leverage a novel data stream on human mobility to characterize activity in indoor versus outdoor environments in the United States. We use an observational mobile app-based location dataset encompassing over 5 million locations nationally. We classify locations as primarily indoor (e.g. stores, offices) or outdoor (e.g. playgrounds, farmers markets), disentangling location-specific visits into indoor and outdoor, to arrive at a fine-scale measure of indoor to outdoor human activity across time and space. Results: We find the proportion of indoor to outdoor activity during a baseline year is seasonal, peaking in winter months. The measure displays a latitudinal gradient with stronger seasonality at northern latitudes and an additional summer peak in southern latitudes. We statistically fit this baseline indoor-outdoor activity measure to inform the incorporation of this complex empirical pattern into infectious disease dynamic models. However, we find that the disruption of the COVID-19 pandemic caused these patterns to shift significantly from baseline and the empirical patterns are necessary to predict spatiotemporal heterogeneity in disease dynamics. Conclusions: Our work empirically characterizes, for the first time, the seasonality of human social behavior at a large scale with a high spatiotemporal resolutio and provides a parsimonious parameterization of seasonal behavior that can be included in infectious disease dynamics models. We provide critical evidence and methods necessary to inform the public health of seasonal and pandemic respiratory pathogens and improve our understanding of the relationship between the physical environment and infection risk in the context of global change. Funding: Research reported in this publication was supported by the National Institute of General Medical Sciences of the National Institutes of Health under award number R01GM123007.

Analysis for Data Mobility and Covid-19 Positive Rate with Multilayer Perceptron

COVID-19 has been affecting human mobility to avoid the risk of infection. Movement restriction was one of the government policies to reduce the rate of infection. However, the mobility was still occurred to be recorded during the policy. This action has led to the problem of the number of beds on hospital have to be prepared for the peak of infection. This study developed a model using Multilayer perceptron as a useful theorem in regression analysis to see the fitness approximation over this problem. Five layers neural networks combination have been used to see the performance of the model to reach the best fit of the model. The process of the study includes data acquisition of the influence of community mobility over the positive number of COVID-19, managed hyperparameters, and calculate the results of prediction in the form of the length of time the patient would be infected with COVID-19 from 2020 to 2021. This study found that the infection was happening mostly after 12 days of human mobility activity in public area such as ATM, market, park, and any public area recorded by Google mobility data. It was also showed the number of infections after 12 days in order to prepare the number of beds on hospital. Furthermore, this study found the best model with smallest loss value on 0.01452617616472448 with the gap number of infection from public area as much as 77 persons. © 2022 IEEE.

COVID-19, stigma, and habituation: evidence from mobility data.

BACKGROUND: The Japanese government has restricted people's going-out behavior by declaring a non-punitive state of emergency several times under COVID-19. This study aims to analyze how multiple policy interventions that impose non-legally binding restrictions on behavior associate with people's going-out. THEORY: This study models the stigma model of self-restraint behavior under the pandemic with habituation effects. The theoretical result indicates that the state of emergency's self-restraint effects weaken with the number of times. METHODS: The empirical analysis examines the impact of emergency declarations on going-out behavior using a prefecture-level daily panel dataset. The dataset includes Google's going-out behavior data, the Japanese government's policy interventions based on emergency declarations, and covariates that affect going-out behavior, such as weather and holidays. RESULTS: First, for multiple emergency declarations from the beginning of the pandemic to 2021, the negative association between emergency declarations and mobility was confirmed in a model that did not distinguish the number of emergency declarations. Second, in the model that considers the number of declarations, the negative association was found to decrease with the number of declarations. CONCLUSION: These empirical analyses are consistent with the results of theoretical analyses, which show that the negative association between people's going-out behavior and emergency declarations decreases in magnitude as the number of declarations increases.

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.

Spatio-temporal Graph Convolution BiLSTM for COVID-19 Community Mobility

Google COVID-19 community mobility data is important information to reflect the level of social activity and infer economic development. However, the data has complexity and non-linear spatiotemporal characteristics, and it is difficult for traditional prediction algorithms to fit such data with both temporal and spatial characteristics. To address such problems, this paper proposes a novel Spatio-temporal Graph Convolution Bidirectional Long Short Term Memory (STGC-BiLSTM) deep learning model, in which, the spatio-temporal graph convolution module can simultaneously mine the temporal and spatial features, and the prediction module encodes and regresses these features to complete the prediction of Google's mobile indices. The experiments show that the STGC-BiLSTM exhibits superior performance for both single-step and multi-step prediction for the four national datasets. Finally, ablation experiments are used to verify the effects of the spatio-temporal graph convolution module and regularization parameters to further illustrate the effectiveness of the model proposed in this paper. © 2022 IEEE.

