Helmholtz AI - cooperative AI research

Logo der Helmholtz AI Cooperation Unit

AI, and machine learning (ML) in particular, is also playing an increasingly central role in research. This is reflected in the evaluation of growing volumes of data, in the monitoring of processes or as a decision-making aid in the design process of new experiments. This is why the Helmholtz Association launched the Helmholtz Artificial Intelligence Platform Helmholtz AI two years ago as a research project of the Helmholtz Incubator Information & Data Science. The overarching mission of the platform is the "democratization of AI for a data-driven future" and aims to make AI algorithms and approaches available to as broad a user group as possible in an easy-to-use and resource-saving manner.

The Helmholtz AI Local Units

The Helmholtz AI platform is structured according to a wheel-spoke model that covers the six research fields of the Helmholtz Association. In recent years, five so-called Local Units have been implemented at various Helmholtz centers. The KIT is responsible for energy research with its local unit. Within this framework, the SCC supports researchers with an advisory unit in the implementation of AI research projects in the exploration of new approaches to energy generation, distribution and storage. The local units each consist of a Helmholtz junior research group and an AI consultant team, which in turn supports other research groups with its AI expertise.

Helmholtz AI Consulting at KIT

At the SCC, the Helmholtz AI Local Energy Consulting team supports project ideas of researchers from the Helmholtz Association who require AI methods and expertise for their research and developments. More information about the Helmholtz AI Consulting service.

Projects

All projects are described on the page of the Helmholtz AI Consulting team of the KIT.

