Papers for

fluid dynamics engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Tensor sampling and recovery improve dynamical system reconstructions

Dynamics-Aware Sampling and Recovery for Tensor-Valued Dynamical Systems

Abstract: We study sampling and recovery for tensor-valued dynamical systems evolving under the t-product, using partial spatial observations over time. Although the t-product Fourier transform yields slicewise matrix dynamics, recovery does not generally decouple across slices. Eigenvalues shared across Fourier-domain frontal slices couple the corresponding eigenspaces into aggregated spectral blocks, which determine the tensor-specific recovery geometry and space--time tradeoff. We establish deterministic identifiability conditions for the initial tensor state. In the diagonalizable case, these are frame conditions on the aggregated blocks. We extend them to non-diagonalizable systems through generalized eigenspaces and Jordan structure. A temporal--spectral factorization of the finite-horizon stacked recovery system underlying Tensor Dynamical Sampling (DS) yields a decoupled two-stage formulation once the temporal threshold is reached. Under independent spatial subsampling, we prove high-probability recovery guarantees using empirical Gram matrices on the aggregated blocks. The bounds depend on aggregated multiplicities, incoherence, and population conditioning. Stability estimates separate the spatial frame factor from the temporal Vandermonde factor and show that increasing temporal depth may worsen numerical conditioning even after identifiability is ensured. We implement Tensor DS and evaluate it on synthetic and real data. Phase transitions track the predicted blockwise sampling thresholds, and stability experiments illustrate Vandermonde conditioning. Experiments on sea surface temperature and turbulence velocity data show that a learned t-product system operator generally yields more accurate and structurally faithful reconstructions than vectorized low-rank, Tucker-type, graph-regularized, graph-spectral, and vectorized dynamical sampling baselines.

Sun 25 OctInformation Theory
The gist
This paper studies how to best sample and reconstruct complex evolving systems that can be represented as tensors—multi-dimensional arrays—rather than simple vectors or matrices. The authors explore how information shared across different frequency components of these tensors affects recovery and identify mathematical conditions that guarantee successful reconstruction from limited spatial observations over time. They show that while observing more time steps can help, it may also introduce numerical difficulties due to complex matrix structures. Their methods are tested on both synthetic data and real-world examples like sea surface temperatures and turbulent flows, demonstrating better accuracy and structure preservation compared to existing techniques.
Open → 2610.34621v1

Structure preserving diagnostics reveal true physics in pde models

Structure-preserving fidelity diagnostics for partial differential equations

Abstract: Machine learning surrogates of partial differential equations (PDEs) are commonly trained on data generated by numerical solvers. Therefore, the training data obey not the PDE but the modified equation of the numerical scheme, and the test loss, computed on data from the same solver, cannot distinguish a model that learned the physics from one that learned the discretization error. Here, we show that the difference is nevertheless visible in the trained model. We propose a suite of structure-preserving fidelity diagnostics, simple scores that measure whether a learned model respects one known property of the physics, such as a conserved quantity, a symmetry or a Hamiltonian structure, without access to the training data or the governing equation. Over five systems, the diagnostics track the error with respect to the true dynamics with a rank correlation of up to $0.94$, while the test loss is uncorrelated or anti-correlated with it. For the Burgers, Korteweg-de Vries and Navier-Stokes equations, the diagnostics separate numerical schemes that the test loss ranks as equivalent, including schemes of the same order. order.

Mon 12 OctMachine Learning
The gist
When computers learn to mimic physical laws described by partial differential equations (PDEs), they train on messy data that includes errors from how the data was generated. This can make it hard to tell if the model really understands the physics or just copied the errors. The authors introduce simple tests that check if these learned models keep key physical properties like conservation rules or symmetries. Their tests can tell which models truly respect the physics better than traditional accuracy tests, even when standard tests see models as equally good.
Open → 2610.17483v1

Physics foundation models improve control of fluid flows efficiently

Physics Foundation Models for Efficient Control of Fluid Flows

Abstract: We investigate whether a physics foundation model (PFM) pretrained for PDE forecasting can be repurposed for closed-loop fluid-flow control. We construct a PFM-based controller by attaching lightweight Gaussian actor and critic heads to frozen pretrained representations and train the policy using proximal policy optimization (PPO). We evaluate the approach on HydroGym's two-dimensional Kolmogorov-flow environment using vorticity observations at \(64\times64\) and \(128\times128\) resolutions and Reynolds numbers \(\mathrm{Re}=100\) and \(200\). Across these settings, we compare the frozen PFM controller against a baseline MLP policy trained with the same PPO framework. The PFM controller achieves consistently higher reward while requiring smaller executed action magnitudes over training, indicating improved control performance with reduced control effort. These results provide initial evidence that representations learned through self-supervised next-frame prediction can be transferred directly to closed-loop fluid flow control. Project page: https://mahindrautela.github.io/morph.

