A Bayesian Machine Learning Approach for Spatio-Temporal Prediction of COVID-19 Cases
Abstract Modeling the behavior and spread of infectious diseases on space and time is key in devising public policies for preventive measures. This behavior is so complex that there are lots of uncertainties in both the data and in the process itself. We argue here that these uncertainties should be taken into account in the modeling strategy. Machine learning methods, and neural networks, in particular, are useful in modeling this sort of complex problems, although they generally lack of probabilistic interpretations. We thus present here a neural network method embedded in a Bayesian framework for modeling 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 neighborhood 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.