arXiv subjects

Ricardo Vinuesa

Publications and source records attributed to Ricardo Vinuesa.

At least 19 recordsLinked to original sources

arXiv2026

AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling

High-fidelity CFD is essential for aerodynamic design, but repeated simulations are computationally expensive, motivating surrogate models for rapid evaluation across geometries and operating conditions. Most existing surrogates are designed for direct field regression, requiring the evaluation of millions of field points even when only an aerodynamic quantity or a localized region is needed, while their internal representations are not intended for direct use in downstream tasks. We introduce AeroJEPA, a framework inspired by joint-embedding predictive architectures that represents the problem in two distinct latent spaces: context tokens encode geometry, while predicted tokens encode the aerodynamic state. Both representations remain directly accessible for downstream tasks, such as linear readouts of design variables and aerodynamic quantities without decoding and integrating the full field. When spatial detail is needed, a continuous implicit decoder evaluates the field only at the requested coordinates while reusing the encoded geometry. We evaluate AeroJEPA on HiLiftAeroML, with multi-million-point fields, and SuperWing, which spans a broad family of transonic wings. Compared with state-of-the-art direct-regression surrogates, AeroJEPA trades peak full-field accuracy for compact, reusable representations. In our selective-decoding experiment, however, AeroJEPA substantially outperforms the evaluated direct-regression surrogates while avoiding predictions over the remainder of the aircraft. The learned representations further support controlled interpolation, concept-vector arithmetic, and preliminary constrained latent-space optimization. These results show how predictive representations can support aerodynamic analysis with or without full-field reconstruction.

cs.LG↗

arXiv2026

Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments

Rapid urbanization demands efficient monitoring of turbulent wind and pollutant dispersion, yet existing reconstruction and sensor placement strategies fail under realistic sparsity constraints. Here, we introduce Diff--SPORT, a diffusion-based framework that combines a generative diffusion prior with maximum a posteriori inference and Shapley-value attribution for high-fidelity flow reconstruction and optimal sensor placement. By training a diffusion prior model once over a domain, Diff--SPORT enables non-linear optimal sensor placement and near-real-time flow reconstruction from sparse measurements orders of magnitude faster than RANS or LES simulations, consistently outperforming state-of-the-art methods. The framework also extends, without algorithmic modification, to experimental passive scalar concentration dataset, a direct proxy for pollutant dispersion, measured in a 1:2400 scale water-flume model of the Beijing Haidian neighbourhood under realistic urban flow conditions. Shapley-guided sensor placement achieves up to 57\% lower reconstruction error than randomly placed sensors at extreme sparsity, identifying compact and physically interpretable configurations. These results establish Diff--SPORT as a modular foundation offering a zero-shot alternative to retraining-intensive downstream strategies, supporting scalable urban flow monitoring for air quality management and resilient city design.

physics.flu-dyn↗

arXiv2026

Unveiling wing turbulence dynamics through explainable deep learning

The three-dimensional organization of coherent structures in the turbulent flow over aircraft wings remains elusive, limiting our ability to reduce fuel consumption. Here, we use explainable artificial intelligence to characterize these structures by predicted flow evolution rather than classical predefined kinematic criteria. After training a deep neural network to predict the short-term evolution of the flow, we identify the highest-relevance flow regions using Shapley-value attribution methods. We have found that as the flow decelerates towards the trailing edge, predictive importance shifts from near-wall low-speed structures to three-dimensional pairs of high- and low-speed fluid regions. Matching no single classical structure family, these pairs progressively dominate the dynamically relevant flow. Most stand spanwise side-by-side, enclosing a near-vertical momentum interface with the strongest velocity jump. Their geometry remains invariant in viscous units while their volume expands when approaching separation. Our results reveal a predictive organization that traditional paradigms overlook, opening new ways to control turbulent flows.

physics.flu-dyn↗

arXiv2026

Low-dimensional Galerkin projection models for predicting turbulent secondary mean flow in a square duct