Publications


2024
Harnessing Orthogonality to Train Low-Rank Neural Networks
Coquelin, D.; Flügel, K.; Weiel, M.; Kiefer, N.; Debus, C.; Streit, A.; Götz, M.
2024. ECAI 2024 : 27th European Conference on Artificial Intelligence 19–24 October 2024, Santiago de Compostela, Spain Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024 ; Proceedings. Ed.: U. Endriss, 2106–2113, IOS Press. doi:10.3233/FAIA240729
Taylor Expansion in Neural Networks: How Higher Orders Yield Better Predictions
Zwerschke, P.; Weyrauch, A.; Götz, M.; Debus, C.
2024. ECAI 2024 – 27th European Conference on Artificial Intelligence, 19–24 October 2024, Santiago de Compostela, Spain – Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024). Ed.: U. Endriss, 2983–2989, IOS Press. doi:10.3233/FAIA240838
Comparative Study of Federated Learning Frameworks NVFlare and Flower for Detecting Thermal Bridges in Urban Environments
Duda, L. J.; Alibabaei, K. F.; Vollmer, E.; Klug, L.; Benz, M.; Kozlov, V.; Rebekka Volk; Götz, M.; Schultmann, F.; Streit, A.
2024, September 3. EGI Conference (2024), Lecce, Italy, September 30–October 4, 2024
ReCycle: Fast and Efficient Long Time Series Forecasting with Residual Cyclic Transformers
Weyrauch, A.; Steens, T.; Taubert, O.; Hanke, B.; Eqbal, A.; Götz, E.; Streit, A.; Götz, M.; Debus, C.
2024. 2024 IEEE Conference on Artificial Intelligence (CAI), Singapore, Singapore, 25-27 June 2024, 1187–1194, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/CAI59869.2024.00212
How Does Feature Engineering Impact UAV-based Multispectral Semantic Segmentation? An RGB and Thermal Image Ablation Study
Vollmer, E.; Benz, M.; Kahn, J.; Klug, L.; Volk, R.; Schultmann, F.; Götz, M.
2024, June 12. Helmholtz Artificial Intelligence Conference (Helmholtz AI 2024), Düsseldorf, Germany, June 12–14, 2024
Federated Learning for Urban Energy Efficiency: Detecting Thermal with UAV-based Imaging and AI
Duda, L. J.; Alibabaei, K.; Vollmer, E.; Klug, L.; Benz, M.; Kozlov, V.; Volk, R.; Goetz, M.; Schultmann, F.; Streit, A.
2024, June 12. Helmholtz Artificial Intelligence Conference (Helmholtz AI 2024), Düsseldorf, Germany, June 12–14, 2024
Feasibility of Forecasting Highly Resolved Power Grid Frequency Utilizing Temporal Fusion Transformers
Pütz, S.; El Ashhab, H.; Hertel, M.; Mikut, R.; Götz, M.; Hagenmeyer, V.; Schäfer, B.
2024. e-Energy ’24: Proceedings of the 15th ACM International Conference on Future and Sustainable Energy Systems, 447–453, Association for Computing Machinery (ACM). doi:10.1145/3632775.3661963
Simulation and Data Life Cycle Labs at SCC
Aversa, R.; Azmi, E.; Fischer, M.; Götz, M.
2024, May 2. Strategic Advisory Board (SAB) meeting for the Helmholtz Program EDF (2024), Karlsruhe, Germany, May 2, 2024
Model Fusion via Neuron Transplantation
Öz, M.; Kiefer, N.; Debus, C.; Hörter, J.; Streit, A.; Götz, M.
2024. Machine Learning and Knowledge Discovery in Databases. Research Track : European Conference, ECML PKDD 2024, Vilnius, Lithuania, September 9–13, 2024, Proceedings, Part IV. Ed. by Albert Bifet, Jesse Davis, Tomas Krilavičius, Meelis Kull, Eirini Ntoutsi, Indrė Žliobaitė, 3–19, Springer Nature Switzerland. doi:10.1007/978-3-031-70359-1_1
Automatic heliostat learning for in situ concentrating solar power plant metrology with differentiable ray tracing
Pargmann, M.; Ebert, J.; Götz, M.; Maldonado Quinto, D.; Pitz-Paal, R.; Kesselheim, S.
2024. Nature Communications, 15 (1), Art.-Nr.: 6997. doi:10.1038/s41467-024-51019-z
(Semi-) Automatic Review Process for Common Compound Characterization Data in Organic Synthesis
Huang, Y.-C.; Tremouilhac, P.; Kuhn, S.; Huang, P.-C.; Lin, C.-L.; Schlörer, N.; Taubert, O.; Götz, M.; Jung, N.; Bräse, S.
2024. ChemRxiv. doi:10.26434/chemrxiv-2024-1r9tb
Surrogate Modelling for Core Degradation in pressurized Water Reactors
Dressner, J.; Götz, M.; Stakhanova, A.; Gabrielli, F.; Debus, C.
2024. Helmholtz Artificial Intelligence Conference (Helmholtz AI 2024), Düsseldorf, Germany, June 12–14, 2024
