arXiv subjects

Michele Buzzicotti

Publications and source records attributed to Michele Buzzicotti.

At least 19 recordsLinked to original sources

arXiv2026

Gappy Reconstruction of Bubbly Flows by Guided Diffusion Models

Experiments in multiphase flows are often limited in their ability to simultaneously obtain velocity measurements in different phases. At the same time, flow reconstruction from phase-limited measurements is a challenging problem due to the substantially different velocity statistics across the phases. We address this problem for buoyancy-driven bubbly flows in the pseudo-turbulence regime by using a guided diffusion model. We train the model using two-dimensional slices of the velocity field extracted from fully resolved three-dimensional direct numerical simulations. The model generates physically realistic velocity fields both unconditionally and when conditioned on the surrounding liquid flow. The reconstructed bubble-phase velocity field accurately reproduces key statistical features of the flow. We further show that a simple patching procedure for adjacent two-dimensional slices enables a reasonable reconstruction of the three-dimensional flow inside a bubble. These results establish the potential of diffusion models to serve as generative priors for three-dimensional turbulent multiphase flows, opening a route toward the reconstruction of unobserved or experimentally inaccessible velocity fields from sparse, partial, or phase-limited measurements.

physics.flu-dyn↗

arXiv2026

Stochastic Multiscale Reconstruction of Lagrangian Turbulence via Guided Diffusion Models

Lagrangian turbulence is characterized by intermittent, fat-tailed fluctuations and nontrivial correlations across temporal scales, making a quantitative description of its full multiscale probability distribution a longstanding challenge. A particularly important question is whether unresolved fine-scale fluctuations can be inferred from coarse-grained trajectory information. Here, we address this problem by sampling the conditional distribution of unresolved fluctuations using a diffusion-model prior conditioned on large-scale dynamics obtained through a wavelet-based coarse-graining of Lagrangian trajectories. Using tracer trajectories from direct numerical simulations of homogeneous and isotropic turbulence at $Re_\lambda \simeq 310$, we show that the reconstructed signals recover scale-dependent intermittent statistics, including high-order structure functions, flatness, and local scaling exponents, together with cross-scale temporal correlations between resolved and unresolved fluctuations. The method also reproduces the broad stochastic variability of intermittent acceleration fluctuations conditioned on the same coarse-grained trajectory, whereas Gaussian-process reconstructions in wavelet representation suppress rare events. Our results show that small-scale Lagrangian intermittency can be modeled as a non-Gaussian conditional stochastic process constrained by coarse-scale dynamics and quantitatively reproduced through data-driven generative sampling.

physics.flu-dyn↗

arXiv2026

Turbulent pair dispersion with Stochastic Generative Diffusion Models

Recent advances in data-driven modeling have shown that diffusion models can successfully generate synthetic Lagrangian trajectories in turbulent flows. Building on this progress, we extend the method to the joint generation of pairs of Lagrangian velocity trajectories, enabling a fully data-driven representation of turbulent pair dispersion, a long-standing fundamental problem with broad relevance in fluid dynamics. We demonstrate that diffusion models accurately reproduce the evolution of particle-pair separation, including deviations from Richardson's classical scaling law, while simultaneously preserving all key single-particle statistical properties reported in previous studies. These findings underscore the potential of diffusion-based generative models to emulate high-dimensional, multi-scale turbulent dynamics, further establishing them as a powerful tool for scientific modeling and for future geophysical and astrophysical applications.

physics.flu-dyn↗

arXiv2026

Physics-Constrained Diffusion Model for Synthesis of 3D Turbulent Data

Synthesizing fully developed three-dimensional turbulent velocity fields remains a long-standing problem in fluid mechanics and an open challenge for generative modeling. The difficulty arises from the coexistence of extreme dimensionality, multiscale rough fluctuations and strong intermittency, together with exact physical constraints such as incompressibility and zero-mean momentum. We propose a physics-constrained diffusion model (PCDM) in which these \emph{a priori} constraints are incorporated directly into the generative dynamics. Using rotating turbulence as a stringent benchmark, we show that the proposed framework enables stable and statistically faithful synthesis of inertial-range three-dimensional turbulent velocity fields at medium resolution, accurately reproducing anisotropic energy spectra, intermittency statistics, and physical constraints. By contrast, standard denoising diffusion probabilistic models without such constraints exhibit multiscale statistical deviations, violations of physical consistency, and substantially slower training convergence. These findings point to broader implications for generative modeling of high-dimensional complex systems under physical constraints.

physics.flu-dyn↗

arXiv2026

Inferring the Turbulent Breakup of Colloidal Aggregates Using Graph Neural Networks

