Machine Learning in Sustainable Energy Systems

Who we are: We’re the MLSES group within the Cluster of Excellence – Machine Learning for Science at the University of Tübingen and are interested in developing new machine learning algorithms to build and maintain a future sustainable energy system.

Research Areas

Climate Change Impacts on Energy Systems

Climate Change Impacts on Energy Systems

How does climate change impact a renewable energy system?

Probabilistic Forecasting

Probabilistic Forecasting

How can we reliably predict time series in complex systems under uncertainty?

Statistical, Physical Information and Modularity

Statistical, Physical Information and Modularity

How can we include statistical information such as seasonality, trends or concept drifts into DNNs to improve forecasting?

Demand Side Flexibility & Markets

Demand Side Flexibility & Markets

How can we recognise, promote and use flexibility on the demand side?

Latest News

16.11.2023: Our IN-ML-OUT project can now be seen at the Stadtmuseum Tübingen. For more details, follow the link
10.11.2023: Nina's and Nicole's paper "Mind the (spectral) gap: How the temporal resolution of wind speed data affects multi-decadal wind power forecasts" got accepted! The paper is a result of a collaboration with Rachel White from UBC.

Teaching

Machine Learning for Renewable Energy Systems

We’re offering the Seminar on Machine Learning for Renewable Energy Systems in the Summer Term 2024.

Last updated on Apr 23, 2024

In the winter term we’ll offer the lecture “Time Series” (6 ECTS).

Last updated on Oct 16, 2023

Projects

Science Communication Project: Climate Change, Machine Learning and Wind Energy Forecasting

IN-ML-OUT

BMBF funded research project: Machine Learning in Complex Systems under Uncertainty

FEAT

Recent Publications

Luca Schmidt, Nicole Ludwig (2024). Benchmarking Deep Learning Based Downscaling of Wind Speed.

PDF Cite Project DOI URL

Florian Ebmeier, Nicole Ludwig, Jannik Thümmel, Georg Martius, Volker H. Franz (2024). Fault Detection in Solar Thermal Systems Using Probabilistic Reconstructions.

PDF Cite DOI URL

Nina Effenberger, Marvin Pförtner, Philipp Hennig, Nicole Ludwig (2024). Probabilistic Wind Speed Downscaling for Future Wind Power Assessment.

PDF Cite Project DOI URL

Nina Effenberger, Nicole Ludwig, Rachel H. White (2023). Mind the (spectral) gap: How the temporal resolution of wind data affects multi-decadal wind power forecasts.

PDF Cite Project

Julian Friedrich, Anna Bareis, Moritz Bross, Zoé Bürger, Álvaro Cortés Rodríguez, Nina Effenberger, Markus Kleinhansl, Fabienne Kremer, Cornelius Schröder (2023). “How is your thesis going?”-Ph.D. students' perspectives on mental health and stress in academia. PLOS ONE.

See all publications

Where to find us

Maria-von-Linden Str 6
72076 Tübingen