In contrast to conventional approaches, the project uses drone images to identify habitats where ticks – and therefore potential sources of infection – are particularly common. In collaboration with entomologists, the findings on the spread of vectors and pathogens are being refined in order to improve the accuracy of the model. Machine learning algorithms are used for modeling, and weather data is integrated to take into account the effects of climate on tick populations. In a model region that is considered a hotspot for tick-borne encephalitis (TBE) and Lyme disease, volunteers will be invited to take a blood test (serological study) in later phases of the project. Dry blood sample self-tests (DBS) are used to determine how many people already have antibodies against the pathogens. This makes it possible to identify previously undetected infections and improve the available data. At the same time, predictions about the locations of infection foci are validated by field studies.

Objectives:

• Modeling and analysis of environmental factors for TBE and Lyme disease using ML algorithms and drones
• Prediction of TBE and Lyme disease hotspots
• Determining the prevalence of TBE and Lyme disease in the population
• Development of mathematical models for the population dynamics of ticks and the infection dynamics in humans and calibration with collected data
• Analysis of pharmaceutical and non-pharmaceutical interventions
• Establishment of detection and monitoring measures