---
_id: '67306'
author:
- first_name: Jan
full_name: Stenner, Jan
last_name: Stenner
- first_name: Hans
full_name: Harder, Hans
id: '98879'
last_name: Harder
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: Stenner J, Harder H, Peitz S. Sparse Sensor Placement in Multi-Agent Reinforcement
Learning Control of Rayleigh-Bénard Convection. arXiv:260630238. Published
online 2026.
apa: Stenner, J., Harder, H., & Peitz, S. (2026). Sparse Sensor Placement in
Multi-Agent Reinforcement Learning Control of Rayleigh-Bénard Convection. In arXiv:2606.30238.
bibtex: '@article{Stenner_Harder_Peitz_2026, title={Sparse Sensor Placement in Multi-Agent
Reinforcement Learning Control of Rayleigh-Bénard Convection}, journal={arXiv:2606.30238},
author={Stenner, Jan and Harder, Hans and Peitz, Sebastian}, year={2026} }'
chicago: Stenner, Jan, Hans Harder, and Sebastian Peitz. “Sparse Sensor Placement
in Multi-Agent Reinforcement Learning Control of Rayleigh-Bénard Convection.”
ArXiv:2606.30238, 2026.
ieee: J. Stenner, H. Harder, and S. Peitz, “Sparse Sensor Placement in Multi-Agent
Reinforcement Learning Control of Rayleigh-Bénard Convection,” arXiv:2606.30238.
2026.
mla: Stenner, Jan, et al. “Sparse Sensor Placement in Multi-Agent Reinforcement
Learning Control of Rayleigh-Bénard Convection.” ArXiv:2606.30238, 2026.
short: J. Stenner, H. Harder, S. Peitz, ArXiv:2606.30238 (2026).
date_created: 2026-10-01T12:00:58Z
date_updated: 2026-10-01T12:01:23Z
department:
- _id: '655'
keyword:
- own
- own-preprint
- erc
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2606.30238
oa: '1'
publication: arXiv:2606.30238
status: public
title: Sparse Sensor Placement in Multi-Agent Reinforcement Learning Control of Rayleigh-Bénard
Convection
type: preprint
user_id: '47427'
year: '2026'
...
---
_id: '67302'
abstract:
- lang: eng
text: Data-driven surrogate models provide fast and fully differentiable approximations
of complex dynamical systems. In this work, we develop such surrogates for the
Rayleigh–Bénard convection (RBC), which governs thermally driven flows in natural
and industrial environments. Specifically, the proposed models approximate the
discrete-time flow map of the RBC system, advancing the full system state by a
fixed time step. We train Fourier Neural Operator (FNO)–based models to learn
the dynamics of RBC in two and three dimensions and compare them to a convolutional
U-Net baseline and a Koopman-based Linear Recurrent Autoencoder Network (LRAN).
The two-dimensional system serves as a baseline for the more challenging three-dimensional
case, which exhibits increased spatial complexity and turbulent dynamics. Across
all settings, FNO-based models consistently outperform the LRAN, while achieving
performance comparable to the U-Net in several regimes. Incorporating spatio-temporal
inputs via FNOs leads to improved long-term prediction accuracy, particularly
for turbulent flows. The physical fidelity of the predictions is assessed using
convective heat flux statistics, profiles, and fluctuations, showing that FNOs
most closely reproduce the ground-truth flow statistics. In addition, we demonstrate
that FNOs enable zero-shot super-resolution across unseen spatial discretizations,
a capability not shared by the convolutional baselines. These results highlight
the potential of neural operator–based models as accurate, physically consistent,
and resolution-independent surrogates for downstream tasks such as flow control.
author:
- first_name: Thorben
full_name: Markmann, Thorben
last_name: Markmann
- first_name: Michiel
full_name: Straat, Michiel
last_name: Straat
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
citation:
ama: Markmann T, Straat M, Peitz S, Hammer B. Fourier neural operators as data-driven
surrogates for two- and three-dimensional Rayleigh–Bénard convection. Neurocomputing.
