activity
20242026
collaborators

5 papers

physics.flu-dyn2026

Improving turbulence control through explainable deep learning

Miguel Beneitez, Andres Cremades, Luca Guastoni +1

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 c…

cs.LG2025

Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems

Hans Harder, Abhijeet Vishwasrao, Luca Guastoni +2

This paper is concerned with probabilistic techniques for forecasting dynamical systems described by partial differential equations (such as, for example, the Navier-Stokes equatio…

cs.LG2025

PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics

Aleksandra Franz, Hao Wei, Luca Guastoni +1

Despite decades of advancements, the simulation of fluids remains one of the most challenging areas of in scientific computing. Supported by the necessity of gradient information i…

cs.LG2025

Easy attention: A simple attention mechanism for temporal predictions with transformers

Marcial Sanchis-Agudo, Yuning Wang, Roger Arnau +4

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention whic…

physics.flu-dyn2024

Fully convolutional networks for velocity-field predictions based on the wall heat flux in turbulent boundary layers

L. Guastoni, A. G. Balasubramanian, F. Foroozan +6

Fully-convolutional neural networks (FCN) were proven to be effective for predicting the instantaneous state of a fully-developed turbulent flow at different wall-normal locations…