Project and Generate: Divergence-Free Neural Operators for Incompressible Flows

• URL: http://arxiv.org/abs/2603.24500v1
• Date: Wed, 25 Mar 2026 16:40:58 GMT
• Title: Project and Generate: Divergence-Free Neural Operators for Incompressible Flows
• Abstract summary: Learning-based models for fluid dynamics operate in unconstrained function spaces, leading to physically inadmissible simulations.<n>We introduce a unified framework that enforces the incompressible continuity equation as a hard, intrinsic constraint for both deterministic and generative modeling.<n> Experiments on 2D Navier-Stokes equations demonstrate exact incompressibility up to discretization error and substantially improved stability and physical consistency.
• Score: 20.191712078154413
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. While penalty-based methods offer soft regularization, they provide no structural guarantees, resulting in spurious divergence and long-term collapse. In this work, we introduce a unified framework that enforces the incompressible continuity equation as a hard, intrinsic constraint for both deterministic and generative modeling. First, to project deterministic models onto the divergence-free subspace, we integrate a differentiable spectral Leray projection grounded in the Helmholtz-Hodge decomposition, which restricts the regression hypothesis space to physically admissible velocity fields. Second, to generate physically consistent distributions, we show that simply projecting model outputs is insufficient when the prior is incompatible. To address this, we construct a divergence-free Gaussian reference measure via a curl-based pushforward, ensuring the entire probability flow remains subspace-consistent by construction. Experiments on 2D Navier-Stokes equations demonstrate exact incompressibility up to discretization error and substantially improved stability and physical consistency.

