• Corpus ID: 252968416

Classifying Turbulent Environments via Machine Learning

@inproceedings{Buzzicotti2022ClassifyingTE,
  title={Classifying Turbulent Environments via Machine Learning},
  author={Michele Buzzicotti and Fabio Bonaccorso},
  year={2022}
}
. The problem of classifying turbulent environments from partial observation is key for some theoretical and applied fields, from engineering to earth observation and astrophysics, e.g. to precondition searching of optimal control policies in different turbulent backgrounds, to predict the probability of rare events and/or to infer physical parameters labelling different turbulent set-ups. To achieve such goal one can use different tools depending on the system’s knowledge and on the quality and… 

References

SHOWING 1-10 OF 81 REFERENCES

TURB-Rot. A large database of 3d and 2d snapshots from turbulent rotating flows

We present TURB-Rot, a new open database of 3d and 2d snapshots of turbulent velocity fields, obtained by Direct Numerical Simulations (DNS) of the original Navier-Stokes equations in the presence of

Enhancing Computational Fluid Dynamics with Machine Learning

This Perspective highlights some of the areas of highest potential impact of machine learning, including to accelerate direct numerical simulations, to improve turbulence closure modeling, and to develop enhanced reduced-order models.

Deep learning velocity signals allow quantifying turbulence intensity

By using deep neural networks, this work can accurately estimate the Reynolds number within 15% accuracy, from a statistical sample as small as two large-scale eddy turnover times, compared with physics-based statistical estimators, which provide at least a hundredfold larger error.

Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps

A coarse-grained Markov process is built for the macroscopic dynamics of a globally coupled maps system to test the ability of the stochastic machine-learning approach to describe nontrivial evolution laws as the one considered in this study.

Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database

The capability of Convolutional Neural Networks embedded in a Deep Generative Adversarial Model (Deep-GAN) to generate missing data in turbulence, a paradigmatic high dimensional chaotic system is explored.

Perspective on machine learning for advancing fluid mechanics

A perspective is presented on how machine learning methods might advance fluid mechanics. Current limitations are discussed, though the potential impact is deemed high, so long as outcomes are held

Data-driven science and engineering: machine learning, dynamical systems, and control

  • T. Peters
  • Computer Science
    Contemporary Physics
  • 2019

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

This work investigates Zermelo's problem by using a Reinforcement Learning (RL) approach for the case of a vessel that has a slip velocity with fixed intensity, Vs, but variable direction and navigating in a 2D turbulent sea, and shows how the RL approach is able to take advantage of the flow properties in order to reach the target.

Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model

The synergy demonstrated with a low-dimensional system is encouraging for more sophisticated dynamics and motivates further investigation to merge data assimilation and machine learning.

Machine Learning for Fluid Mechanics

Fundamental ML methodologies are outlined and their uses for understanding, modeling, optimizing, and controlling fluid flows are discussed and the strengths and limitations of these methods are addressed.
...