The project consists of the development of an intelligent epidemiological evaluation and prevention system that combines the processing of data on human activity, interaction and mobility, epidemiological and clinical data related to COVID-19, with the mathematical modeling that uses this data to calculate the probabilities of epidemic risk and effective reproductive number in Catalonia and Spain. This system integrates, initially, the different scales of interaction and mobility of each age group, each stage of the disease, and each locality. In addition, it plans to disaggregate the population also by socioeconomic level or by other characteristics that, at any given time, may be defining of the social behavior in relation to the disease (for example, people with or without work, people with PCR test done or not, etc.). The system allows the projection of risks for each locality and for each group from the detected cases. The system also incorporates clinical, healthcare and hospital data, making it possible to detect early risks associated with the saturation of the healthcare system. These predictions are extremely relevant in the early stages of virus spread (when the impact is reduced to a few cases), inhomogeneous epidemic scenarios (such as in March and April) and in the phase of descaling, providing a very useful early warning system. In the first case, in the absence of containment, the system alerts the likely location of secondary and tertiary cases. In the second and third, the system aims to assess multiple non-pharmacological containment strategies based on confinement and reduced mobility, as well as evaluate the development of measures implemented in terms of hospital capacity, encouraging adoption of measures based on scientific evidence.

● Postdoc 1 - to perform tasks related to data acquisition and extension of epidemiological models of compartments
● Postdoc 2 - to develop tools related to data acquisition and the development of machine learning tools with this data
● Postdoc 3 - to perform tasks of integration of machine learning tools in the compartmentalized model