Solid aggregates in turbulent suspensions may break under the action of shear stresses. We explore the use of Graph Neural Networks (GNN) to infer aggregate fragmentation once the aggregate structure and flow velocity gradients are known. We consider two models: the first GNN is a classifier, trained to distinguish aggregates that break from those that do not; the second GNN is a regression model, trained to predict the maximal tensile force within each aggregate in a given flow condition. We show that both models complete their task with a high statistical accuracy, also generalizing to aggregates of different sizes, and generally performing better than the statistical prediction based on mean field quantities. This work paves the way for future use of GNN to quantify aggregate breakup in a large population of aggregates suspended in complex flow configurations, as it takes place in the wet production of fine powders and in the transport of sediments in environmental flows.

physics.flu-dyn↗

arXiv2025

Super-resolution of satellite-derived SST data via Generative Adversarial Networks

In this work, we address the super-resolution problem of satellite-derived sea surface temperature (SST) using deep generative models. Although standard gap-filling techniques are effective in producing spatially complete datasets, they inherently smooth out fine-scale features that may be critical for a better understanding of the ocean dynamics. We investigate the use of deep learning models as Autoencoders (AEs) and generative models as Conditional-Generative Adversarial Networks (C-GANs), to reconstruct small-scale structures lost during interpolation. Our supervised -- model free -- training is based on SST observations of the Mediterranean Sea, with a focus on learning the conditional distribution of high-resolution fields given their low-resolution counterparts. We apply a tiling and merging strategy to deal with limited observational coverage and to ensure spatial continuity. Quantitative evaluations based on mean squared error metrics, spectral analysis, and gradient statistics show that while the AE reduces reconstruction error, it fails to recover high-frequency variability. In contrast, the C-GAN effectively restores the statistical properties of the true SST field at the cost of increasing the pointwise discrepancy with the ground truth observation. Our results highlight the potential of deep generative models to enhance the physical and statistical realism of gap-filled satellite data in oceanographic applications.

physics.ao-ph↗

arXiv2025

Deterministic diffusion models for Lagrangian turbulence: robustness and encoding of extreme events

Modeling Lagrangian turbulence remains a fundamental challenge due to its multiscale, intermittent, and non-Gaussian nature. Recent advances in data-driven diffusion models have enabled the generation of realistic Lagrangian velocity trajectories that accurately reproduce statistical properties across scales and capture rare extreme events. This study investigates three key aspects of diffusion-based modeling for Lagrangian turbulence. First, we assess architectural robustness by comparing a U-Net backbone with a transformer-based alternative, finding strong consistency in generated trajectories, with only minor discrepancies at small scales. Second, leveraging a deterministic variant of diffusion model formulation, namely the deterministic denoising diffusion implicit model (DDIM), we identify structured features in the initial latent noise that align consistently with extreme acceleration events. Third, we explore accelerated generation by reducing the number of diffusion steps, and find that DDIM enables substantial speedups with minimal loss of statistical fidelity. These findings highlight the robustness of diffusion models and their potential for interpretable, scalable modeling of complex turbulent systems.

physics.flu-dyn↗

arXiv2025

A posteriori closure of turbulence models: are symmetries preserved?

Turbulence modeling remains a longstanding challenge in fluid dynamics. Recent advances in data-driven methods have led to a surge of novel approaches aimed at addressing this problem. This work builds upon our recent work [Phys. Rev. Fluids 10, 044602 (2025)], where we introduced a new closure for a shell model of turbulence using an a posteriori (or solver-in-the-loop) approach. Unlike most deep learning-based models, our method explicitly incorporates physical equations into the neural network framework, ensuring that the closure remains constrained by the underlying physics benefiting from enhanced stability and generalizability. In this paper, we further analyze the learned closure, probing its capabilities and limitations. In particular, we look at joint probability density functions between resolved and unresolved variables, as well as the scale invariance of multipliers (ratios between adjacent shells) within the inertial range. Although our model excels in reproducing high-order statistical moments, it breaks this known symmetry near the cutoff, indicating a fundamental limitation. We discuss the implications of these findings for subgrid-scale modeling in 3D turbulence and outline directions for future research.

physics.flu-dyn↗

arXiv2024

Generation of cosmic ray trajectories by a Diffusion Model trained on test particles in 3D magnetohydrodynamic turbulence

Models for the transport of high energy charged particles through strong magnetic turbulence play a key role in space and astrophysical studies, such as describing the propagation of solar energetic particles and high energy cosmic rays. Inspired by the recent advances in high-performance machine learning techniques, we investigate the application of generative diffusion models to synthesizing test particle trajectories obtained from a turbulent magnetohydrodynamics simulation. We consider velocity increment, spatial transport and curvature statistics, and find excellent agreement with the baseline trajectories for fixed particle energies. Additionally, we consider two synthetic turbulence models for comparison. Finally, challenges towards an application-ready transport model based on our approach are discussed.

