I am a Research Associate Professor at Northeastern University, Roux Institute member, and Core Faculty at the Network Science Institute. My research lies at the intersection between network science, data science, epidemiology, economics, and artificial intelligence. My most recent work focuses on developing large-scale, data-driven computational models to study and forecast the spatial spread of infectious diseases while considering the impact of changes in human behavior (e.g. mobility, contact patterns, vaccine hesitancy, ..) and policy interventions.
My research interests include: a) the development of computational and analytical models to study and forecast the spatial spread of infectious diseases; b) the development of agent-based models to create realistic representations of population dynamics; c) the study of human mobility and contact patterns using high-resolution large-scale de-identified location data; d) the development of computational frameworks that combine mechanistic epidemic models with machine learning/deep learning models; and e) the study of the evolution and structure of science and innovation.
In response to the ongoing COVID-19 outbreak, we extended the Global Epidemic and Mobility model (GLEAM) to incorporate the effects of travel restrictions, non-pharmaceutical interventions, age-structured contact patterns, and vaccination campaigns to study, project, and forecast the evolution of the COVID-19 pandemic. Read more..
We combine traditional epidemic modeling approaches with state-of-the-art machine learning and deep learning methods to improve forecasts, accelerate large-scale stochastic simulations, and reconstruct the early stages of an epidemic. Read more..
We introduce a multiscale modeling approach to study the diffusion and impact of SARS-CoV-2 at both global and local scale combining epidemic models that work at different geographical resolutions. Read more..
The Global Epidemic and Mobility project, GLEAM, combines real-world data on populations and human mobility with elaborate stochastic models of disease transmission to deliver analytic and forecasting power to address the challenges faced in developing intervention strategies that minimize the impact of potentially devastating epidemics. Read more..
We characterize collective physical distancing—mobility reductions, minimization of contacts, shortening of contact duration—in response to the COVID-19 pandemic by analyzing de-identified location data for a panel of over 5.5 million anonymized, opted-in U.S. devices. Read more..