geoEpi - spatio-temporal epidemiology of emerging viruses — leveraging crowdsourced data and occurrence data to improve early disease detection systems
A couple of viruses are of global interest with respect to human health and well-being. These pathogens include the novel coronavirus SARS-CoV-2, Dengue, Chikungunya, Yellow fever, Zika and Ebola. These viruses show interesting spatio-temporal dynamics. Improved understanding of the driving and moderating factors will help to cope with these pathogens. The DFG/DACH funded project geoEpi aims at revealing those driving and moderating factors.
The project intends to use social media and web search data together with official health surveillance data to develop novel algorithms to achieve higher information quality to generate more reliable conclusions and more accurate predictions about the spatio-temporal spread of diseases. Major innovations of the project are:
- the inclusion of the temporal dimension into spatial epidemiology,
- the use of crowdsourced data in combination with official health surveillance data for fine scale monitoring disease dispersal,
- the inclusion of mobility/urban demographic and environmental covariates to derive ‘socio-ecological corridors’ that describe likely routes of disease spread after initial outbreaks, and
- the development of ML algorithms to deal with the massive amounts of crowdsourced data and to complement and to improve rule- /model-based approaches.
The work is performed by three partners: 1) GIScience, Heidelberg University under involvement of HeiGIT, 2) the Heidelberg University Hospital and 3) University of Salzburg – Department of Geoinformatics – Z_GIS.
Work at GIScience will focus specifically on the relationships between Pathogen Movement, Environmental Covariates and Human Movement Patterns. The driving factors of the spatio-temporal patterns of the diseases in focus are still not entirely clear. The work aims at a fine-grained analysis of the spatio-temporal pattern of the dispersal of the viruses addressed and the study of the spatio-temporal pattern association with environmental and socio-economic variables. A particular focus will be on linking socio-ecological driving factors with spatio-temporal patterns of disease spread. Our hypothesis is that the spatio-temporal pattern of the outbreaks of SARS-CoV-2, Dengue, Chikungunya, Yellow fever, Zika and Ebola is moderated by a combination of environmental conditions, land use, traffic networks and human movement patterns. We aim to develop an integrated method to quantify how spatio-temporal movement patterns of the different diseases are shaped by transport networks and socio-environmental conditions, which are expected to form “socio-ecological corridors.”