Predicting COVID-19 Spread from Large-Scale Mobility Data

To manage the COVID-19 epidemic effectively, decision-makers in public health need accurate forecasts of case numbers. A potential near real-time predictor of future case numbers is human mobility; however, research on the predictive power of mobility is lacking. To fill this gap, we introduce a novel model for epidemic forecasting based on mobility data, called mobility marked Hawkes model. The proposed model consists of three components: (1) A Hawkes process captures the transmission dynamics of infectious diseases. (2) A mark modulates the rate of infections, thus accounting for how the reproduction number R varies across space and time. The mark is modeled using a regularized Poisson regression based on mobility covariates. (3) A correction procedure incorporates new cases seeded by people traveling between regions. Our model was evaluated on the COVID-19 epidemic in Switzerland. Specifically, we used mobility data from February through April 2020, amounting to approximately 1.5 billion trips. Trip counts were derived from large-scale telecommunication data, i.e., cell phone pings from the Swisscom network, the largest telecommunication provider in Switzerland. We compared our model against various state-of-the-art baselines in terms of out-of-sample root mean squared error. We found that our model outperformed the baselines by 15.52%. The improvement was consistently achieved across different forecast horizons between 5 and 21 days. In addition, we assessed the predictive power of conventional point of interest data, confirming that telecommunication data is superior. To the best of our knowledge, our work is the first to predict the spread of COVID-19 from telecommunication data. Altogether, our work contributes to previous research by developing a scalable early warning system for decision-makers in public health tasked with controlling the spread of infectious diseases.

[1]  Joseph J. Sabia,et al.  WHEN DO SHELTER‐IN‐PLACE ORDERS FIGHT COVID‐19 BEST? POLICY HETEROGENEITY ACROSS STATES AND ADOPTION TIME , 2020, Economic inquiry.

[2]  Marcin Woźniak,et al.  Neural network powered COVID-19 spread forecasting model , 2020, Chaos, Solitons & Fractals.

[3]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[4]  Jessica T Davis,et al.  The effect of travel restrictions on the spread of the 2019 novel coronavirus (COVID-19) outbreak , 2020, Science.

[5]  Christos Nicolaides,et al.  Rationing social contact during the COVID-19 pandemic: Transmission risk and social benefits of US locations , 2020, Proceedings of the National Academy of Sciences.

[6]  Caroline O Buckee,et al.  The use of mobile phone data to inform analysis of COVID-19 pandemic epidemiology , 2020, Nature Communications.

[7]  N. Jewell,et al.  Mobility trends provide a leading indicator of changes in SARS-CoV-2 transmission , 2020, medRxiv.

[8]  J. Gaudart,et al.  Using Mobile Phone Data to Predict the Spatial Spread of Cholera , 2015, Scientific Reports.

[9]  J. Rocklöv,et al.  The reproductive number of COVID-19 is higher compared to SARS coronavirus , 2020, Journal of travel medicine.

[10]  A. Vespignani,et al.  Modelling the impact of testing, contact tracing and household quarantine on second waves of COVID-19 , 2020, Nature Human Behaviour.

[11]  Liangxu Wang,et al.  Prediction of the COVID-19 spread in African countries and implications for prevention and control: A case study in South Africa, Egypt, Algeria, Nigeria, Senegal and Kenya , 2020, Science of The Total Environment.

[12]  When Do Shelter‐in‐Place Orders Fight COVID‐19 Best? Policy Heterogeneity Across States and Adoption Time[Link] , 2020, Economic inquiry.

[13]  Xiao Zhou,et al.  Cultural investment and urban socio-economic development: a geosocial network approach , 2017, Royal Society Open Science.

[14]  H. Friedl Econometric Analysis of Count Data , 2002 .

[15]  Royce J. Wilson,et al.  Google COVID-19 Community Mobility Reports: Anonymization Process Description (version 1.0) , 2020, ArXiv.

[16]  A. Hawkes,et al.  A cluster process representation of a self-exciting process , 1974, Journal of Applied Probability.

[17]  Stefan Feuerriegel,et al.  Monitoring the COVID-19 epidemic with nationwide telecommunication data , 2021, Proceedings of the National Academy of Sciences.

[18]  R. Schlickeiser,et al.  A Gaussian model for the time development of the Sars-Cov-2 corona pandemic disease. Predictions for Germany made on March 30, 2020 , 2020, medRxiv.

[19]  Ahmed M. Alaa,et al.  When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes , 2020, NeurIPS.

[20]  Christos Nicolaides,et al.  Rationing social contact during the COVID-19 pandemic: Transmission risk and social benefits of US locations , 2020, Proceedings of the National Academy of Sciences.