The presence of sidewalls in turbulent duct flows leads to the emergence of secondary flow structures in the form of counter-rotating streamwise vortices near the corners (Prandtl's secondary flow of the second kind). This work develops reduced-order Galerkin projection models that can predict the emergence and structure of these turbulent mean secondary flows in a square duct geometry, without requiring any prior knowledge of the turbulent statistics. The models are obtained by projecting the Navier--Stokes equations onto eigenmodes of the linearised system, with the resulting systems of ordinary differential equations simulated with the addition of zero-mean forcing. We show that most models obtained using leading streamwise-constant eigenmodes predict the correct shape and direction of the secondary mean, with the minimal such model requiring only two modes. In these models, the secondary mean contribution arises due to the nonzero average coefficient of an eigenmode that possesses all of the symmetry properties expected of a secondary mean. The models are sufficiently simple such that the relationship between this mean coefficient and the joint second moment of other mode coefficients can be computed analytically. We confirm that running streamwise-constant direct numerical simulations (DNS) with the same forcing structure as used in the reduced-order models produces similar secondary-flow structures. We additionally demonstrate that our models produce qualitatively similar Reynolds stress distributions to fully resolved direct numerical simulations, with improved agreement as model dimension increases.

physics.flu-dyn↗

arXiv2026

GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion Guidance

Urban wind flow reconstruction is essential for assessing air quality, heat dispersion, and pedestrian comfort, yet remains challenging when only sparse sensor data are available. We propose GenDA, a generative data assimilation framework that reconstructs high-resolution wind fields on unstructured meshes from limited observations. The model employs a multiscale graph-based diffusion architecture trained on computational fluid dynamics (CFD) simulations and interprets classifier-free guidance as a learned posterior reconstruction mechanism: the unconditional branch learns a geometry-aware flow prior, while the sensor-conditioned branch injects observational constraints during sampling. This formulation enables obstacle-aware reconstruction and generalization to held-out mesh geometries, wind directions, and sensor configurations within the studied urban-flow setting, without retraining. We consider both sparse fixed sensors and trajectory-based observations using the same reconstruction procedure. When evaluated against supervised graph neural network (GNN) baselines and classical reduced-order data assimilation methods, GenDA reduces the relative root-mean-square error (RRMSE) by 25-57% and increases the structural similarity index (SSIM) by 23-33% across the tested meshes. Experiments are conducted on Reynolds-averaged Navier-Stokes (RANS) simulations of a real urban neighborhood in Bristol, United Kingdom, at a characteristic Reynolds number of $\mathrm{Re}\approx2\times10^{7}$, featuring complex building geometry and irregular terrain. The proposed framework provides a scalable path toward generative, geometry-aware data assimilation for environmental monitoring in complex domains.

cs.LG↗

arXiv2026

The HydroGym Reinforcement Learning Platform for Fluid Dynamics

Modeling and controlling fluids is critical across science and engineering. Effective flow control can increase lift, reduce drag, enhance mixing, and attenuate noise, potentially unlocking new technologies. Yet controlling fluids is hard: the dynamics are high-dimensional, nonlinear, and multiscale. While reinforcement learning (RL) has recently succeeded in robotics and protein folding through shared benchmarks, fluid dynamics has resisted such progress: each controller is typically tuned to a single geometry and operating point, making results hard to accumulate, transfer, and compare. We introduce HydroGym, a solver-independent RL platform for flow control, and show that standardized infrastructure unlocks transferable control intelligence across flow regimes. HydroGym provides 61+ validated environments spanning laminar to turbulent flows, with systematic Reynolds number progressions up to Re=400,000 and Mach number variations in 2D and 3D. It supports diverse backends, including finite-volume, spectral-element, finite-element, lattice-Boltzmann, and fully differentiable solvers for gradient-enhanced optimization. Across environments, RL agents consistently discover robust control principles, such as boundary-layer manipulation, acoustic-feedback disruption, and wake reorganization, yielding drag reductions exceeding 90% in canonical configurations. Critically, we demonstrate zero-shot transfer: agents trained only on a simplified channel flow achieve 38% friction-drag reduction on an unseen 3D wing section at chord Reynolds number Re=200,000 reducing exploration costs by four orders of magnitude versus direct on-wing optimization. This suggests RL agents uncover essential physics rather than configuration-specific patterns, pointing toward generalizable control. HydroGym offers extensible, scalable community infrastructure for fluid dynamics, machine learning, and control research.

