Projektdaten
Datenassimilation - Die nahtlose Verschmelzung von Daten und Modellen
Fakultät/Einrichtung
Mathematik und Naturwissenschaften
Drittmittelgeber
Deutsche Forschungsgemeinschaft
Bewilligungssumme, Auftragssumme
203.550,00 €
Abstract:
BOB: Continuous learning by integrating reinforcement learning and data assimilation to individualise drug treatments
The variability in the response of patients to drug treatment is one of the key challenges in drug therapy. An important example is cytotoxic chemotherapy. The project aims at a novel class of model-informed precision dosing approaches based on a combination of reinforcement learning and sequential data assimilation that allows for continuous learning across patients, and addresses the key problems of model bias and complexity encountered in real-world scenarios. The aim is to provide decision support to individualise drug treatment based on relevant patient factors combined with therapeutic drug/biomarker monitoring data.
B06 - Novel methods for the data assimilation of highly variable and dynamic ring current populations
Energetic particles in the near-Earth space pose a significant risk to Earth-orbiting satellites and humans in space. During the first funding period, we focused on developing data-assimilative tools for the most energetic electrons called radiation belts. In the second funding period, we will focus on another highly variable population of electrons that is usually referred to as the "ring current", which produces charges on satellites. The new approaches and methods will be tested on space physics data.