Postdoctoral Researcher in Energy System Modelling and Machine Learning (SURE-RES project)

The Overall Energy System Modelling and e-mobility group of Eurac Research's Institute for Renewable Energy is recruiting a postdoc for SURE-RES (Spatially-resolved UnceRtainty analysis for futurE Renewable based Energy Systems), a three-year project with the Climate Policy Lab of ETH Zurich co-funded by the Swiss National Science Foundation and the Autonomous Province of Bolzano. SURE-RES develops multi-fidelity methods for rigorous uncertainty analysis in high-resolution energy system models.

Starting from a sector-coupled PyPSA-Eur model of Europe with about 200 nodes and hourly resolution, it compares resolution-reduced models combined with polynomial chaos expansion against graph neural network surrogates that emulate the hourly operational optimisation while preserving spatial detail, and translates the results into spatially resolved policy guidance for South Tyrol and Switzerland. The postdoc will build reduced model variants, train surrogates and run global sensitivity analysis, design GNN surrogates (e.g. GAT, GraphSAGE, GIN) for capacity-expansion planning, compare the strategies and publish open code and data.

The fixed-term contract in Bolzano lasts one to three years.

PhD in energy engineering, computer science, applied mathematics, physics or a related field (candidates close to completion may be considered); proven experience in energy system modelling and optimisation (e.g. PyPSA, Calliope, oemof, TIMES) and/or machine learning for energy or engineering systems; very good Python and scientific computing; peer-reviewed publications; very good English. Experience with PyPSA-Eur, solvers such as Gurobi or HiGHS, PyTorch Geometric, uncertainty quantification, HPC and Italian or German is an asset.