2026;679:133201. doi:10.1016/j.neucom.2026.133201
apa: Markmann, T., Straat, M., Peitz, S., & Hammer, B. (2026). Fourier neural
operators as data-driven surrogates for two- and three-dimensional Rayleigh–Bénard
convection. Neurocomputing, 679, 133201. https://doi.org/10.1016/j.neucom.2026.133201
bibtex: '@article{Markmann_Straat_Peitz_Hammer_2026, title={Fourier neural operators
as data-driven surrogates for two- and three-dimensional Rayleigh–Bénard convection},
volume={679}, DOI={10.1016/j.neucom.2026.133201},
journal={Neurocomputing}, author={Markmann, Thorben and Straat, Michiel and Peitz,
Sebastian and Hammer, Barbara}, year={2026}, pages={133201} }'
chicago: 'Markmann, Thorben, Michiel Straat, Sebastian Peitz, and Barbara Hammer.
“Fourier Neural Operators as Data-Driven Surrogates for Two- and Three-Dimensional
Rayleigh–Bénard Convection.” Neurocomputing 679 (2026): 133201. https://doi.org/10.1016/j.neucom.2026.133201.'
ieee: 'T. Markmann, M. Straat, S. Peitz, and B. Hammer, “Fourier neural operators
as data-driven surrogates for two- and three-dimensional Rayleigh–Bénard convection,”
Neurocomputing, vol. 679, p. 133201, 2026, doi: 10.1016/j.neucom.2026.133201.'
mla: Markmann, Thorben, et al. “Fourier Neural Operators as Data-Driven Surrogates
for Two- and Three-Dimensional Rayleigh–Bénard Convection.” Neurocomputing,
vol. 679, 2026, p. 133201, doi:10.1016/j.neucom.2026.133201.
short: T. Markmann, M. Straat, S. Peitz, B. Hammer, Neurocomputing 679 (2026) 133201.
date_created: 2026-10-01T11:55:20Z
date_updated: 2026-10-01T11:56:04Z
department:
- _id: '655'
doi: 10.1016/j.neucom.2026.133201
intvolume: ' 679'
keyword:
- own
- own-journal
- erc
language:
- iso: eng
page: '133201'
publication: Neurocomputing
publication_identifier:
issn:
- 0925-2312
status: public
title: Fourier neural operators as data-driven surrogates for two- and three-dimensional
Rayleigh–Bénard convection
type: journal_article
user_id: '47427'
volume: 679
year: '2026'
...
---
_id: '67299'
author:
- first_name: Hans
full_name: Harder, Hans
id: '98879'
last_name: Harder
- first_name: Abhijeet
full_name: Vishwasrao, Abhijeet
last_name: Vishwasrao
- first_name: Luca
full_name: Guastoni, Luca
last_name: Guastoni
- first_name: Ricardo
full_name: Vinuesa, Ricardo
last_name: Vinuesa
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: 'Harder H, Vishwasrao A, Guastoni L, Vinuesa R, Peitz S. Efficient probabilistic
surrogate modeling techniques for partially-observed large-scale dynamical systems.
In: Sukhatme G, Lindemann L, Tu S, Wierman A, Atanasov N, eds. Proceedings
of The 8th Annual Learning for Dynamics and Control Conference. Vol 331. Proceedings
of Machine Learning Research. PMLR; 2026:1601–1619. doi:10.48550/arXiv.2511.04641'
apa: Harder, H., Vishwasrao, A., Guastoni, L., Vinuesa, R., & Peitz, S. (2026).
