Wavelet Flow Matching for Multi-Scale Physics Emulation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913134122369024 |
|---|---|
| author | Accarino, Gabriele Nathaniel, Juan Roesch, Carla Gentine, Pierre Shamekh, Sara Watson-Parris, Duncan Acquaviva, Viviana |
| author_facet | Accarino, Gabriele Nathaniel, Juan Roesch, Carla Gentine, Pierre Shamekh, Sara Watson-Parris, Duncan Acquaviva, Viviana |
| contents | Accurate emulation of multi-scale physical systems governed by PDEs demands models that remain stable over long autoregressive rollouts while preserving fine-scale structures. Deterministic emulators produce overly-smoothed predictions, while generative approaches better capture details but are costly. Latent-space generative models have emerged as a compromise but with the additional cost of separately pre-trained autoencoders. We propose Wavelet Flow Matching (WFM), a novel generative emulator that overcomes current trade-offs between cost and skill by performing optimal-transport directly in the multi-scale wavelet space. Rather than learning a latent compression, WFM leverages the hierarchical structure of a U-Net to jointly predict transport velocities of a prescribed wavelet representation. On three challenging systems of chaotic fluid dynamics, WFM achieves superior long-horizon stability, accuracy and spectral coherence compared to state-of-the-art models. Our results clearly position the wavelet space as an effective training-free representation for generative emulation of complex physical dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16573 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Wavelet Flow Matching for Multi-Scale Physics Emulation Accarino, Gabriele Nathaniel, Juan Roesch, Carla Gentine, Pierre Shamekh, Sara Watson-Parris, Duncan Acquaviva, Viviana Machine Learning Artificial Intelligence Fluid Dynamics 42C40, 65T60, 35Q68, I.4.10; I.5.4; I.2.10; G.3 Accurate emulation of multi-scale physical systems governed by PDEs demands models that remain stable over long autoregressive rollouts while preserving fine-scale structures. Deterministic emulators produce overly-smoothed predictions, while generative approaches better capture details but are costly. Latent-space generative models have emerged as a compromise but with the additional cost of separately pre-trained autoencoders. We propose Wavelet Flow Matching (WFM), a novel generative emulator that overcomes current trade-offs between cost and skill by performing optimal-transport directly in the multi-scale wavelet space. Rather than learning a latent compression, WFM leverages the hierarchical structure of a U-Net to jointly predict transport velocities of a prescribed wavelet representation. On three challenging systems of chaotic fluid dynamics, WFM achieves superior long-horizon stability, accuracy and spectral coherence compared to state-of-the-art models. Our results clearly position the wavelet space as an effective training-free representation for generative emulation of complex physical dynamics. |
| title | Wavelet Flow Matching for Multi-Scale Physics Emulation |
| topic | Machine Learning Artificial Intelligence Fluid Dynamics 42C40, 65T60, 35Q68, I.4.10; I.5.4; I.2.10; G.3 |
| url | https://arxiv.org/abs/2605.16573 |