Related papers

• Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulation [39.8019405552335]
  Pure Lagrangian neural simulators offer geometric flexibility and exact advection.<n>The absence of a fixed global reference frame introduces two severe limitations.<n>We propose a Hybrid Lagrangian-Eulerian neural simulator that augments Lagrangian dynamics with an Eulerian representation.
  arXiv  Detail & Related papers  (2026-08-02T11:36:08Z)
• Stochastic Counterdiabatic Driving via Biorthogonal Liouvillian Eigenmodes [42.668742604089324]
  Escorted free energy simulations address the non-adiabatic lag by engineering control fields $mathbfu$ that eliminate the lag.<n>We construct a complementary numerical framework based on gauge-type transforms instead of generalized coordinate transforms.<n>We show that the counterdiabatic condition is satisfied to machine precision, with the non-adiabatic lag suppressed by roughly twelve orders of magnitude.
  arXiv  Detail & Related papers  (2026-07-27T13:08:14Z)
• Capturing non-Markovian dynamics in non-equilibrium stochastic systems using flow matching [39.146761527401424]
  We develop a generative flow matching method that directly models the probability distribution of flux from particle simulations.<n>We show the model accurately captures the short-time behavior and provides better predictions of the statistical moments of the number density.
  arXiv  Detail & Related papers  (2026-06-04T19:06:10Z)
• PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics [14.400502760340862]
  PDE-governed fields from sparse and irregular measurements are challenging due to their ill-posed nature.<n>We propose PerFlow, a rectified Flow for efficient sparse reconstruction and uncertainty quantification oftemporal dynamics.<n> Experiments on various PDE systems demonstrate competitive reconstruction accuracy with sound physics, while enabling efficient conditional sampling.
  arXiv  Detail & Related papers  (2026-05-05T09:19:09Z)
• Geometric Decoupling: Diagnosing the Structural Instability of Latent [44.374154158781295]
  We analyze the generative Jacobian, decomposing geometry into textitLocalScaling (capacity) and textitLocal Complexity (curvature)<n>Our study uncovers a textbfGeometric Decoupling": while curvature in normal generation functionally encodes image detail, OOD generation exhibits a functional decoupling where extreme curvature is wasted on unstable semantic boundaries rather than perceptible details.
  arXiv  Detail & Related papers  (2026-04-20T20:22:27Z)
• Model-Free Quantum Stabilization via Finite-Difference Lyapunov Control [0.0]
  We develop a model-free framework for stabilizing quantum states using only empirical finite-difference evaluations of a measurement-derived Lyapunov observable.<n>The approach combines three key elements: sign-based Lyapunov descent, adaptive gain amplification, and a finite-difference analogue of LaSalle's in principle.
  arXiv  Detail & Related papers  (2026-04-11T15:36:27Z)
• Stability of nonlinear dissipative systems with applications in fluid dynamics [0.7816377212023299]
  We investigate the stability of dissipative partial differential equations with second-order nonlinearities.<n>We apply the framework to fluid-dynamical models governed by nonlinear partial differential equations.
  arXiv  Detail & Related papers  (2026-03-27T17:27:13Z)
• Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems [41.99844472131922]
  We propose a data-driven framework to learn interaction kernels in multi-agent systems.<n>Our approach aims at identifying the functional form of nonlocal interaction and diffusion terms directly from trajectory data.
  arXiv  Detail & Related papers  (2026-03-16T21:19:25Z)
• Infinite dimensional generative sensing [0.9749560288448113]
  This work presents a rigorous framework for generative compressed sensing in Hilbert spaces.<n>Thanks to a generalization of the Restricted Isometry Property, we show that stable recovery holds when the number of measurements is proportional to the prior's intrinsic dimension.
  arXiv  Detail & Related papers  (2026-03-03T17:52:18Z)
• Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function [0.0]
  We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space under a learned, time-dependent Hamiltonian.<n> Token probabilities are extracted using the Born rule, a quadratic measurement operator that couples magnitudes and relative phases.<n>We derive a continuity equation for the latent probability mass, yielding conserved pairwise currents that serve as a built-in diagnostic.
  arXiv  Detail & Related papers  (2026-02-24T23:42:18Z)
• Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates [10.39662017167378]
  Uncertainty quantification (UQ) must be both computationally efficient and spatially faithful.<n>We propose a structure-aware UQ scheme that exploits the modular anatomy common to modern NOs.<n> Experiments on challenging PDE benchmarks demonstrate that the proposed structure-aware design yields more reliable coverage, tighter bands, and improved residual-uncertainty alignment.
  arXiv  Detail & Related papers  (2026-02-24T10:17:24Z)
• Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds [1.1668521361095043]
  We present a generative modeling framework for physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions.<n>Our approach integrates three complementary components: (1) a boundary-conditioned diffusion model operating on velocity fields; (2) a physics-informed training objective incorporating a divergence penalty; and (3) a projection-constrained reverse diffusion process that enforces exact incompressibility through a geometry-aware Helmholtz-Hodge operator.
  arXiv  Detail & Related papers  (2026-02-19T19:10:27Z)
• Latent-Variable Learning of SPDEs via Wiener Chaos [2.0901018134712297]
  We study the problem of learning the law of linear partial differential equations (SPDEs) with additive Gaussian forcing from observations.<n>Our approach combines a spectral Galerkin projection with a truncated Wiener chaos expansion, yielding a separation between evolution and forcing domains.<n>This reduces the infinite-dimensional deterministic SPDE to a finite system of parametrized ordinary differential equations governing latent temporal dynamics.
  arXiv  Detail & Related papers  (2026-02-12T10:19:43Z)
• Fast-Forward Lattice Boltzmann: Learning Kinetic Behaviour with Physics-Informed Neural Operators [37.65214107289304]
  We introduce a physics-informed neural operator framework for the lattice Boltzmann equation (LBE)<n>Our framework is discretization-invariant, enabling models trained on coarse lattices to generalise to finer ones.<n>Results demonstrate robustness across complex flow scenarios, including von Karman vortex shedding, ligament breakup, and bubble adhesion.
  arXiv  Detail & Related papers  (2025-09-26T14:36:23Z)
• Error Analysis of Discrete Flow with Generator Matching [34.847768962128164]
  We develop a unified framework grounded in calculus theory to investigate the theoretical properties of discrete flow models.<n>Specifically, we derive the KL divergence of two path measures regarding two continuous-time Markov chains with different transition rates.<n>We provide a comprehensive analysis that encompasses the error arising from transition rate estimation and early stopping.
  arXiv  Detail & Related papers  (2025-09-26T05:41:45Z)
• Neural equilibria for long-term prediction of nonlinear conservation laws [38.88412478541979]
  We introduce Neural Discrete Equilibrium (NeurDE), a machine learning (ML) approach for long-term forecasting of flow phenomena.<n>We show that NeurDE enables accurate prediction of compressible flows, including supersonic flows, while tracking shocks over hundreds of time steps.
  arXiv  Detail & Related papers  (2025-01-12T21:02:20Z)
• Sufficient condition for gapless spin-boson Lindbladians, and its connection to dissipative time-crystals [64.76138964691705]
  We discuss a sufficient condition for gapless excitations in the Lindbladian master equation for collective spin-boson systems. We argue that gapless modes can lead to persistent dynamics in the spin observables with the possible formation of dissipative time-crystals.
  arXiv  Detail & Related papers  (2022-09-26T18:34:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.