Glacio-Hydrological Modeling of Glaciers’ Buffering Role in the Alps and Andes Against Climate Change

This PhD position focuses on advancing glacio-hydrological modeling to assess glaciers’ role as water buffers in the face of climate change. The candidate will enhance a physics-informed machine learning framework (using ODINN.jl) to improve glacier thickness inversion and future projections in the Alps and Andes. The work integrates heterogeneous datasets (surface velocities, radar thickness, mass balance, and digital elevation models) and couples glacier models with differentiable hydrological models calibrated via LSTM. The research aims to bridge climate projections with actionable water resource insights, addressing critical gaps in basin-scale glacier process representation.

• Develop and enhance a coupled glacio-hydrological modeling framework combining physics-based glacier models and differentiable machine learning techniques.
• Improve glacier thickness inversion and future projections for the Alps and Andes using heterogeneous datasets (surface velocities, radar thickness, mass balance, and digital elevation models).
• Couple the glacier model ODINN.jl with a differentiable hydrological model calibrated using LSTM to simulate glacier meltwater flow and downstream hydrological impacts.
• Analyze and interpret model outputs to provide actionable insights on water resource availability under climate change scenarios.
• Publish research findings in peer-reviewed journals and present results at international conferences.