physics.flu-dyn↗

arXiv2026

Weak Dominant Balance for Robust Identification of Dynamically Consistent Fluid Flow Structure

Extracting interpretable, localized physical mechanisms from complex spatiotemporal data is a foundational challenge across physics, biology, and engineering, but has remained out of reach on real measurements. The central obstacle is obtaining high-quality gradients of data via numerical differentiation, which amplifies noise, diverges for high-order equations, and falters on irregular geometries, limiting the scope of existing approaches to clean simulations of low-order systems. Here, we present weak dominant balance, a derivative-free framework that projects governing equations into a weak (integral) formulation, offloading differentiation onto smooth analytical test functions and leaving the data untouched. The method sustains accurate regime identification under severe noise where existing approaches categorically fail, delivers the first data-driven decomposition of a third-order partial differential equation applied to turbulent duct flow, and produces matching decompositions across direct numerical simulation and particle-image velocimetry measurements of a wavy channel flow, uncovering a previously uncharacterized dynamical regime. Weak dominant balance brings mechanism-level analysis out of simulation and onto measured data, and opens complex physical systems to direct, equation-grounded interpretation.

cs.CE↗

arXiv2026

Low-Cost High-Order Singular Value Decomposition for Tensor-Based Reconstruction from Sparse Sensor Measurements: Urban Flow and Air-Quality Applications

Urban flow and air-quality simulations generate high-dimensional datasets describing velocity and pollutant transport across multiple spatial, temporal, and physical-variable dimensions. Reconstructing these fields from sparse sensor measurements is a fundamental challenge in environmental monitoring, digital twins, forecasting, and data assimilation. Existing low-cost reconstruction approaches are commonly based on matrix decompositions, which require multidimensional datasets to be flattened into two-dimensional snapshot matrices, thereby discarding important structural information. This work introduces the low-cost High-Order Singular Value Decomposition (lcHOSVD), a novel tensor-based sparse-sensing reconstruction framework for high-dimensional environmental fields. To the authors' knowledge, this is the first methodology that combines sparse sensing and HOSVD for field reconstruction. Unlike matrix-based approaches, lcHOSVD preserves the natural tensor structure of the data, enabling the exploitation of correlations across spatial, temporal, and physical-variable dimensions while substantially reducing the computational requirements of conventional HOSVD. The methodology is applied to urban flow and air-quality datasets, where three-dimensional velocity and pollutant concentration fields are reconstructed using only 1-4% of the available spatial locations. While lcSVD provides larger computational speed-ups, lcHOSVD consistently achieves lower reconstruction errors in configurations characterized by strong multidimensional coupling and heterogeneous dynamics across dimensions. Additional sensor-anisotropy analyses demonstrate that the tensor formulation is significantly more robust to uneven sensor distributions, a common situation in practical environmental monitoring networks.

cs.LG↗

arXiv2026

The near-wall cycle for skin-friction generation revealed through explainable deep learning

Skin friction in wall-bounded turbulence is produced by intermittent near-wall motions, yet conventional coherent-structure definitions do not identify which individual events generate wall-shear stress, and thus friction. We train neural networks to predict the future velocity field and wall-shear-stress distribution in turbulent channel flow, and use SHAP-derived importance maps to identify the the input regions most influential for each prediction. The dominant events appear as paired objects: an upstream velocity-relevant region is associated with high-momentum motion toward the wall, while a downstream friction-relevant region marks the enhanced wall-shear-stress left in its wake. Tracking these pairs reveals a recurrent cycle of growth, streamwise elongation, decay, and occasional splitting into new wall-shear-producing events. These results redefine near-wall coherent structures not by what the flow looks like, but by what they do to wall-shear stress.

