Duration
July 2022 to December 2025
Contact
Dr. Stefan Kesselheim
Head of SDL Applied Machine Learning & AI Consultant team
Building 14.14 / Room 3023
+49 2461/61-85927
E-MailJens Henrik Göbbert
Building 16.4 / Room 307
+49 2461/61-96498
E-MailLOKI-Pandemics
Lokales Frühwarnsystem zur Kontrolle von Infektionsausbrüchen (Local Early Warning System for Control of Infection Outbreaks)
The LOKI pilot project was launched on 1 July 2022 under the leadership of the Helmholtz Centre for Infection Research (HZI) and in collaboration with the Academy of Public Health, the CISPA Helmholtz Center for Information Security, Forschungszentrum Jülich (FZJ), the German Aerospace Center (DLR), and the Helmholtz Centre for Environmental Research (UFZ). The goal is to provide health authorities with a local early warning system for epidemiologically relevant outbreaks of infection in the future – in a customizable and practical manner.
Since the pooling of data in the health sector is subject to strict requirements concerning the protection of private data, privacy and IT security are priorities in the project. The data thus obtained will be supplemented with publicly available data, and then entered into an automated modelling process.
The huge amounts of data will be fed into various equation-based and agent-based computer models that will be designed in LOKI. High-performance computers can then be used to make detailed predictions about how the outbreak might develop locally and what effect the measures taken might have.
To this end, the Jülich Supercomputing Centre is developing a secure cloud infrastructure, interfaces for connection to high-performance computing, and customized, highly automated tools for real-time analysis of infection events using artificial intelligence methods.