Efficient probabilistic surrogate modeling techniques for partially-observed large-scale
dynamical systems. In G. Sukhatme, L. Lindemann, S. Tu, A. Wierman, & N. Atanasov
(Eds.), Proceedings of The 8th Annual Learning for Dynamics and Control Conference
(Vol. 331, pp. 1601–1619). PMLR. https://doi.org/10.48550/arXiv.2511.04641
bibtex: '@inproceedings{Harder_Vishwasrao_Guastoni_Vinuesa_Peitz_2026, series={Proceedings
of Machine Learning Research}, title={Efficient probabilistic surrogate modeling
techniques for partially-observed large-scale dynamical systems}, volume={331},
DOI={10.48550/arXiv.2511.04641},
booktitle={Proceedings of The 8th Annual Learning for Dynamics and Control Conference},
publisher={PMLR}, author={Harder, Hans and Vishwasrao, Abhijeet and Guastoni,
Luca and Vinuesa, Ricardo and Peitz, Sebastian}, editor={Sukhatme, Gaurav and
Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, year={2026},
pages={1601–1619}, collection={Proceedings of Machine Learning Research} }'
chicago: Harder, Hans, Abhijeet Vishwasrao, Luca Guastoni, Ricardo Vinuesa, and
Sebastian Peitz. “Efficient Probabilistic Surrogate Modeling Techniques for Partially-Observed
Large-Scale Dynamical Systems.” In Proceedings of The 8th Annual Learning for
Dynamics and Control Conference, edited by Gaurav Sukhatme, Lars Lindemann,
Stephen Tu, Adam Wierman, and Nikolay Atanasov, 331:1601–1619. Proceedings of
Machine Learning Research. PMLR, 2026. https://doi.org/10.48550/arXiv.2511.04641.
ieee: 'H. Harder, A. Vishwasrao, L. Guastoni, R. Vinuesa, and S. Peitz, “Efficient
probabilistic surrogate modeling techniques for partially-observed large-scale
dynamical systems,” in Proceedings of The 8th Annual Learning for Dynamics
and Control Conference, 2026, vol. 331, pp. 1601–1619, doi: 10.48550/arXiv.2511.04641.'
mla: Harder, Hans, et al. “Efficient Probabilistic Surrogate Modeling Techniques
for Partially-Observed Large-Scale Dynamical Systems.” Proceedings of The 8th
Annual Learning for Dynamics and Control Conference, edited by Gaurav Sukhatme
et al., vol. 331, PMLR, 2026, pp. 1601–1619, doi:10.48550/arXiv.2511.04641.
short: 'H. Harder, A. Vishwasrao, L. Guastoni, R. Vinuesa, S. Peitz, in: G. Sukhatme,
L. Lindemann, S. Tu, A. Wierman, N. Atanasov (Eds.), Proceedings of The 8th Annual
Learning for Dynamics and Control Conference, PMLR, 2026, pp. 1601–1619.'
date_created: 2026-10-01T11:51:57Z
date_updated: 2026-10-01T11:52:48Z
department:
- _id: '655'
doi: 10.48550/arXiv.2511.04641
editor:
- first_name: Gaurav
full_name: Sukhatme, Gaurav
last_name: Sukhatme
- first_name: Lars
full_name: Lindemann, Lars
last_name: Lindemann
- first_name: Stephen
full_name: Tu, Stephen
last_name: Tu
- first_name: Adam
full_name: Wierman, Adam
last_name: Wierman
- first_name: Nikolay
full_name: Atanasov, Nikolay
last_name: Atanasov
intvolume: ' 331'
keyword:
- own
- own-conference
- erc
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://openreview.net/pdf?id=Z9srtyqVLE
oa: '1'
page: 1601–1619
publication: Proceedings of The 8th Annual Learning for Dynamics and Control Conference
publisher: PMLR
series_title: Proceedings of Machine Learning Research
status: public
title: Efficient probabilistic surrogate modeling techniques for partially-observed
large-scale dynamical systems
type: conference
user_id: '47427'
volume: 331
year: '2026'
...
---
_id: '67305'
author:
- first_name: Jannis
full_name: Becktepe, Jannis
last_name: Becktepe
- first_name: Aleksandra
full_name: Franz, Aleksandra
last_name: Franz
- first_name: Nils
full_name: Thuerey, Nils
last_name: Thuerey
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: 'Becktepe J, Franz A, Thuerey N, Peitz S. Plug-and-Play Benchmarking of Reinforcement
Learning Algorithms for Large-Scale Flow Control. In: International Conference
on Machine Learning (ICML). ; 2026. doi:10.48550/arXiv.2601.15015'
apa: Becktepe, J., Franz, A., Thuerey, N., & Peitz, S. (2026). Plug-and-Play
Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control.