physics.flu-dyn↗

arXiv2024

Solver-in-the-loop approach to closure of shell models of turbulence

This work studies an a posteriori data-driven approach (known as solver-in-the-loop) for sub-grid modeling of a shell model for turbulence. This approach takes advantage of the differentiable physics paradigm of deep learning, allowing a neural network model to interact with the differential equation solver over time during the training process. The closure model is, then, naturally exposed to equations-informed input distributions by accounting for prior corrections over the temporal evolution in training. Such a characteristic makes this approach depart from the conventional a priori instantaneous training paradigm and often leads to a more accurate and stable closure model. Our study demonstrates that the closure learned via this a posteriori approach is able to reproduce high-order statistical moments of interest also in closures of high Reynolds number turbulence. Moreover, we investigate the performance of the learned model by experimenting with the effect of unrolling in time, which has remained for the most part unexplored in the literature. Finally, we discuss potential extensions of this approach to Navier-Stokes equations.

physics.flu-dyn↗

arXiv2024

Stochastic Reconstruction of Gappy Lagrangian Turbulent Signals by Conditional Diffusion Models

We present a stochastic method for reconstructing missing spatial and velocity data along the trajectories of small objects passively advected by turbulent flows with a wide range of temporal or spatial scales, such as small balloons in the atmosphere or drifters in the ocean. Our approach makes use of conditional generative diffusion models, a recently proposed data-driven machine learning technique. We solve the problem for two paradigmatic open problems, the case of 3D tracers in homogeneous and isotropic turbulence, and 2D trajectories from the NOAA-funded Global Drifter Program. We show that for both cases, our method is able to reconstruct velocity signals retaining non-trivial scale-by-scale properties that are highly non-Gaussian and intermittent. A key feature of our method is its flexibility in dealing with the location and shape of data gaps, as well as its ability to naturally exploit correlations between different components, leading to superior accuracy, with respect to Gaussian process regressions, for both pointwise reconstruction and statistical expressivity. Our method shows promising applications also to a wide range of other Lagrangian problems, including multi-particle dispersion in turbulence, dynamics of charged particles in astrophysics and plasma physics, and pedestrian dynamics.

physics.flu-dyn↗

arXiv2024

TURB-Lagr. A database of 3d Lagrangian trajectories in homogeneous and isotropic turbulence

We present TURB-Lagr, a new open database of 3d turbulent Lagrangian trajectories, obtained by Direct Numerical Simulations (DNS) of the original Navier-Stokes equations in the presence of a homogeneous and isotropic forcing. The aim is to provide the community interested in data-assimilation and/or Lagrangian-properties of turbulence a new testing-ground made of roughly 300K different Lagrangian trajectories. TURB-Lagr data are influenced by the strong non-Gaussian fluctuations characteristic of turbulence and by the rough and non differentiable fields. In addition, coming from fully resolved numerical simulations of the original partial differential equations, they offer the possibility to apply a wide range of approaches, from equation-free to physics-based models. TURB-Lagr data are reachable at http://smart-turb.roma2.infn.it

physics.flu-dyn↗

arXiv2024

Generative diffusion models for synthetic trajectories of heavy and light particles in turbulence

Heavy and light particles are commonly found in many natural phenomena and industrial processes, such as suspensions of bubbles, dust, and droplets in incompressible turbulent flows. Based on a recent machine learning approach using a diffusion model that successfully generated single tracer trajectories in three-dimensional turbulence and passed most statistical benchmarks across time scales, we extend this model to include heavy and light particles. Given the particle type - tracer, light, or heavy - the model can generate synthetic, realistic trajectories with correct fat-tail distributions for acceleration, anomalous power laws, and scale dependent local slope properties. This work paves the way for future exploration of the use of diffusion models to produce high-quality synthetic datasets for different flow configurations, potentially allowing interpolation between different setups and adaptation to new conditions.

