activity
20242026
collaborators

28 papers

physics.flu-dyn2026

A hybrid proper orthogonal decomposition and diffusion framework for reduced-order forecasting of turbulent flow dynamics

Rodrigo Abadia-Heredia, Xiangrui Zou, Manuel Lopez-Martin +2

Forecasting turbulent flow dynamics requires a balance between predictive fidelity and computational efficiency. Diffusion-based generative models can represent complex spatiotempo…

cs.LG2026

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

Francisco Giral, Álvaro Manzano, Ignacio Gómez +2

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.…

cs.LG2026

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

Arindam Sengupta, Paul Jeanney, Ricardo Vinuesa +2

Urban flow and air-quality simulations generate high-dimensional datasets describing velocity and pollutant transport across multiple spatial, temporal, and physical-variable dimen…

physics.flu-dyn2026

Divergence-aware adaptive prediction framework for accelerating CFD simulations of unsteady flows

Xiangrui Zou, Zhuoqun Zhao, Guillermo Barragán +1

Reliable long-horizon prediction remains a challenge for data-driven CFD surrogates, because offline-trained models accumulate autoregressive errors and lose accuracy when operatin…

cs.LG2026

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

Francisco Giral, Abhijeet Vishwasrao, Andrea Arroyo Ramo +8

Aerodynamic surrogate models are increasingly used to replace repeated high-fidelity CFD evaluations in many-query design settings, but current approaches still face two important…

physics.flu-dyn2026

MoTIF: A Mode-Structured Tensor Framework for Multi-Parametric Approximation, Super-Resolution and Forecasting of Unsteady Systems

Guillermo Barragán, Ashton Hetherington, Arindam Sengupta +3

We introduce MoTIF, a mode-structured tensor framework for multi-parametric approximation, super-resolution, and temporal forecasting of high-dimensional unsteady systems. The meth…