The study demonstrates that a wide‑activation deep super‑resolution (WDSR) network can learn to reconstruct unseen two‑dimensional homogeneous isotropic turbulence fields from overlapping patches of a single high‑resolution realization. By training exclusively on these patches, the model achieves extreme super‑resolution factors of x32 and x64, accurately recovering coherent vortical structures and fine‑scale features better than conventional interpolation. Spectral and statistical analyses confirm improved high‑wavenumber energy recovery and multiscale flow characteristics, and comparisons with models trained on multiple full snapshots highlight the advantage of exploiting spatial redundancy within a single realization.
arXiv:2507. 22082v2 Announce Type: replace-cross Abstract: Direct numerical simulation (DNS) accurately resolves all spatio-temporal scales of wall-bounded turbulence but becomes prohibitively expensive as the Reynolds number increases.
The paper presents a turbulence‑aware framework for reconstructing high‑fidelity three‑dimensional flow fields from coarse‑grained data. It combines a multiscale neural operator with a state‑space model to enforce temporal consistency, incorporates Navier‑Stokes residuals as soft constraints, and uses a mixture‑of‑experts mechanism for unsupervised adaptation to unknown coarse‑graining. Experiments on canonical turbulent systems and atmospheric reanalysis data show reduced reconstruction errors and better preservation of multiscale spatial structure and coherent temporal evolution compared to existing learning‑based and classical baselines.
High-fidelity three-dimensional turbulent flow fields are crucial for scientific and engineering analyses, but direct numerical simulation or high-resolution measurements are costly. The paper introduces a turbulence-aware framework that couples a multiscale neural operator with a state space model and incorporates Navier-Stokes residuals as soft constraints to reconstruct time-resolved 3‑D flow fields from coarse-grained data. The method also uses a mixture-of-experts mechanism for unsupervised adaptation to unknown coarse-graining, and demonstrates reduced reconstruction errors and improved preservation of multiscale spatial structure and coherent temporal evolution on canonical turbulent systems and atmospheric reanalysis data.
arXiv:2609. 38977v1 Announce Type: cross Abstract: Neural surrogates have emerged as fast alternatives to the numerical simulation of three-dimensional turbulence.
arXiv:2507. 00719v3 Announce Type: replace-cross Abstract: Typically, numerical simulations of Earth systems are coarse, and Earth observations are sparse and gappy.
arXiv:2608. 16546v1 Announce Type: cross Abstract: Most super-resolution models learn from paired data by supervising only the final high-resolution output.
arXiv:2608. 14744v1 Announce Type: new Abstract: Recovering high-resolution states from sparse, low-resolution observations is a central challenge in scientific machine learning and data assimilation.
arXiv:2608. 05981v1 Announce Type: new Abstract: High-resolution climate data is crucial for meteorological predictions and for informing decision support across diverse domains.
arXiv:2610.19274v1 Announce Type: cross Abstract: Atmospheric turbulence creates complex spatial and temporal distortions that significantly reduce image quality. This work compares two deep learning...
arXiv:2607. 03279v1 Announce Type: new Abstract: Accurate regional weather prediction requires resolving fine-scale structure while remaining consistent with global dynamics.
arXiv:2606. 11691v1 Announce Type: new Abstract: Latent diffusion and flow matching have emerged as leading approaches for synthetic turbulence generation, yet they systematically under-represent dissipation-range amplitudes.
arXiv:2606. 16765v1 Announce Type: new Abstract: Evaluating neural operators for 3D turbulent flow requires validated datasets with physical benchmarks.