International Conference on Machine Learning (ICML). https://doi.org/10.48550/arXiv.2601.15015
bibtex: '@inproceedings{Becktepe_Franz_Thuerey_Peitz_2026, title={Plug-and-Play
Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control},
DOI={10.48550/arXiv.2601.15015},
booktitle={International Conference on Machine Learning (ICML)}, author={Becktepe,
Jannis and Franz, Aleksandra and Thuerey, Nils and Peitz, Sebastian}, year={2026}
}'
chicago: Becktepe, Jannis, Aleksandra Franz, Nils Thuerey, and Sebastian Peitz.
“Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale
Flow Control.” In International Conference on Machine Learning (ICML),
2026. https://doi.org/10.48550/arXiv.2601.15015.
ieee: 'J. Becktepe, A. Franz, N. Thuerey, and S. Peitz, “Plug-and-Play Benchmarking
of Reinforcement Learning Algorithms for Large-Scale Flow Control,” 2026, doi:
10.48550/arXiv.2601.15015.'
mla: Becktepe, Jannis, et al. “Plug-and-Play Benchmarking of Reinforcement Learning
Algorithms for Large-Scale Flow Control.” International Conference on Machine
Learning (ICML), 2026, doi:10.48550/arXiv.2601.15015.
short: 'J. Becktepe, A. Franz, N. Thuerey, S. Peitz, in: International Conference
on Machine Learning (ICML), 2026.'
date_created: 2026-10-01T11:59:35Z
date_updated: 2026-10-01T12:00:51Z
department:
- _id: '655'
doi: 10.48550/arXiv.2601.15015
keyword:
- own
- own-conference
- erc
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://safe-autonomous-systems.github.io/fluidgym/
oa: '1'
publication: International Conference on Machine Learning (ICML)
status: public
title: Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale
Flow Control
type: conference
user_id: '47427'
year: '2026'
...
---
_id: '67298'
author:
- first_name: Christian
full_name: Mugisho Zagabe, Christian
last_name: Mugisho Zagabe
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: Mugisho Zagabe C, Peitz S. Automatic feature identification in least-squares
policy iteration using the Koopman operator framework. arXiv:260326464.
Published online 2026.
apa: Mugisho Zagabe, C., & Peitz, S. (2026). Automatic feature identification
in least-squares policy iteration using the Koopman operator framework. In arXiv:2603.26464.
bibtex: '@article{Mugisho Zagabe_Peitz_2026, title={Automatic feature identification
in least-squares policy iteration using the Koopman operator framework}, journal={arXiv:2603.26464},
author={Mugisho Zagabe, Christian and Peitz, Sebastian}, year={2026} }'
chicago: Mugisho Zagabe, Christian, and Sebastian Peitz. “Automatic Feature Identification
in Least-Squares Policy Iteration Using the Koopman Operator Framework.” ArXiv:2603.26464,
2026.
ieee: C. Mugisho Zagabe and S. Peitz, “Automatic feature identification in least-squares
policy iteration using the Koopman operator framework,” arXiv:2603.26464.
2026.
mla: Mugisho Zagabe, Christian, and Sebastian Peitz. “Automatic Feature Identification
in Least-Squares Policy Iteration Using the Koopman Operator Framework.” ArXiv:2603.26464,
2026.
short: C. Mugisho Zagabe, S. Peitz, ArXiv:2603.26464 (2026).
date_created: 2026-10-01T11:50:28Z
date_updated: 2026-10-01T11:51:41Z
department:
- _id: '655'
keyword:
- own
- own-preprint
- erc
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2603.26464
oa: '1'
publication: arXiv:2603.26464
status: public
title: Automatic feature identification in least-squares policy iteration using the
Koopman operator framework
type: preprint
user_id: '47427'
year: '2026'
...
