Published:
Thermal Bridges on Building Rooftops - hyperspectral (RGB + Thermal + Height) drone imagery of Karlsruhe, Germany, with thermal bridge annotations, contributed by 6 researchers.
Recommended citation: Mayer, Z., Kahn, J., Götz, M., Hou, Y., Beiersdörfer, T., Blumenröhr, N., Streit, A., & Schultmann, F. (2023). "Thermal Bridges on Building Rooftops." Scientific Data, 10(1), 268. https://doi.org/10.5281/zenodo.7022736
Download Paper
Published:
Operational data of a concentrating solar power plant, following FAIR data principles, contributed by 13 researchers.
Recommended citation: Phipps, K., Kuhl, M., Weiel, M., Busch, M., Lewen, J., Blumenröhr, N., Maldonado Quinto, D., Debus, C., Göhring, F., Kaufhold, O., Streit, A., Pitz-Paal, R., Götz, M., & Pargmann, M. (2026). "The PAINT database for operational concentrating solar power plant data following FAIR data principles." Nature Energy.
Download Paper
Published in Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments (MLHPC 15), pp. 1–10, 2015
We present HPDBSCAN, a highly parallel, distributed-memory implementation of the DBSCAN clustering algorithm that scales density-based clustering to large datasets on high-performance computing systems.
Recommended citation: Götz, M., Bodenstein, C., & Riedel, M. (2015). "HPDBSCAN: Highly Parallel DBSCAN." In: Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments (MLHPC 15), pp. 1–10.
Download Paper
Published in European Conference on Parallel Processing (Euro-Par), Springer, pp. 17–31, 2023
We present perun, an open-source tool for measuring and benchmarking the energy consumption of high-performance computing applications, enabling more transparent and sustainable HPC and AI research.
Recommended citation: Gutiérrez Hermosillo Muriedas, J. P., Flügel, K., Debus, C., Obermaier, H., Streit, A., & Götz, M. (2023). "perun: Benchmarking Energy Consumption of High-Performance Computing Applications." In: European Conference on Parallel Processing. Springer, pp. 17–31.
Download Paper
Published in Nature Communications, 15(1), 6997, 2024
We use differentiable ray tracing to automatically calibrate heliostats in situ, learning precise geometric alignment metrology for concentrating solar power plants directly from operational sensor data.
Recommended citation: Pargmann, M., Ebert, J., Götz, M., Maldonado Quinto, D., Pitz-Paal, R., & Kesselheim, S. (2024). "Automatic heliostat learning for in situ concentrating solar power plant metrology with differentiable ray tracing." Nature Communications, 15(1), 6997.
Download Paper
Published in Energy & Environmental Science, 2025
We combine deep learning with in-situ luminescence imaging to monitor and better understand the scalable fabrication process of perovskite thin films, enabling augmented, data-driven process control for photovoltaics manufacturing.
Recommended citation: Laufer, F., Götz, M., & Paetzold, U. W. (2025). "Deep learning for augmented process monitoring of scalable perovskite thin-film fabrication." Energy & Environmental Science.
Download Paper
Published in Proceedings of the Platform for Advanced Scientific Computing Conference (PASC 26), 2026
We introduce Jigsaw, a model parallelization scheme combining domain and tensor parallelism to train multi-billion-parameter AI weather models, eliminating memory redundancy and achieving state-of-the-art scaling on up to 256 GPUs.
Recommended citation: Kieckhefen, D., Götz, M., Heyen, L. H., Streit, A., & Debus, C. (2026). "Combining Domain and Tensor Parallelism to Train Multi-billion-parameter AI Weather Models." In: Proceedings of the Platform for Advanced Scientific Computing Conference (PASC 26).
Download Paper
Published in Nature Energy, 2026
We introduce PAINT, the first FAIR, open-access database of operational concentrating solar power tower plant data, providing 849 GB of heliostat, calibration, and weather data to accelerate AI-driven solar research.
Recommended citation: Phipps, K., Kuhl, M., Weiel, M., Busch, M., Lewen, J., Blumenröhr, N., Maldonado Quinto, D., Debus, C., Göhring, F., Kaufhold, O., Streit, A., Pitz-Paal, R., Götz, M., & Pargmann, M. (2026). "The PAINT database for operational concentrating solar power plant data following FAIR data principles." Nature Energy.
Download Paper
Published:
A distributed and GPU-accelerated tensor framework for large-scale data analytics and high-performance AI, built on top of PyTorch and MPI.
Published:
A massively parallel and asynchronous evolutionary optimizer for hyperparameter search and black-box optimization on high-performance computing systems.
Published:
A lightweight tool for measuring and benchmarking the energy consumption of parallel Python applications on high-performance computing systems.
Master lecture, Karlsruhe Institute of Technology, Department of Informatics, 2021
Teaching assignment, Karlsruhe Institute of Technology, Winter Semester 2021/22, 4 ECTS points.
Master lecture, Karlsruhe Institute of Technology, Department of Informatics, 2022
Teaching assignment, Karlsruhe Institute of Technology, Winter Semester 2022/23, 4 ECTS points.
Master lecture, Karlsruhe Institute of Technology, Department of Informatics, 2023
Teaching assignment, Karlsruhe Institute of Technology, Winter Semester 2023/24, 4 ECTS points.
Master lecture, Karlsruhe Institute of Technology, Department of Informatics, 2024
Teaching assignment, Karlsruhe Institute of Technology, Winter Semester 2024/25, 4 ECTS points.
Bachelor lecture, TUM Campus Heilbronn, Technical University of Munich, 2026
Lecture for Bachelor students at TUM Campus Heilbronn, offered in Winter Semester 2026/2027, introducing the foundations of machine learning as the third course in the Data Science lecture series, 6 ECTS points.
Bachelor and Master seminar, TUM Campus Heilbronn, Technical University of Munich, 2026
Seminar for Bachelor and Master students at TUM Campus Heilbronn, offered in Winter Semester 2026/2027, focusing on machine learning methods applied to computer vision problems, 3 ECTS points.