Sat 10 OctMachine Learning
The gist
Controlling how fluids move can be very complicated and needs smart methods. The authors study if a special type of computer model, trained to predict fluid patterns, can also be used to control fluids in real time. They show their model works better and uses less effort than a typical approach. This suggests that these physics-based models can learn useful ways to control fluids without extra training from scratch.
Open → 2610.15173v1

Seq-Flow improves forecast updates using fewer sampling steps

Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control

Abstract: Many scientific forecasting tasks require updating a distribution over future trajectories as new observations arrive. Conventional diffusion and flow models generate each forecast from Gaussian noise, often at the cost of many sampling steps. Warm-start methods reuse earlier predictions to reduce this cost, but their models are not trained to perform the forecast update itself, which can compromise quality under few-step sampling. In this work, we introduce Seq-Flow, a conditional flow model whose ODE transports samples from the previous forecast distribution to the updated one. Because successive forecasts often differ only modestly, this transport starts from an informative distribution and can produce accurate updates with few flow evaluations. Recursive reuse also creates a challenge: errors in one forecast become errors in the initial states of subsequent flows. We address this with self-rollout training, in which a moving average copy of the model generates forecasts that initialize later training updates. Unlike self-forcing methods, which reuse generated outputs as conditioning context, Seq-Flow reuses them as the source of the next flow. Experiments On particle-accelerator beam spill forecasting show Seq-Flow reduces CRPS by 65% under a few-NFE sampling budget, while remaining competitive with strong baselines on fluid-dynamics forecasting tasks. Although trained on self-rollouts of at most four updates, Seq-Flow remains accurate over more than 400 consecutive updates. Our code is available at https://github.com/Graph-COM/Seq-Flow.

Wed 7 OctMachine Learning
The gist
Forecasting how something will change over time can be hard because predictions often need to be updated with new information. The authors propose Seq-Flow, a method that improves these updates by transforming old predictions into new ones directly, making it faster and more accurate when only a few update steps are used. They also developed a training approach that helps the method avoid building up errors over many updates. Experiments show Seq-Flow can give better predictions in scientific tasks like particle accelerator and fluid dynamics forecasting, even when making hundreds of updates.
Open → 2610.10440v1

Advectra improves modeling of moving physics in fluid flows

Advectra: Asymmetric Latent Transport for Non-Stationary Physics

Abstract: Many latent neural operators represent input and output fields in a stationary latent chart. In particular, common latent routing mechanisms use fixed or shared assignment weights for feature projection and reconstruction, limiting their ability to model transport-dominated systems where coherent structures move relative to fixed coordinate frames. We propose Advectra, a transport-aware latent operator that introduces a regularized kinematic coordinate map to decouple source and target coordinate systems. This yields an approximately co-moving latent reference frame and enables asymmetric feature aggregation and reconstruction. Combined with a geometry-aware ordering mechanism for state-space models, Advectra captures advective dynamics while maintaining stable global interactions. Advectra achieves the best performance among evaluated geometry-constrained and form-free baselines on advection-dominated benchmarks, including passive scalar transport in Navier--Stokes flows and Rayleigh--Taylor instability, while demonstrating strong generalization on real-world engineering tasks. These results highlight the benefit of explicit moving-frame structure in neural operators for non-stationary physics.

Sun 4 OctMachine Learning
The gist
Modeling how things like smoke or fluids move and change over time is hard because their shapes and positions keep changing. This paper presents Advectra, a new approach that follows moving parts instead of assuming everything stays in one place. By doing this, Advectra better captures the flow and movement patterns, making it more accurate in predicting complex fluid behaviors. The authors tested it on common physics problems and real engineering tasks, showing it works well even when things move a lot.
Open → 2610.05098v1

Variational latent models improve long horizon pde predictions

Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction

Abstract: Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution shift and accumulate under recursive deployment. We develop a variational approach to this problem by introducing latent Markov dynamics in which physical states are represented by latent distributions and evolved through probabilistic transitions. The framework is formulated directly on function spaces and specialized to functional Gaussian models, where structured latent perturbations induce a spectral geometry and variational transition alignment regularizes the learned dynamics. We further analyze how these mechanisms affect autoregressive error propagation, providing a theoretical connection between variational training and long-horizon prediction. We instantiate the framework as the Variational Autoencoding Markov Operator (VAMO), which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition. Empirically, we demonstrate the effectiveness of VAMO on several fluid-dynamics benchmarks with prediction horizons extending substantially beyond those represented during training, where it consistently reduces error accumulation and improves rollout stability over several deterministic and noise-injection baselines. Overall, these results highlight variational modeling as a complementary approach to robust long-horizon neural PDE dynamics.

Tue 15 SeptMachine Learning
The gist
Predicting how physical systems change over time using neural networks is hard because small errors add up. The authors developed a method that represents the system in a way that focuses on probabilities and smooth transitions, helping avoid growing mistakes. Their approach models the system’s hidden states with special math tools called variational latent distributions and Gaussian processes. This helps their predictions for things like fluid flow stay accurate even when looking far into the future.
Open → 2609.16621v1