PETNet–Coincident Particle Event Detection using Spiking Neural Networks
Debus, J.; Debus, C.; Dissertori, G.; Götz, M.
2024. 2024 Neuro Inspired Computational Elements Conference (NICE), 9 S., Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/NICE61972.2024.10549584
2023
Providing AI expertise as an infrastructure in academia
Piraud, M.; Camero, A.; Götz, M.; Kesselheim, S.; Steinbach, P.; Weigel, T.
2023. Patterns, 4 (8), Art.-Nr.: 100819. doi:10.1016/j.patter.2023.100819
Deep learning approaches to building rooftop thermal bridge detection from aerial images
Mayer, Z.; Kahn, J.; Hou, Y.; Götz, M.; Volk, R.; Schultmann, F.
2023. Automation in Construction, 146, Art.-Nr.: 104690. doi:10.1016/j.autcon.2022.104690
Precise Energy Consumption Measurements of Heterogeneous Artificial Intelligence Workloads
Caspart, R.; Ziegler, S.; Weyrauch, A.; Obermaier, H.; Raffeiner, S.; Schuhmacher, L. P.; Scholtyssek, J.; Trofimova, D.; Nolden, M.; Reinartz, I.; Isensee, F.; Götz, M.; Debus, C.
2023. High Performance Computing. ISC High Performance 2022 International Workshops – Hamburg, Germany, May 29 – June 2, 2022, Revised Selected Papers. Ed.: H. Anzt, 108–121, Springer International Publishing. doi:10.1007/978-3-031-23220-6_8
perun: Benchmarking Energy Consumption of High-Performance Computing Applications
Gutiérrez Hermosillo Muriedas, J. P.; Flügel, K.; Debus, C.; Obermaier, H.; Streit, A.; Götz, M.
2023. Euro-Par 2023: Parallel Processing. Ed.: J. Cano, 17–31, Springer Nature Switzerland. doi:10.1007/978-3-031-39698-4_2
Reporting electricity consumption is essential for sustainable AI
Debus, C.; Piraud, M.; Streit, A.; Theis, F.; Götz, M.
2023. Nature Machine Intelligence, 5 (11), 1176–1178. doi:10.1038/s42256-023-00750-1
RNA contact prediction by data efficient deep learning
Taubert, O.; von der Lehr, F.; Bazarova, A.; Faber, C.; Knechtges, P.; Weiel, M.; Debus, C.; Coquelin, D.; Basermann, A.; Streit, A.; Kesselheim, S.; Götz, M.; Schug, A.
2023. Communications Biology, 6 (1), 913. doi:10.1038/s42003-023-05244-9
Massively Parallel Genetic Optimization Through Asynchronous Propagation of Populations
Taubert, O.; Weiel, M.; Coquelin, D.; Farshian, A.; Debus, C.; Schug, A.; Streit, A.; Götz, M.
2023. doi:10.48550/arXiv.2301.08713
Massively Parallel Genetic Optimization Through Asynchronous Propagation of Populations
Taubert, O.; Weiel, M.; Coquelin, D.; Farshian, A.; Debus, C.; Schug, A.; Streit, A.; Götz, M.
2023. High Performance Computing – 38th International Conference, ISC High Performance 2023, Hamburg, Germany, May 21–25, 2023, Proceedings. Ed.: A. Bhatele, 106 – 124, Springer Nature Switzerland. doi:10.1007/978-3-031-32041-5_6
Thermal Bridges on Building Rooftops
Mayer, Z.; Kahn, J.; Götz, M.; Hou, Y.; Beiersdörfer, T.; Blumenröhr, N.; Volk, R.; Streit, A.; Schultmann, F.
2023. Scientific Data, 10 (1), Art.-Nr.: 268. doi:10.1038/s41597-023-02140-z
2022
A Computational Workflow for Interdisciplinary Deep Learning Projects utilizing bwHPC Infrastructure
Schilling, M.; Neumann, O.; Scherr, T.; Cui, H.; Popova, A. A.; Levkin, P. A.; Götz, M.; Reischl, M.
2022. Proceedings of the 7th bwHPC Symposium, 69–74, Kommunikations- und Informationszentrum (kiz). doi:10.18725/OPARU-46069
Hyde: The First Open-Source, Python-Based, Gpu-Accelerated Hyperspectral Denoising Package
Coquelin, D.; Rasti, B.; Gotz, M.; Ghamisi, P.; Gloaguen, R.; Streit, A.
2022. 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Rome, Italy, 13-16 September 2022, 1–5, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/WHISPERS56178.2022.9955088
Accelerating neural network training with distributed asynchronous and selective optimization (DASO)
Coquelin, D.; Debus, C.; Götz, M.; Lehr, F. von der; Kahn, J.; Siggel, M.; Streit, A.
2022. Journal of Big Data, 9 (1), 14. doi:10.1186/s40537-021-00556-1
Prediction of Optimal Solvers for Sparse Linear Systems Using Deep Learning
Funk, Y.; Götz, M.; Anzt, H.