---
_id: '67304'
author:
- first_name: Tim
full_name: Plotzki, Tim
last_name: Plotzki
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: Plotzki T, Peitz S. Koopman-based surrogate modeling for reinforcement-learning-control
of Rayleigh-Benard convection. arXiv:260328074. Published online 2026.
apa: Plotzki, T., & Peitz, S. (2026). Koopman-based surrogate modeling for reinforcement-learning-control
of Rayleigh-Benard convection. In arXiv:2603.28074.
bibtex: '@article{Plotzki_Peitz_2026, title={Koopman-based surrogate modeling for
reinforcement-learning-control of Rayleigh-Benard convection}, journal={arXiv:2603.28074},
author={Plotzki, Tim and Peitz, Sebastian}, year={2026} }'
chicago: Plotzki, Tim, and Sebastian Peitz. “Koopman-Based Surrogate Modeling for
Reinforcement-Learning-Control of Rayleigh-Benard Convection.” ArXiv:2603.28074,
2026.
ieee: T. Plotzki and S. Peitz, “Koopman-based surrogate modeling for reinforcement-learning-control
of Rayleigh-Benard convection,” arXiv:2603.28074. 2026.
mla: Plotzki, Tim, and Sebastian Peitz. “Koopman-Based Surrogate Modeling for Reinforcement-Learning-Control
of Rayleigh-Benard Convection.” ArXiv:2603.28074, 2026.
short: T. Plotzki, S. Peitz, ArXiv:2603.28074 (2026).
date_created: 2026-10-01T11:59:03Z
date_updated: 2026-10-01T11:59:27Z
department:
- _id: '655'
keyword:
- own
- own-preprint
- erc
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2603.28074
oa: '1'
publication: arXiv:2603.28074
status: public
title: Koopman-based surrogate modeling for reinforcement-learning-control of Rayleigh-Benard
convection
type: preprint
user_id: '47427'
year: '2026'
...
---
_id: '67318'
author:
- first_name: Fynn
full_name: Fromme, Fynn
last_name: Fromme
- first_name: Christine
full_name: Allen-Blanchette, Christine
last_name: Allen-Blanchette
- first_name: Hans
full_name: Harder, Hans
id: '98879'
last_name: Harder
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: Fromme F, Allen-Blanchette C, Harder H, Peitz S. Surrogate Modeling of 3D Rayleigh-Bénard
Convection with Equivariant Autoencoders. arXiv:250513569. Published online
2025.
apa: Fromme, F., Allen-Blanchette, C., Harder, H., & Peitz, S. (2025). Surrogate
Modeling of 3D Rayleigh-Bénard Convection with Equivariant Autoencoders. In arXiv:2505.13569.
bibtex: '@article{Fromme_Allen-Blanchette_Harder_Peitz_2025, title={Surrogate Modeling
of 3D Rayleigh-Bénard Convection with Equivariant Autoencoders}, journal={arXiv:2505.13569},
author={Fromme, Fynn and Allen-Blanchette, Christine and Harder, Hans and Peitz,
Sebastian}, year={2025} }'
chicago: Fromme, Fynn, Christine Allen-Blanchette, Hans Harder, and Sebastian Peitz.
“Surrogate Modeling of 3D Rayleigh-Bénard Convection with Equivariant Autoencoders.”
ArXiv:2505.13569, 2025.
ieee: F. Fromme, C. Allen-Blanchette, H. Harder, and S. Peitz, “Surrogate Modeling
of 3D Rayleigh-Bénard Convection with Equivariant Autoencoders,” arXiv:2505.13569.
2025.
mla: Fromme, Fynn, et al. “Surrogate Modeling of 3D Rayleigh-Bénard Convection with
Equivariant Autoencoders.” ArXiv:2505.13569, 2025.
short: F. Fromme, C. Allen-Blanchette, H. Harder, S. Peitz, ArXiv:2505.13569 (2025).
date_created: 2026-10-01T12:06:29Z
date_updated: 2026-10-01T12:06:45Z
department:
- _id: '655'
keyword:
- own
- own-preprint
- erc
language:
- iso: eng
publication: arXiv:2505.13569
status: public
title: Surrogate Modeling of 3D Rayleigh-Bénard Convection with Equivariant Autoencoders
type: preprint
user_id: '47427'
year: '2025'
...