Hi there, this is Charlotte:) I just started my first term this fall as a Master in Environmental Studies (MES) student at the University of Waterloo.
My current research project focuses on the evolution of human mobility patterns through different stages of the COVID-19 pandemic, especially how the local mobility patterns have reacted to the different lockdown policies in Ontario. Attached below is a brief introduction about my project and my lab.
Discovering the Evolution of Human Mobility Patterns through Different Phases of the COVID-19 Response in Ontario
As the topic suggests, in this project, I aim to evaluate the non-pharmaceutical interventions from the local and the provincial governments in Ontario by leveraging the power of human mobility data and deep learning models.
Several previous studies on COVID-19 response (Pepe et al. 2020 & Kang et al. 2020) have all shown that human mobility data is the key to measuring the impacts of non-pharmaceutical interventions during the pandemic. While dozens of mobility datasets addressing this problem have been created for China, Italy, United State and many other regions of the world (Gao et al. 2020, Zhou et al. 2020, Pepe et al. 2020 & Kang et al. 2020), there is still no such work done in Canada. And if we specifically look at the COVID-19 intervention timeline in Ontario (Figure 1), we can easily find that the past two year of pandemic is crammed of turning points representing all kind of policy changes ranging from service closure, to social distancing, to travel restrictions. At the same time, we have saw recurring anti-lockdown protests with no social distance maintained in many cities of Ontario and constantly heard voice against all the policies and especially the stay-at-home order from the local people. Knowing the gap between policy and implementation, we demand a quantitative method to better assess the real effects of those non-pharmaceutical policies to answer the questions:
In Ontario, how effective have those lockdown policies been? Do we still need them if they have failed to reduce people’s moving activities but instead exuberated the case by urging more people to gather on the streets? How would the travelling decision of individuals make a difference to their community or the city/province overall?
To put this research in a broader context and to echo the urgent call for action of the Sustainable Development Goals (SDGs) from the United Nations, I will give my two cents on how my research help achieve the following three SDGs:
-
Good Health & Well-Being
According to the United Nations, the COVID-19 pandemic has intensively reserved progress in physical and mental health status and even shortened life expectancy. I believe one of the common motivations lying behind all the pandemic response studies is that we hope to devise effective strategies to fight the pandemic and bring back health to people.
-
Decent Work & Economic Growth
Do you know that the current pandemic has led to the loss of the equivalent of 255 million jobs? By providing data insights, this study can help to form evidence-based safety strategies to control the transmission and restore the labor market to its level before the pandemic.
-
Sustainable Cities & Communities
One of the goals of this research is to help form more effective pandemic safety strategies in cities of Ontario and thus enable people to live in an inclusive, safe, resilient and sustainable community.
Last year right after I graduated from my underdrate school the University of Toronto, I started to do researching at one of the labs at UW, the GeoSensing and Data Intelligence Lab, and that's how I got attracted by geospatial data science and ended up doing my masters here at UW working with Professor Jonathan Li. Recently I have done a project using geographically weighted regression models to investigate the correlation between COVID growing trends and economic factors in Canada. Now my team and I are starting a new project to investigate how the human mobilities have varied during the pandemic in the data collection stage. The major challenge is that we don't have open source mobility data sets for Canada, that have a high gragulatity in terms of location. For my research paper project, I will be narrowing down the scope to Ontario and focusing more on the impact of local COVID policies.
A breif about my supervisor, Dr. Jonathan Li. He is a professor of geospatial data science at the Department of Geography and Environmental Management at UW and also the founder of our lab. His recent research projects focus on the development of innovative AI-based algorithms, methods, and software tools for handling large-volume geospatial data; the development of sensor-driven mobile mapping solutions to modeling of roadway environments; the development of remote sensing approaches to understanding urban growth and examining the environmental consequences of urban expansion. Profiles of all my teammates at the lab are accessible here: https://uwaterloo.ca/geospatial-sensing/people-profiles
Gao, S., Rao, J., Kang, Y., Liang, Y., Kruse, J., Doepfer, D., ... & Yandell, B. S. (2020). Mobile phone location data reveal the effect and geographic variation of social distancing on the spread of the COVID-19 epidemic. arXiv preprint arXiv:2004.11430.
Kang Y, Gao S, Liang Y, Li M, Rao J, Kruse J. Multiscale dynamic human mobility flow dataset in the U.S. during the COVID-19 epidemic. Sci Data. 2020 Nov 12;7(1):390. doi: 10.1038/s41597-020-00734-5. PMID: 33184280; PMCID: PMC7661515.
Luca, M., Barlacchi, G., Lepri, B., & Pappalardo, L. (2020). Deep learning for human mobility: a survey on data and models. arXiv preprint arXiv:2012.02825.
Pepe, E., Bajardi, P., Gauvin, L. et al. COVID-19 outbreak response, a dataset to assess mobility changes in Italy following national lockdown. Sci Data 7, 230 (2020). https://doi.org/10.1038/s41597-020-00575-2
Zhou, Y., Xu, R., Hu, D., Yue, Y., Li, Q., & Xia, J. (2020). Effects of human mobility restrictions on the spread of COVID-19 in Shenzhen, China: a modelling study using mobile phone data. The Lancet Digital Health, 2(8), e417-e424. https://doi.org/10.1016/S2589-7500(20)30165-5