[21]  Luyang Liu,et al.  Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks , 2020, ArXiv.

[23]  A. L. Schmidt,et al.  Economic and social consequences of human mobility restrictions under COVID-19 , 2020, Proceedings of the National Academy of Sciences.

[24]  Swapnil Mishra,et al.  SIR-Hawkes: Linking Epidemic Models and Hawkes Processes to Model Diffusions in Finite Populations , 2017, WWW.

[25]  F. Dominici,et al.  Aggregated mobility data could help fight COVID-19 , 2020, Science.

[26]  Stefan Feuerriegel,et al.  Early Detection of User Exits from Clickstream Data: A Markov Modulated Marked Point Process Model , 2020, WWW.

[27]  Ruiyun Li,et al.  Substantial undocumented infection facilitates the rapid dissemination of novel coronavirus (SARS-CoV-2) , 2020, Science.

[28]  N. Banholzer,et al.  Estimating the effects of non-pharmaceutical interventions on the number of new infections with COVID-19 during the first epidemic wave , 2021, medRxiv.

[29]  X. Liu,et al.  Hawkes process modeling of COVID-19 with mobility leading indicators and spatial covariates , 2020, International Journal of Forecasting.

[30]  Swapnil Mishra,et al.  SIR-Hawkes: Linking Epidemic Models and Hawkes Processes to Model Diffusions in Finite Populations , 2017, WWW.

[31]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[32]  Dirk Brockmann,et al.  COVID-19 lockdown induces disease-mitigating structural changes in mobility networks , 2020, Proceedings of the National Academy of Sciences.

[33]  W. O. Kermack,et al.  A contribution to the mathematical theory of epidemics , 1927 .

[34]  Hannah R. Meredith,et al.  The Incubation Period of Coronavirus Disease 2019 (COVID-19) From Publicly Reported Confirmed Cases: Estimation and Application , 2020, Annals of Internal Medicine.

[35]  S. Pei,et al.  Differential Effects of Intervention Timing on COVID-19 Spread in the United States , 2020, Science Advances.

[36]  Elisa Franco,et al.  The challenges of modeling and forecasting the spread of COVID-19 , 2020, Proceedings of the National Academy of Sciences.

[37]  Lei Zhang,et al.  Mobile device data reveal the dynamics in a positive relationship between human mobility and COVID-19 infections , 2020, Proceedings of the National Academy of Sciences.

[38]  Xing Xie,et al.  Predicting the Spatio-Temporal Evolution of Chronic Diseases in Population with Human Mobility Data , 2018, IJCAI.

[39]  Marc Hoffmann,et al.  A recursive point process model for infectious diseases , 2017, Annals of the Institute of Statistical Mathematics.

[40]  Raja Jurdak,et al.  Modeling stochastic processes in disease spread across a heterogeneous social system , 2018, Proceedings of the National Academy of Sciences.

[41]  Jure Leskovec,et al.  Mobility network models of COVID-19 explain inequities and inform reopening , 2020, Nature.

[42]  Bahman Rostami Tabar,et al.  Forecasting COVID-19 daily cases using phone call data , 2020, Applied Soft Computing.

[43]  Junhyung Park,et al.  Real-time predictions of the 2018–2019 Ebola virus disease outbreak in the Democratic Republic of the Congo using Hawkes point process models , 2019, Epidemics.

[44]  Benito E. Flores,et al.  The utilization of the Wilcoxon test to compare forecasting methods: A note , 1989 .

[45]  Martin B. Short,et al.  Analyzing the World-Wide Impact of Public Health Interventions on the Transmission Dynamics of COVID-19 , 2020, 2004.01714.

[46]  Yosihiko Ogata,et al.  Statistical Models for Earthquake Occurrences and Residual Analysis for Point Processes , 1988 .

[47]  C. Pang,et al.  Estimation of the time-varying reproduction number of COVID-19 outbreak in China , 2020, International Journal of Hygiene and Environmental Health.

[48]  Marco De Nadai,et al.  Mobile phone data for informing public health actions across the COVID-19 pandemic life cycle , 2020, Science Advances.

[49]  A. Desai,et al.  Stopping the Spread of COVID-19. , 2020, JAMA.

[50]  Stefan Feuerriegel,et al.  Leveraging Mobility Flows from Location Technology Platforms to Test Crime Pattern Theory in Large Cities , 2020, ICWSM.

[51]  N. Banholzer,et al.  Impact of non-pharmaceutical interventions on documented cases of COVID-19 , 2020, medRxiv.

[52]  C. Whittaker,et al.  Report 9: Impact of non-pharmaceutical interventions (NPIs) to reduce COVID19 mortality and healthcare demand , 2020 .