AI4COVID: Artificial Intelligence and geographical information for monitoring and prediction of Covid-19 outbreak

Home » Cocreating Eosc » AI4COVID: Artificial Intelligence and geographical information for monitoring and prediction of Covid-19 outbreak


The COVID-19 pandemic emerged and evolved so quickly that societies were not able to respond quickly enough, mainly due to the nature of the Covid-19 virus’ rate of spread and also the largely open societies that we live in. While we have been willingly moving towards open societies and reducing movement barriers, there is a need to be prepared for minimizing the openness of society on occasions such as large pandemics, which are low probability events with massive impacts. Certainly, similar to many phenomena, the Covid-19 pandemic has shown us its own geography, presenting its emergence and evolving patterns as well as taking advantage of our geographical settings for escalating its spread.

Watch our past Co-creating EOSC Webinars: Fighting COVID-19 with Open Science

Objectives & Challenges

This study aims at presenting a data-driven approach for exploring the spatio-temporal patterns of the pandemic over a regional scale, i.e., Europe and a country scale, i.e., Denmark, and also what geographical variables potentially contribute to expediting its spread. We used official regional infection rates, points of interest, temperature, and air pollution data for monitoring the pandemic’s spread across Europe and also applied geospatial methods such as spatial autocorrelation and space-time autocorrelation to extract relevant indicators that could explain the dynamics of the pandemic. Furthermore, we applied statistical methods, e.g., ordinary least squares, geographically weighted regression, as well as machine learning methods, e.g., random forest for exploring the potential correlation between the chosen underlying factors and the pandemic spread.

Main Findings

Our study successfully proved the importance and unique contribution of geographical data and tools in addressing managerial decisions related to public health, and in particular pandemics. Our findings indicate that population density, amenities such as cafes and bars, and pollution levels are the most influential explanatory variables, while pollution levels can be explicitly used to monitor lockdown measures and infection rates at country level. The choice of data and methods used in this study along with the achieved results and presented discussions can empower health authorities and decision makers with an interactive decision support tool, which can be useful for imposing geographically varying lockdowns and protective measures using historical data.

Main Recommendations

Our study was funded within an unexpected research demand extending the traditional topical coverage of EOSC, hence the following recommendations are given from our experience.

  • EOSC's financial support for such small projects with high impact on societal challenges can lead to great contribution to respective scientific fields.
  • EOSC's further support for open source tools development in the cloud similar to Microsoft Azure or Google Cloud is appreciated and can promote reproducible research environment. Doing so will allow data-demanding and artificial intelligence-based studies be handled quicker and more conveniently.
  • EOSC should extend its topical coverage to broader topics allowing junior researchers and mini projects to be realised, which can provide the seed for bigger and more impactful projects.


Visit the Github Repository here