Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems

Hans Harder, Abhijeet Vishwasrao, Luca Guastoni, Ricardo Vinuesa, Sebastian Peitz
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:1601-1619, 2026.

Abstract

This paper is concerned with probabilistic techniques for forecasting dynamical systems described by partial differential equations (such as, for example, the Navier-Stokes equations). In particular, it is investigating and comparing various extensions to the flow matching paradigm that reduce the number of sampling steps. In this regard, it compares direct distillation, progressive distillation, adversarial diffusion distillation, Wasserstein GANs and rectified flows. Moreover, experiments are conducted on a set of challenging systems. In particular, we also address the challenge of directly predicting 2D slices of large-scale 3D simulations, paving the way for efficient inflow generation for solvers.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-harder26a, title = {Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems}, author = {Harder, Hans and Vishwasrao, Abhijeet and Guastoni, Luca and Vinuesa, Ricardo and Peitz, Sebastian}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {1601--1619}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/harder26a/harder26a.pdf}, url = {https://proceedings.mlr.press/v331/harder26a.html}, abstract = {This paper is concerned with probabilistic techniques for forecasting dynamical systems described by partial differential equations (such as, for example, the Navier-Stokes equations). In particular, it is investigating and comparing various extensions to the flow matching paradigm that reduce the number of sampling steps. In this regard, it compares direct distillation, progressive distillation, adversarial diffusion distillation, Wasserstein GANs and rectified flows. Moreover, experiments are conducted on a set of challenging systems. In particular, we also address the challenge of directly predicting 2D slices of large-scale 3D simulations, paving the way for efficient inflow generation for solvers.} }
Endnote
%0 Conference Paper %T Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems %A Hans Harder %A Abhijeet Vishwasrao %A Luca Guastoni %A Ricardo Vinuesa %A Sebastian Peitz %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-harder26a %I PMLR %P 1601--1619 %U https://proceedings.mlr.press/v331/harder26a.html %V 331 %X This paper is concerned with probabilistic techniques for forecasting dynamical systems described by partial differential equations (such as, for example, the Navier-Stokes equations). In particular, it is investigating and comparing various extensions to the flow matching paradigm that reduce the number of sampling steps. In this regard, it compares direct distillation, progressive distillation, adversarial diffusion distillation, Wasserstein GANs and rectified flows. Moreover, experiments are conducted on a set of challenging systems. In particular, we also address the challenge of directly predicting 2D slices of large-scale 3D simulations, paving the way for efficient inflow generation for solvers.
APA
Harder, H., Vishwasrao, A., Guastoni, L., Vinuesa, R. & Peitz, S.. (2026). Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:1601-1619 Available from https://proceedings.mlr.press/v331/harder26a.html.

Related Material