physics.flu-dyn↗

arXiv2026

A Hybrid Generative Reduced-Order Model for the Minimal Flow Unit

A data-driven reduced-order modelling framework is proposed for wall-bounded turbulent flows to forecast the intermittent near-wall dynamics over extended time horizons from sparse sensor measurements. The approach combines a $β$-VAE-GAN, which compresses high-dimensional flow fields into a low-dimensional latent space, with a sensor-conditioned Transformer that forecasts the evolution of the latent variables. The temporal module employs Easy Attention, a static time-mixing operator that replaces the learnable query-key mechanism of standard self-attention at reduced computational cost, combined with an adapted AdaLN-Zero modulation mechanism for sensor-based conditioning. Evaluated on the Minimal Flow Unit ($Re_τ= 200$) at $y^+ = 14$, the compression stage recovers $87\%$ of the turbulent kinetic energy within a four-dimensional latent space, exceeding the standard $β$-VAE baseline by more than $10\%$. The latent dimensions autonomously encode the characteristic timescales of the flow, with specific coordinates capturing the low-frequency signature of the near-wall regeneration cycle ($T^+ \approx 1724$), establishing the physical interpretability of the learnt representation. The sensor-conditioned Transformer maintains accurate forecasts over $17{,}288\,t^+$ from an initialisation window of only $128\,t^+$, whilst end-to-end inference reconstructs $82\%$ of the turbulent kinetic energy. The principal limitation is the attenuation of rare, extreme-amplitude events, a consequence of the encoder prioritising the most statistically recurrent flow states within the low-dimensional bottleneck. Nevertheless, the framework accurately reproduces the alternating active and quiescent phases of the regeneration cycle, demonstrating its suitability as a surrogate model for the intermittent dynamics of wall-bounded turbulence.

physics.flu-dyn↗

arXiv2026

Explainable deep reinforcement learning reveals energy-efficient control strategies for turbulent drag reduction

We propose a method combining Multi-Agent Deep Reinforcement Learning (MARL) and eXplainable Deep Learning (XDL) to reduce drag in wall-bounded turbulent flows. Taking as a baseline the results of training agents directly targeting wall-shear stress and opposition control, three SHAP-guided approaches are compared. In the first, the reward is computed from SHAP attributions of a U-net predicting the future velocity field; in the second, from SHAP attributions of a U-net predicting the skin-friction coefficient; in the third, from a combination of SHAP attributions of two U-nets predicting the skin-friction coefficient and the wall pressure fluctuations, respectively. The combined SHAP strategy based on skin-friction coefficient and wall-pressure fluctuations achieves the best overall performance, achieving a DR of 34.44% and a NES of 34.01% with only 0.43% normalized input power. Relative to opposition control, drag reduction and net energy saving increase by 49.41% and 48.52%, respectively. Compared with the direct wall-shear-stress baseline, the proposed strategy simultaneously improves performance while reducing the normalized actuation cost from 5.90% to 0.43%. Analysis of the results reveals that the energetically efficient policy is consistent with pressure-gated actuation, activating predominantly at near-zero wall pressure, and operates on a temporal timescale comparable to the lifetime of the near-wall turbulent structures.

cs.LG↗

arXiv2026

Improving turbulence control through explainable deep learning

Turbulent-flow control aims to develop strategies that effectively manipulate fluid systems, such as the reduction of drag in transportation and enhancing energy efficiency, both critical steps towards reducing global CO$_2$ emissions. Deep reinforcement learning (DRL) offers novel tools to discover flow-control strategies, which we combine with our knowledge of the physics of turbulence. We integrate explainable deep learning (XDL) to objectively identify the coherent structures containing the most informative regions in the flow, with a DRL model trained to reduce them. The model trained with XDL targets the most relevant regions in the flow to sustain turbulence and produces a drag reduction which is higher than that of a model specifically trained to reduce the drag, resulting in a $18.1\%$ better net-energy saving. The XDL-based control remains the most effective control strategy when generalizing across Reynolds numbers and geometries. This demonstrates that combining DRL with XDL can produce causal control strategies that precisely target the most influential features of turbulence. By directly addressing the core mechanisms that sustain turbulence, our approach offers a powerful pathway towards its efficient control, which is a long-standing challenge in physics with profound implications for energy systems, climate modeling and aerodynamics.