2022. Proceedings of the 2022 SIAM Conference on Parallel Processing for Scientific Computing (PP). Ed.: X. Li, 14–24, Society for Industrial and Applied Mathematics (SIAM). doi:10.1137/1.9781611977141.2
2021
A Computational Workflow for Interdisciplinary Deep Learning Projects utilizing bwHPC Infrastructure
Schilling, M. P.; Neumann, O.; Scherr, T.; Cui, H.; Popova, A. A.; Levkin, P. A.; Götz, M.; Reischl, M.
2021, November 8. 7th bwHPC Symposium (2021), Online, November 8, 2021
Heat - A Distributed and Accelerated Tensor Framework for Data Analytics and Machine Learning
Comito, C.; Götz, M.; Debus, C.; Coquelin, D.; Tarnawa, M.; Krajsek, K.; Knechtges, P.; Siggel, M.; Hagemeier, B.; Basermann, A.; Streit, A.
2021, October 5. 1st Artificial Intelligence Symposium on Theory, Application & Research (AI STAR 2021), Online, October 5–6, 2021
Dynamic particle swarm optimization of biomolecular simulation parameters with flexible objective functions
Weiel, M.; Götz, M.; Klein, A.; Coquelin, D.; Floca, R.; Schug, A.
2021. Nature machine intelligence, 3 (8), 727–734. doi:10.1038/s42256-021-00366-3
Evolutionary Optimization of Neural Architectures in Remote Sensing Classification Problems
Coquelin, D.; Sedona, R.; Riedel, M.; Götz, M.
2021. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 12-16 July 2021, 1587–1590, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/IGARSS47720.2021.9554309
HyDe - Hyperspectral Denoising Algorithm Toolbox in Python
Coquelin, D.; Götz, M.
2021, February 23
Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)
Coquelin, D.; Debus, C.; Götz, M.; Lehr, F. von der; Kahn, J.; Siggel, M.; Streit, A.
2021. Springer. doi:10.21203/rs.3.rs-832355/v1
2020
HeAT – a Distributed and GPU-accelerated Tensor Framework for Data Analytics
Götz, M.; Coquelin, D.; Debus, C.; Krajsek, K.; Comito, C.; Knechtges, P.; Hagemeier, B.; Tarnawa, M.; Hanselmann, S.; Siggel, M.; Basermann, A.; Streit, A.
2020. doi:10.5445/IR/1000123473
HeAT - A Distributed and GPU-accelerated Tensor Framework for Data Analytics
Götz, M.; Debus, C.; Coquelin, D.; Krajsek, K.; Comito, C.; Knechtges, P.; Hagemeier, B.; Tarnawa, M.; Hanselmann, S.; Siggel, M.; Basermann, A.; Streit, A.
2020. 2020 IEEE International Conference on Big Data (Big Data): 10-13 December 2020, online, 276–287, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/BigData50022.2020.9378050
Loss Scheduling for Class-Imbalanced Segmentation Problems
Taubert, O.; Götz, M.; Schug, A.; Streit, A.
2020. 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 422–427, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ICMLA51294.2020.00073
HeAT – a Distributed and GPU-accelerated TensorFramework for Data Analytics
Götz, M.; Debus, C.; Coquelin, D.; Krajsek, K.; Comito, C.; Knechtges, P.; Hagemeier, B.; Tarnawa, M.; Hanselmann, S.; Siggel, M.; Basermann, A.; Streit, A.
2020. 2020 IEEE International Conference on Big Data (Big Data), 276–287, Institute of Electrical and Electronics Engineers (IEEE)
2019
Machine learning-aided numerical linear Algebra: Convolutional neural networks for the efficient preconditioner generation
Götz, M.; Anzt, H.
2019. Proceedings of ScalA 2018: 9th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, 49–56, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ScalA.2018.00010
Remote Sensing Data Analytics with the Udocker Container Tool using Multi-GPU Deep Learning Systems
Cavallaro, G.; Kozlov, V.; Götz, M.; Riedel, M.
2019. Proceedings of 2019 Big Data from Space (BiDS’19). Ed.: S. Pierre, 177–180. doi:10.2760/848593
2018
The Helmholtz Analytics Toolkit (HEAT): A scientific Big Data Library for HPC
Krajsek, K.; Comito, C.; Götz, M.; Hagemeier, B.; Knechtges, P.; Siggel, M.
2018. Proceedings of the Extreme Data Workshop 2018
Machine learning-aided numerical linear algebra: Convolutional neural network for the efficient preconditioner generation
Götz, M.; Anzt, H.
2018. ScalA18: 9th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, Dallas, TX, November 12, 2018