Digital epidemiology leverages computational simulations, ranging from compartmental SIR/SEIR systems to AI-based and agent-based frameworks, to transform real-time data into defensible public health decisions. This talk distils the mathematical intuition and data pipelines that power epidemic models. It contrasts their utility for critical tasks, such as incidence forecasting, hotspot clustering, assessing shocks such as conflict or natural disasters, quantifying socio-environmental drivers of spread, and estimating vaccination thresholds for elimination. Case studies across infectious diseases demonstrate how calibrated, uncertainty-aware scenarios have informed surge-capacity planning, targeted immunisation, and risk communication. By outlining best practices for model selection, validation, and transparent communication, the talk argues that reproducible simulation is more than prediction; it is a dynamic decision aid that sharpens the timeliness, precision, and accountability of infectious disease control.
About the speaker:
Dmytro Chumachenko is an Associate Professor at the Department of Mathematical Modelling and Artificial Intelligence of National Aerospace University “Kharkiv Aviation Institute” (Ukraine). Currently, he is a scholar at the Balsillie School of International Affairs.
Dmytro obtained a Bachelor of Science degree in “Applied Mathematics” and Master’s degrees in “Social Informatics” and “Project and Program Management” at the National Aerospace University “Kharkiv Aviation Institute”. Dmytro obtained PhD degree in Systems and Means of Artificial Intelligence at the Kharkiv National University of Radioelectronics and continued his research as a Post-doctoral Research Fellow at the Ubiquitous Health Technologies Lab of the University of Waterloo.
His research focuses on simulating the spread of infectious diseases and applying AI tools and methods for public health and strategic communications.
