A Bayesian machine learning approach for spatio-temporal prediction of COVID-19 cases Seminar

Abstract:

Modelling the spread of infectious diseases in space and time needs to take care of complex dependencies and uncertainties. Machine learning methods, and neural networks, in particular, are useful in modelling this sort of complex problems, although they generally lack probabilistic interpretations. We propose a neural network method embedded in a Bayesian framework for modelling and predicting the number of cases of infectious diseases in areal units. A key feature is that our combined model considers the impact of human movement on the spread of the infectious disease, as an additional random factor to the also considered spatial neighbourhood and temporal correlation components. Our model is evaluated over a COVID-19 dataset for 245 health zones of Castilla-Leon (Spain). The results show that a Bayesian model informed by a neural network method is generally able to predict the number of cases of COVID-19 in both space and time, with the human mobility factor having a strong influence on the model, together with the number of infections and deaths in nearby areas.

Speaker Information

Speaker: Somnath Chaudhuri

Bio:

Somnath Chaudhuri is a Research Fellow specializing in spatial statistics in the WorldPop Research Group, University of Southampton, UK. His research interests include Bayesian models and spatiotemporal modelling across various domains such as socio-demographics, health, urban, and environmental areas. I obtained my Ph.D. in Spatial Statistics from the University of Girona, Spain.

He has a master's in computer science and engineering from the University of Calcutta, India. His second Masters in Geospatial Technology is under the Erasmus Mundus Scholarship Program jointly from three Universities of Germany, Spain and Portugal funded by the European Commission. He has several years of experience in academic and research roles at universities in different countries, including India, Bhutan, Maldives, Saudi Arabia, Germany, and Spain. 

Link to join in online

Please remember to turn off your camera/microphone to save bandwidth. 

Please also note that the seminar will be recorded.