Deep learning-based parameter estimation of high spatial resolution mathematical models for the spread and control of COVID-19 in Germany

• Applicant: Professor Dr. Gordon Pipa, since 5/2023
• Subject Area: Epidemiology and Medical Biometry/Statistics ; Mathematics ; Computer Architecture, Embedded and Massively Parallel Systems ; Statistical Physics, Nonlinear Dynamics, Complex Systems, Soft and Fluid Matter, Biological Physics
• Term: from 2021 to 2024
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 492349907

• Final Report Year: 2024

Final Report Abstract

The Core Goal of the project was to provide a fully data-driven analysis and forecast of spatialtemporal dynamics, with an improved spatial resolution that will enable decision-makers to judge the current and predicted dynamics, to assess the reliability and possible variations of the predictions, plan and adjust regulation to control the outbreak. We achieved this goal during the project time and did not have to adjust any subgoal. We demonstrated an improvement by including different scales and identified key constrains for future applications. The results and code are available to the public, and we are in the final phase of preparing the publication.

Publications

• Learning COVID-19 Regional Transmission Using Universal Differential Equations in a SIR Model
  Rojas-Campos, A., Stelz, L. & Nieters, P.