TLTianyi Li

Tianyi Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Tianyi Li has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Spatial Super-Resolution of Satellite-Derived SST Data via Generative Adversarial Networks in the Mediterranean Sea

    by Claudia Fanelli, Tianyi Li, Luca Biferale, Bruno Buongiorno Nardelli, Daniele Ciani, Andrea Pisano, Michele Buzzicotti

    In this work, we compare deep convolutional and generative models to improve the reconstruction of sea surface temperature (SST) gradients and effective resolution from cloud-contaminated satellite infrared data. Standard gap-filling techniques produce spatially complete datasets, but they inherently smooth out fine-scale features and gradients that may be critical for a better understanding of the ocean dynamics. Here, we investigate how the use of deep learning models as Autoencoders (AEs) and generative models as Conditional Generative Adversarial Networks (C-GANs) differently contribute to recovering the small-scale structures lost during interpolation. Our supervised, observation-based training relies on satellite-derived SST data from the Mediterranean Sea, with a focus on learning the statistical relationship between high-resolution fields and their low-resolution counterparts. We apply a tiling and merging strategy to deal with limited observational coverage and to ensure spatial continuity. Quantitative validation based on mean squared error metrics, spectral analysis, and gradient statistics shows that the AE reduces the reconstruction error, but 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 observations. Our results highlight the potential of deep models to enhance the physical and statistical realism of gap-filled satellite data in oceanographic applications.


  • Open Access

    A generative diffusion framework for physically consistent 3D turbulence

    by Tianyi Li, Michele Buzzicotti, Fabio Bonaccorso, Luca Biferale

    Synthesizing fully developed three-dimensional turbulence remains a long-standing problem in fluid mechanics and an open challenge for generative modeling. This difficulty arises from extreme dimensionality, multiscale fluctuations, strong intermittency, and the need to satisfy exact physical constraints, including incompressibility and prescribed mass and momentum fluxes under given boundary conditions. We propose a physics-constrained diffusion model in which some a priori constraints can be incorporated directly into the generative dynamics. Using rotating turbulence as a paradigmatic system with key geophysical applications, we assess the proposed framework. Here, we show that it enables stable and statistically faithful single-time synthesis of inertial-range three-dimensional turbulent velocity fields, accurately reproducing anisotropic energy spectra, intermittent statistics, and physical constraints, whereas standard denoising diffusion probabilistic models exhibit multiscale statistical deviations, violations of physical consistency, and substantially slower training convergence, thereby pointing to broader implications for generative modeling of high-dimensional, physically constrained complex systems.

  • Open Access

    Generation of Cosmic-Ray Trajectories by a Diffusion Model Trained on Test Particles in 3D Magnetohydrodynamic Turbulence

    by Johannes Martin, Jeremiah Lübke, Tianyi Li, Michele Buzzicotti, Rainer Grauer, Luca Biferale

    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 toward an application-ready transport model based on our approach are discussed.


  • High-fidelity reconstruction of large-area damaged turbulent fields with a physically constrained generative adversarial network

    by Qinmin Zheng, Tianyi Li, Benteng Ma, Lin Fu, Xiaomeng Li

    The reconstruction of incomplete information in flow fields is a pervasive challenge in numerous turbulence-related applications. This paper proposes a framework for the high-fidelity reconstruction of large-area damaged turbulent fields with high resolution based on a physically constrained generative adversarial network. The network incorporates some special designs, such as leveraging complete or sparse fields of velocity components as physical constraints, employing a ResNet-like network with a fast Fourier convolution module, and adopting a PatchGAN discriminator network. To train the network, we employ a combination of loss functions, which comprise mean absolute error, network-level loss, and feature matching loss. We validate our method on a dataset of compressible isotropic turbulent flow and investigate three distinct damaged distributions with gap ratios of 39.06% and 56.25%. The proposed reconstruction framework has been shown to achieve excellent reconstruction performance. The reconstructed flow fields are consistent with the raw flow fields in terms of magnitude, power spectrum, and two-point correlation function. We also provide extensive ablation studies to validate our approach. The results indicate that the utilization of physical constraints significantly improves the reconstruction performance in damaged regions, particularly in cases that involve a large damaged area. Furthermore, in the proposed reconstruction framework, the size of patch in the PatchGAN discriminator network can be flexibly adjusted according to the scale of turbulence structures, and the perceptual loss function plays a crucial role in evaluating differences between feature maps of flow fields at network levels based on a pretrained network. These special designs ensure consistency across diverse scales of turbulence structures and improve the accuracy and efficiency of network training.


  • Open Access

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

    by Tianyi Li, Alessandra S. Lanotte, Michele Buzzicotti, Fabio Bonaccorso, Luca Biferale

    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 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 uncertainty quantification and risk assessment.