physics.flu-dyn↗

arXiv2026

Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering

Skin-friction drag induced by wall-bounded turbulent flows accounts for a substantial fraction of energy consumption across commercial aerospace, wind energy, and marine transport. Its active reduction is one of the highest-value targets in engineering fluid dynamics. Deep reinforcement learning (DRL) has emerged as the leading approach for real-time flow control, yet its performance ceiling is set not by algorithmic capability but by reward structure, the naive scalar objective does not optimally reflect the underlying physics. Policy-DRIFT bypasses this ceiling by relocating reward information from policy gradients to generative model inference: a conditional flow matching model (CFM) constructs a physically-grounded manifold of realisable flow states spanning multiple control regimes, Terminal Reward Guidance (TRG) steers samples toward reward-maximising targets at inference, and a lightweight DRL policy, structurally decoupled from reward quality, tracks these full-field targets via root-mean-squared error (RMSE) minimisation. The test case is turbulent channel flow simulated using direct numerical simulation (DNS) at friction Reynolds number of $\mathrm{Re}_τ= 180$, which is the canonical benchmark for wall-bounded turbulence. Policy-DRIFT achieves $49\%$ drag reduction approaching the theoretical upper bound, which is $\approx 16\%$ higher than the DRL benchmark, while consuming 37$\times$ less actuation energy. Our approach combines generative methods with active flow control, marking a paradigm shift towards controlling complex physical systems efficiently.

physics.flu-dyn↗

arXiv2026

High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning

This study investigates active flow control (AFC) of a 30P30N high-lift wing at a Reynolds number Re$_c$ = 450,000 and angle of attack $α$ = 23$^\circ$ using wallresolved large-eddy simulations (LES). Two optimization strategies are explored: open-loop Bayesian optimization (BO) and closed-loop deep reinforcement learning (DRL), both targeting the mitigation of stall and the improvement of aerodynamic efficiency via synthetic jets on the slat, main, and flap elements. The uncontrolled configuration was validated against literature data, confirming the reliability of the LES setup. The BO framework successfully identified steady jet velocities that increased efficiency by +10.9% through a -9.7% drag reduction while maintaining lift. In contrast, the DRL agent, despite leveraging instantaneous flow information from distributed sensors, achieved only minor improvements in lift and drag, with negligible efficiency gain. Training analysis indicated that the penalty-dominated reward constrained exploration. These results highlight the need for carefully designed rewards and computational acceleration strategies in DRL-based flow control at high Reynolds numbers.

physics.flu-dyn↗

arXiv2026

Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI

4D Flow Magnetic Resonance Imaging (4D Flow MRI) enables non-invasive quantification of blood flow and hemodynamic parameters. However, its clinical application is limited by low spatial resolution and noise, particularly affecting near-wall velocity measurements. Machine learning-based super-resolution has shown promise in addressing these limitations, but challenges remain, not least in recovering near-wall velocities. Generative adversarial networks (GANs) offer a compelling solution, having demonstrated strong capabilities in restoring sharp boundaries in non-medical super-resolution tasks. Yet, their application in 4D Flow MRI remains unexplored, with implementation challenged by known issues such as training instability and non-convergence. In this study, we investigate GAN-based super-resolution in 4D Flow MRI. Training and validation were conducted using patient-specific cerebrovascular in-silico models, converted into synthetic images via an MR-true reconstruction pipeline. A dedicated GAN architecture was implemented and evaluated across three adversarial loss functions: Vanilla, Relativistic, and Wasserstein. Our results demonstrate that the proposed GAN improved near-wall velocity recovery compared to a non-adversarial reference (vNRMSE: 6.9% vs. 9.6%); however, that implementation specifics are critical for stable network training. While Vanilla and Relativistic GANs proved unstable compared to generator-only training (vNRMSE: 8.1% and 7.8% vs. 7.2%), a Wasserstein GAN demonstrated optimal stability and incremental improvement (vNRMSE: 6.9% vs. 7.2%). The Wasserstein GAN further outperformed the generator-only baseline at low SNR (vNRMSE: 8.7% vs. 10.7%). These findings highlight the potential of GAN-based super-resolution in enhancing 4D Flow MRI, particularly in challenging cerebrovascular regions, while emphasizing the need for careful selection of adversarial strategies.

