PpbYour position /b /p /p This project will advance multi-fidelity modelling approaches tailored to headwater systems and deliver new insights into groundwater-surface water interactions. A key challenge for hydrological headwater catchment analyses lies in characterizing and predicting their hydrological functioning, and this is fundamentally related to the fact that the majority of them are unmonitored and their hydraulic parameters unknown. The objective of this PhD project is bridge this gap and develop data-driven, machine learning-based approaches to identify the governing hydraulic parameters of headwater catchments, hind- and forecast their stream and groundwater outflows, and to understand their susceptibility to extreme hydrometeorological conditions based on storyline approaches.br/br/You will specifically:br/liContribute to the development of the multi-fidelity modelling platform HydroModPy, /liliImplement machine-learning based approaches to estimate hydraulic properties across the headwater catchments of Europe, /liliEvaluate hydrological validation approaches for headwater catchment properties identification, /liliImplement hybrid-modelling approaches to hind- and forecast the hydrological behavior of ungauged headwater catchments using climate storylines /libr/The outcomes of this project will support both the scientific community and practitioners by improving the assessment and prediction of hydrological responses to climate change. ppbbYour profile /b /b /p /p Required Qualifications:liMSc in Hydrology, Hydrogeology, Data/Computer Science or a related field, /liliStrong interest in environmental data analysis and/or numerical modelling, /liliProficiency in Python programming, /liliFluency and excellent writing skills in English, with a strong interest in scientific and public communication. /li