arXiv:2608. 04222v1 Announce Type: cross Abstract: Turbulence is a central testbed for machine learning on physical dynamics because its governing laws are known exactly.
arXiv:2604. 23874v3 Announce Type: replace-cross Abstract: The differentiable physics paradigm may be leveraged as an a-posteriori approach for discovering turbulence closure models by embedding a neural network parameterization directly inside the solver and optimizing it given potentially sparse target data.
SHIFT‑Truck is the first high‑fidelity aerodynamics dataset and benchmark specifically for pickup trucks, comprising 1,000 Spalart‑Allmaras delayed detached‑eddy simulations of a reference truck geometry morphed across 17 shape parameters. Each simulation uses a ~100‑million‑cell mesh at a Reynolds number of 1.4×10⁷ and provides time‑averaged surface pressure, wall shear stress, volumetric pressure, and velocity data, verified by grid refinement, repeated runs, and wind‑tunnel measurements. The benchmark defines geometry‑grouped splits and evaluates four neural surrogates—DoMINO, GeoTransolver, AB‑UPT, and SMART—on surface and volume tracks, while also introducing controlled distribution shifts in operating point, surface discretization, and vehicle archetype to test generalization.
arXiv:2507. 00719v3 Announce Type: replace-cross Abstract: Typically, numerical simulations of Earth systems are coarse, and Earth observations are sparse and gappy.
This chapter reviews recent advances in Scientific Machine Learning (SciML) for modeling coupled fluid flow and transport phenomena governed by the incompressible Navier-Stokes and scalar transport equations. Such systems, found in applications like turbidity currents and thermal convection, feature strong nonlinear coupling and multiscale behavior that make high-fidelity simulations computationally expensive.
RheOPT is a transformer-based neural operator that first pretrains on inexpensive Newtonian fluid simulations and then fine‑tunes on a small set of non‑Newtonian samples. By reusing geometry‑conditioned transport structures rather than the Newtonian constitutive response, RheOPT achieves accurate few‑shot predictions for complex fluids such as Giesekus, Oldroyd‑B, and Bingham in a contraction channel and for oscillatory wake flows behind a triangular obstacle. The approach demonstrates that Newtonian pretraining can match or surpass models trained from scratch with four times as many non‑Newtonian samples, especially when using reversible instance normalization.
arXiv:2606. 19562v1 Announce Type: new Abstract: This chapter reviews recent advances in Scientific Machine Learning (SciML) for modeling coupled fluid flow and transport phenomena governed by the incompressible Navier-Stokes and scalar transport equations.
The paper presents cross‑domain pretraining for neural surrogates in steady‑state computational fluid dynamics (CFD). By training models across varied geometries, boundary conditions, and fidelities, the authors show that such pretraining improves zero‑ and few‑shot performance compared to training from scratch or transferring from domain‑specific experts. Finetuning a pretrained cross‑domain model can reduce errors by 2–3× at the same sample size and require eight times fewer samples to reach the same error, with benefits that grow with model size and dataset diversity.
The paper introduces a local and sparse kernel method for learning solution operators of incompressible flows, replacing global output reconstruction with local divergence‑free interpolants and a multiscale kernel that approaches Kolmogorov statistics under refinement. A compactly supported, positive‑semidefinite kernel yields sparse operator regression, with support radius fitted to data and optional affine polynomials capturing global trends. The method employs Operator Lagrange weights to avoid forming local coefficients, achieving accuracy comparable to or better than previous dense methods and neural operators, while offering significant GPU speed‑ups and reduced storage.
arXiv:2611.06912v1 Announce Type: cross Abstract: Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables. Yet it remains unclea...
The paper presents an online, end‑to‑end machine‑learning approach for subgrid‑scale modeling of two‑dimensional quasi‑geostrophic turbulence in a rapidly rotating annular domain. By developing a differentiable solver, the authors train SGS models over a single turnover time using coarse‑grained data from direct numerical simulations, achieving accurate reproduction of global diagnostics, energy spectra, and long‑term jet dynamics that extend beyond the training window. The trained models outperform traditional hyperdiffusivity and Leith closure schemes, enabling significant computational speed‑ups for studying long‑term geophysical fluid processes.
Many nonlinear physical systems exhibit an initial transient phase in which perturbations grow before nonlinear interactions lead to a statistically steady state. While this saturated regime is of primary interest, direct numerical simulations must resolve the full transient dynamics before reaching it, incurring significant computational cost.