Michael Ebner

Mr. Michael Ebner

FfE München
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 February 2022 in Energies
Verified
Journal Article
Open access
PDF file
SKStephan Kigle
Stephan Kigle
MEMichael Ebner
Michael Ebner
AGAndrej Guminski
Andrej Guminski
Greenhouse gas emissions need to be drastically reduced to mitigate the environmental impacts caused by climate change, and to lead to a transformation of the European energy system. A model landscape consisting of four final energy consumption sector models with high spatial (NUTS-3) and temporal (hourly) resolution and the multi-energy system model ISAaR is extended and applied to investigate the transformation pathway of the European energy sector in the deep emission mitigation scenario solidEU. The solidEU scenario describes not only the techno-economic but also the socio-political contexts, and it includes the EU27 + UK, Norway, and Switzerland. The scenario analysis shows that volatile renewable energy sources (vRES) dominate the energy system in 2050. In addition, the share of flexible sector coupling technologies increases to balance electricity generation from vRES. Seasonal differences are balanced by hydrogen storage with a seasonal storage profile. The deployment rates of vRES in solidEU show that a fast, profound energy transition is necessary to achieve European climate protection goals.

21 January 2026 in IEEE Access
Verified
Journal Article
Open access
JFJonas Fill
Jonas Fill
MEMichael Eichelbeck
Michael Eichelbeck
MEMichael Ebner
Michael Ebner
Building-specific knowledge, such as building type and function information, is important for numerous energy applications. However, comprehensive datasets containing this information for individual households are lacking in many regions of Europe. For the first time, we investigate whether predicting building types and functional classes at a European scale is feasible based only on open datasets available across countries. We train a graph neural network (GNN) classifier on a graph dataset of OpenStreetMap (OSM) buildings across the EU, Norway, Switzerland, and the UK. To efficiently perform training using the large-scale graph, we utilize localized subgraphs. A graph transformer model achieves a Cohen’s kappa coefficient of 0.7536 when classifying buildings into 9 classes, and 0.8442 when classifying buildings into the residential and non-residential classes. Transferability experiments demonstrate strong generalization to unseen regions ( $\kappa =0.7379$ in region-based spatial cross-validation), with a model trained in Germany maintaining predictive power across Europe when minimal local data is included ( $\kappa =0.6403$ ). The results imply three key novel contributions to the literature. Firstly, we show that building classification across multiple countries is possible using a multi-source dataset. Secondly, our results indicate that GNNs that consider contextual information about building neighborhoods improve predictive performance compared to models that only consider individual buildings and ignore the neighborhood. Third, we show that training with GNNs on localized subgraphs instead of standard GNNs improves the performance of the building classification task.

1 September 2026 in Geo-spatial Information Science
Verified
Journal Article
Open access
MEMichael Ebner
Michael Ebner
PBPaul Bantelmann
Paul Bantelmann
DWDaniela Wohlschlager
Daniela Wohlschlager
THThomas Hamacher
Thomas Hamacher
1. In order to achieve the goal of greenhouse gas neutrality by 2045, Germany presented a new climate protection program in October 2023, in which new measures were defined for the individual secto...