Identifying the Socioeconomic, Demographic, and Political Determinants of Social Mobility and Their Effects on COVID-19 Cases and Deaths: Evidence From US Counties.

Background: The spread of COVID-19 at the local level is significantly impacted by population mobility. The U.S. has had extremely high per capita COVID-19 case and death rates. Efficient nonpharmaceutical interventions to control the spread of COVID-19 depend on our understanding of the determinants of public mobility. Objective: This study used publicly available Google data and machine learning to investigate population mobility across a sample of US counties. Statistical analysis was used to examine the socioeconomic, demographic, and political determinants of mobility and the corresponding patterns of per capita COVID-19 case and death rates. Methods: Daily Google population mobility data for 1085 US counties from March 1 to December 31, 2020, were clustered based on differences in mobility patterns using K-means clustering methods. Social mobility indicators (retail, grocery and pharmacy, workplace, and residence) were compared across clusters. Statistical differences in socioeconomic, demographic, and political variables between clusters were explored to identify determinants of mobility. Clusters were matched with daily per capita COVID-19 cases and deaths. Results: Our results grouped US counties into 4 Google mobility clusters. Clusters with more population mobility had a higher percentage of the population aged 65 years and over, a greater population share of Whites with less than high school and college education, a larger percentage of the population with less than a college education, a lower percentage of the population using public transit to work, and a smaller share of voters who voted for Clinton during the 2016 presidential election. Furthermore, clusters with greater population mobility experienced a sharp increase in per capita COVID-19 case and death rates from November to December 2020. Conclusions: Republican-leaning counties that are characterized by certain demographic characteristics had higher increases in social mobility and ultimately experienced a more significant incidence of COVID-19 during the latter part of 2020.

Spatiotemporal disease case prediction using contrastive predictive coding

Time series prediction models have played a vital role in guiding effective policymaking and response during the COVID-19 pandemic by predicting future cases and deaths at the country, state, and county levels. However, for emerging diseases, there is not sufficient historic data to fit traditional supervised prediction models. In addition, such models do not consider human mobility between regions. To mitigate the need for supervised models and to include human mobility data in the prediction, we propose Spatial Probabilistic Contrastive Predictive Coding (SP-CPC) which leverages Contrastive Predictive Coding (CPC), an unsupervised time-series representation learning approach. We augment CPC to incorporate a covariate mobility matrix into the loss function, representing the relative number of individuals traveling between each county on a given day. The proposal distribution learned by the algorithm is then sampled by the Metropolis-Hastings algorithm to give a final prediction of the number of COVID-19 cases. We find that the model applied to COVID-19 data can make accurate short-term predictions, more accurate than ARIMA and simple time-series extrapolation methods, one day into the future. However, for longer-term prediction windows of seven or more days into the future, we find that our predictions are not as competitive and require future research. © 2022 ACM.

The Apple Mobility Trends Data in Human Mobility Patterns during Restrictions and Prediction of COVID-19: A Systematic Review and Meta-Analysis.

The objective of this systematic review with PRISMA guidelines is to discover how population movement information has epidemiological implications for the spread of COVID-19. In November 2022, the Web of Science and Scopus databases were searched for relevant reports for the review. The inclusion criteria are: (1) the study uses data from Apple Mobility Trends Reports, (2) the context of the study is about COVID-19 mobility patterns, and (3) the report is published in a peer-reviewed venue in the form of an article or conference paper in English. The review included 35 studies in the period of 2020-2022. The main strategy used for data extraction in this review is a matrix proposal to present each study from a perspective of research objective and outcome, study context, country, time span, and conducted research method. We conclude by pointing out that these data are not often used in studies and it is better to study a single country instead of doing multiple-country research. We propose topic classifications for the context of the studies as transmission rate, transport policy, air quality, re-increased activities, economic activities, and financial markets.

To lockdown or not to lockdown: Analysis of the EU lockdown performance vs. COVID-19 outbreak.