physics.flu-dyn↗

arXiv2024

Synthetic Lagrangian Turbulence by Generative Diffusion Models

Lagrangian turbulence lies at the core of numerous applied and fundamental problems related to the physics of dispersion and mixing in engineering, bio-fluids, atmosphere, oceans, and astrophysics. Despite exceptional theoretical, numerical, and experimental efforts conducted over the past thirty years, no existing models are capable of faithfully reproducing statistical and topological properties exhibited by particle trajectories in turbulence. We propose a machine learning approach, based on a state-of-the-art diffusion model, to generate single-particle trajectories in three-dimensional turbulence at high Reynolds numbers, thereby bypassing the need for direct numerical simulations or experiments to obtain reliable Lagrangian data. Our model demonstrates the ability to reproduce most statistical benchmarks across time scales, including the fat-tail distribution for velocity increments, the anomalous power law, and the increased intermittency around the dissipative scale. Slight deviations are observed below the dissipative scale, particularly in the acceleration and flatness statistics. Surprisingly, the model exhibits strong generalizability for extreme events, producing events of higher intensity and rarity that still match the realistic statistics. This paves the way for producing synthetic high-quality datasets for pre-training various downstream applications of Lagrangian turbulence.

physics.flu-dyn↗

arXiv2024

Teaching to extract spectral densities from lattice correlators to a broad audience of learning-machines

We present a new supervised deep-learning approach to the problem of the extraction of smeared spectral densities from Euclidean lattice correlators. A distinctive feature of our method is a model-independent training strategy that we implement by parametrizing the training sets over a functional space spanned by Chebyshev polynomials. The other distinctive feature is a reliable estimate of the systematic uncertainties that we achieve by introducing several ensembles of machines, the broad audience of the title. By training an ensemble of machines with the same number of neurons over training sets of fixed dimensions and complexity, we manage to provide a reliable estimate of the systematic errors by studying numerically the asymptotic limits of infinitely large networks and training sets. The method has been validated on a very large set of random mock data and also in the case of lattice QCD data. We extracted the strange-strange connected contribution to the smeared $R$-ratio from a lattice QCD correlator produced by the ETM Collaboration and compared the results of the new method with the ones previously obtained with the HLT method by finding a remarkably good agreement between the two totally unrelated approaches.

hep-lat↗

arXiv2023

Multi-scale Reconstruction of Turbulent Rotating Flows with Generative Diffusion Models

We address the problem of data augmentation in a rotating turbulence set-up, a paradigmatic challenge in geophysical applications. The goal is to reconstruct information in two-dimensional (2D) cuts of the three-dimensional flow fields, imagining to have spatial gaps present within each 2D observed slice. We evaluate the effectiveness of different data-driven tools, based on diffusion models (DMs), a state-of-the-art generative machine learning protocol, and generative adversarial networks (GANs), previously considered as the best-performing method both in terms of point-wise reconstruction and the statistical properties of the inferred velocity fields. We focus on two different DMs recently proposed in the specialized literature: (i) RePaint, based on a heuristic strategy to guide an unconditional DM for flow generation by using partial measurements data and (ii) Palette, a conditional DM trained for the reconstruction task with paired measured and missing data. Systematic comparison shows that (i) DMs outperform the GAN in terms of the mean squared error and/or the statistical accuracy; (ii) Palette DM emerges as the most promising tool in terms of both point-wise and statistical metrics. An important property of DMs is their capacity for probabilistic reconstructions, providing a range of predictions based on the same measurements, enabling for uncertainty quantification and risk assessment.

physics.flu-dyn↗

arXiv2023

Extraction of lattice QCD spectral densities from an ensemble of trained machines

In this talk we discuss a novel method, that we have presented in Ref. [1], to extract hadronic spectral densities from lattice correlators by using deep learning techniques. Hadronic spectral densities play a crucial role in the study of the phenomenology of strong-interacting particles and the problem of their extraction from Euclidean lattice correlators has already been approached in the literature by using machine learning techniques. A distinctive feature of our method is a model-independent training strategy that we implement by parametrizing the training sets over a functional space spanned by Chebyshev polynomials. The other distinctive feature is a reliable estimate of the systematic uncertainties that we obtain by introducing an ensemble of machines in order to study numerically the asymptotic limits of infinitely large networks and training sets. The method is validated on a very large set of random mock data and also in the case of lattice QCD data.

hep-lat↗

arXiv2023

Data reconstruction for complex flows using AI: recent progress, obstacles, and perspectives

In recent years the fluid mechanics community has been intensely focused on pursuing solutions to its long-standing open problems by exploiting the new machine learning, (ML), approaches. The exchange between ML and fluid mechanics is bringing important paybacks in both directions. The first is benefiting from new physics-inspired ML methods and a scientific playground to perform quantitative benchmarks, whilst the latter has been open to a large set of new tools inherently well suited to deal with big data, flexible in scope, and capable of revealing unknown correlations. A special case is the problem of modeling missing information of partially observable systems. The aim of this paper is to review some of the ML algorithms that are playing an important role in the current developments in this field, to uncover potential avenues, and to discuss the open challenges for applications to fluid mechanics.

physics.flu-dyn↗