eess.IV↗

arXiv2026

Timescale Separation Enables Deep Reinforcement Learning Control of Rotating Detonation Engine Mode Transitions

Rotating detonation engines (RDEs) are a promising propulsion concept that may offer higher thermodynamic efficiency and specific impulse than conventional systems, but nonlinear phenomena, including transitions to oscillatory or chaotic propagation modes, can hinder practical operation. Deep Reinforcement Learning (DRL) has emerged as a promising method for controlling complex nonlinear dynamics such as those observed in RDEs. However, the multi-timescale nature of the RDE system makes direct application of DRL challenging. We address this challenge by reformulating the DRL problem in a moving reference frame that follows the detonation-wave pattern, making the wave structure appear quasi-steady to the agent. This reformulation enables scale separation between fast detonation propagation and slower operating-mode dynamics. We train DRL controllers to modulate spatially segmented injection pressure in a one-dimensional reduced-order RDE model and induce rapid transitions between different mode-locked states. Across a range of actuation periods, initial states, and target modes, controllers trained in the moving frame learn more reliably than those trained in a stationary frame and remain effective over a broader range of actuation periods. These results suggest that symmetry-aware moving reference frame formulations may be useful for related multiscale flow-control problems and that scale separation should be exploited whenever possible to enable DRL control of multi-timescale systems.

physics.flu-dyn↗

arXiv2026

Physics-guided surrogate learning enables zero-shot control of turbulent wings

Turbulent boundary layers over aerodynamic surfaces are a major source of aircraft drag, yet their control remains challenging due to multiscale dynamics and spatial variability, particularly under adverse pressure gradients. Reinforcement learning has outperformed state-of-the-art strategies in canonical flows, but its application to realistic geometries is limited by computational cost and transferability. Here we show that these limitations can be overcome by exploiting local structures of wall-bounded turbulence. Policies are trained in turbulent channel flows matched to wing boundary-layer statistics and deployed directly onto a NACA4412 wing at $Re_c=2\times10^5$ without further training, being the so-called zero-shot control. This achieves a 28.7% reduction in skin-friction drag and a 10.7% reduction in total drag, outperforming the state-of-the-art opposition control by 40% in friction drag reduction and 5% in total drag. Training cost is reduced by four orders of magnitude relative to on-wing training, enabling scalable flow control.

physics.flu-dyn↗

arXiv2026

VIVALDy: A Hybrid Generative Reduced-Order Model for Turbulent Flows, Applied to Vortex-Induced Vibrations

Developing reduced-order models applicable to fluid-dynamics problems involving complex geometries and different flow conditions remains a critical challenge for turbulent flows. This study introduces VIVALDy, a novel machine-learning framework that employs a hybrid $β$-Variational Autoencoder-Generative Adversarial Network ($β$-VAE-GAN) architecture with masked convolutions to extract dominant flow features into a compact latent space while preserving fidelity at solid-fluid interfaces. A bidirectional transformer then models the temporal evolution of these features, learning to predict flow trajectories from minimal sensor inputs. This two-stage approach enables the transformer to map sensor measurements to dominant flow variables identified by the autoencoder, advancing reduced-order modeling capabilities for real-time flow prediction. The effectiveness of the framework is demonstrated through application to a problem relevant to vortex-induced vibration (VIV) energy harvesting systems, reconstructing the turbulent flow around a one-degree-of-freedom moving cylinder. Validated against experimental data spanning fluid-structure interaction regimes of interest, VIVALDy accurately predicts different flow states using only the cylinder displacement. The framework demonstrates adequate performance in both reconstruction accuracy and statistical fidelity across diverse operating conditions, enabling efficient prediction of the turbulent flow phenomena governing vortex-induced vibration.

physics.flu-dyn↗