The worldwide COVID-19 outbreak has dramatically called for appropriate responses from governments. Scientists estimated both the basic reproduction number and the lethality of the virus. The former one depends on several factors (environment and social behavior, virus characteristics, removal rate). In the absence of specific treatments (vaccine, drugs) for COVID-19 there was a limited capability to control the likelihood of transmission or the recovery rate. Therefore, to limit the expected exponential spread of the disease and to reduce its consequences, most national authorities have adopted containment strategies that are mostly focused on social distancing measures. In this context, we performed an analysis of the effects of government lockdown policies in 5 European Countries (France, Germany, Italy, Spain, United Kingdom). We used phone mobility data, published by Apple Inc. and Google, as an indirect measure of social distancing over time since we believe they represent a good approximation of actual changes in social behaviors. (i) The responsiveness of the governments in taking decisions. (ii) The coherence of the lockdown policy with changes in mobility data. (iii) The lockdown implementation performance in each country. (iv) The effects of social distancing on the epidemic evolution. These data were first analyzed in relation with the evolution of political recommendations and directives to both assess (i) responsiveness of governments in taking decisions and (ii) the implementation performance in each country. Subsequently, we used data made available by John Hopkins University in the attempt to compare changes in people behaviors with the evolution of COVID-19 epidemic (confirmed cases, new and cumulative) in each country in scope. Finally, we made an attempt to identify some key lockdown performance parameters in order to: (i) establish responsiveness, efficiency and effectiveness of the lockdown measures. (ii) model the latency occurring between the changes in social behaviors and the changes in growth rate of the disease.

A cross-country analysis of behavioral changes in response to COVID-19 social distancing policies

As the COVID-19 pandemic spreads globally, many countries now resort to social distancing policies. However, its effectiveness varies from country to country, and the factors responsible for such variations are not yet known. In this study, we conducted a cross-country analysis of behavioral changes that accompany social distancing policies using Google Community Mobility Reports and Apple’s Mobility Trend Reports. The results revealed that (1) the impact of social distancing policies on people’s behavior varies completely across countries and time periods, even with the same policy stringency, and (2) not only strong behavioral regulations but also income compensation, information provision, and vaccination policies affect behavior. Moreover, considering that long-term behavioral regulations seriously affect people’s physical and mental health and communities, policymakers must well combine direct regulations and indirect policies.

Automated Machine Learning for COVID-19 Forecasting

When responding to a pandemic situation, policy makers rely on forecasts of the spread. In the context of the current COVID-19 pandemic, various sophisticated epidemic and machine learning models have been used for forecasting. These models, however, rely on carefully selected architectures and detailed data that is often only available for specific regions. Automated machine learning (AutoML) addresses these challenges by allowing to automatically create forecasting pipelines in a data-driven manner, resulting in high-quality predictions. In this paper we study the role of open data along with AutoML systems in acquiring high-performance forecasting models for COVID-19. Here, we adapted the AutoML framework auto-sklearn to the time series forecasting task and introduced two variants for multi-step ahead COVID-19 forecasting which we refer to as (a) multi-output and (b) repeated single output forecasting. We studied the usefulness of anonymized open mobility data sets (place visits, and the use of different transportation modes) in addition to open mortality data. We evaluated three drift adaptation strategies to deal with concept drifts in data by (i) refitting our models on part of the data, (ii) the full data, or (iii) retraining the models completely. We compared the performance of our AutoML methods in terms of RMSE with five baselines on two testing periods (over 2020 and 2021). Our results show that combining mobility features and mortality data improves forecasting accuracy. Furthermore, we show that when faced with concept drifts, our method refitted on recent data using place visits mobility features outperforms all other approaches for 22 of the 26 countries considered in our study. Author

Multiwave COVID-19 Prediction from Social Awareness Using Web Search and Mobility Data

Recurring outbreaks of COVID-19 have posed enduring effects on global society, which calls for a predictor of pandemic waves using various data with early availability. Existing prediction models that forecast the first outbreak wave using mobility data may not be applicable to the multiwave prediction, because the evidence in the USA and Japan has shown that mobility patterns across different waves exhibit varying relationships with fluctuations in infection cases. Therefore, to predict the multiwave pandemic, we propose a Social Awareness-Based Graph Neural Network (SAB-GNN) that considers the decay of symptom-related web search frequency to capture the changes in public awareness across multiple waves. Our model combines GNN and LSTM to model the complex relationships among urban districts, inter-district mobility patterns, web search history, and future COVID-19 infections. We train our model to predict future pandemic outbreaks in the Tokyo area using its mobility and web search data from April 2020 to May 2021 across four pandemic waves collected by Yahoo Japan Corporation under strict privacy protection rules. Results demonstrate our model outperforms state-of-the-art baselines such as ST-GNN, MPNN, and GraphLSTM. Though our model is not computationally expensive (only 3 layers and 10 hidden neurons), the proposed model enables public agencies to anticipate and prepare for future pandemic outbreaks. © 2022 Owner/Author.