  • Open Access

    Generative Adversarial Networks to infer velocity components in rotating turbulent flows

    by Tianyi Li, Michele Buzzicotti, Luca Biferale, Fabio Bonaccorso

    Inference problems for two-dimensional snapshots of rotating turbulent flows are studied. We perform a systematic quantitative benchmark of point-wise and statistical reconstruction capabilities of the linear Extended Proper Orthogonal Decomposition (EPOD) method, a non-linear Convolutional Neural Network (CNN) and a Generative Adversarial Network (GAN). We attack the important task of inferring one velocity component out of the measurement of a second one, and two cases are studied: (I) both components lay in the plane orthogonal to the rotation axis and (II) one of the two is parallel to the rotation axis. We show that EPOD method works well only for the former case where both components are strongly correlated, while CNN and GAN always outperform EPOD both concerning point-wise and statistical reconstructions. For case (II), when the input and output data are weakly correlated, all methods fail to reconstruct faithfully the point-wise information. In this case, only GAN is able to reconstruct the field in a statistical sense. The analysis is performed using both standard validation tools based on $L_2$ spatial distance between the prediction and the ground truth and more sophisticated multi-scale analysis using wavelet decomposition. Statistical validation is based on standard Jensen-Shannon divergence between the probability density functions, spectral properties and multi-scale flatness.

  • Open Access

    Evolution of a Stratified Turbulent Cloud under Rotation

    by Tianyi Li, Minping Wan, Shiyi Chen

    Localized turbulence is common in geophysical flows, where the roles of rotation and stratification are paramount. In this study, we investigate the evolution of a stratified turbulent cloud under rotation. Recognizing that a turbulent cloud is composed of vortices of varying scales and shapes, we start our investigation with a single eddy using analytical solutions derived from a linearized system. Compared to an eddy under pure rotation, the stratified eddy shows the physical manifestation of a known potential vorticity mode, appearing as a static stable vortex. In addition, the expected shift from inertial waves to inertial-gravity waves is observed. In our numerical simulations of the turbulent cloud, carried out at a constant Rossby number over a range of Froude numbers, stratification causes columnar structures to deviate from vertical alignment. This deviation increases with increasing stratification, slowing the expansion rate of the cloud. The observed characteristics of these columnar structures are consistent with the predictions of linear theory, particularly in their tilt angles and vertical growth rates, suggesting a significant influence of inertial-gravity waves. Using Lagrangian particle tracking, we have identified regions where wave activity dominates over turbulence. In scenarios of milder stratification, these inertial-gravity waves are responsible for a significant energy transfer away from the turbulent cloud, a phenomenon that attenuates with increasing stratification.


  • Open Access

    Evolution of a Stratified Turbulent Cloud under Rotation

    by Tianyi Li, Minping Wan, Shiyi Chen

    Localized turbulence is common in geophysical flows, where the roles of rotation and stratification are paramount. In this study, we investigate the evolution of a stratified turbulent cloud under rotation. Recognizing that a turbulent cloud is composed of vortices of varying scales and shapes, we start our investigation with a single eddy. Compared to an eddy under pure rotation, the stratified eddy shows the physical manifestation of a known potential vorticity mode, appearing as a static stable vortex. In addition, the expected shift from inertial waves to inertial-gravity waves is observed. In our numerical simulations of the turbulent cloud, carried out at a constant Rossby number over a range of Froude numbers, stratification causes columnar structures to deviate from vertical alignment. This deviation increases with increasing stratification, slowing the expansion rate of the cloud. The observed characteristics of these columnar structures are consistent with the predictions of linear theory, particularly in their tilt angles and vertical growth rates, suggesting a significant influence of inertial-gravity waves. Using Lagrangian particle tracking, we have identified regions where wave activity dominates over turbulence. In scenarios of milder stratification, these inertial-gravity waves are responsible for a significant energy transfer away from the turbulent cloud, a phenomenon that attenuates with increasing stratification.


  • Open Access

    Generative adversarial networks to infer velocity components in rotating turbulent flows

    by Tianyi Li, Michele Buzzicotti, Luca Biferale, Fabio Bonaccorso

    Inference problems for two-dimensional snapshots of rotating turbulent flows are studied. We perform a systematic quantitative benchmark of point-wise and statistical reconstruction capabilities of the linear Extended Proper Orthogonal Decomposition (EPOD) method, a nonlinear Convolutional Neural Network (CNN) and a Generative Adversarial Network (GAN). We attack the important task of inferring one velocity component out of the measurement of a second one, and two cases are studied: (I) both components lay in the plane orthogonal to the rotation axis and (II) one of the two is parallel to the rotation axis. We show that EPOD method works well only for the former case where both components are strongly correlated, while CNN and GAN always outperform EPOD both concerning point-wise and statistical reconstructions. For case (II), when the input and output data are weakly correlated, all methods fail to reconstruct faithfully the point-wise information. In this case, only GAN is able to reconstruct the field in a statistical sense. The analysis is performed using both standard validation tools based on $$L_2$$ L 2 spatial distance between the prediction and the ground truth and more sophisticated multi-scale analysis using wavelet decomposition. Statistical validation is based on standard Jensen–Shannon divergence between the probability density functions, spectral properties and multi-scale flatness. Graphical