# 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

- PhysicsArXiv
- 2020

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

- Computer Science
- 2021

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

- PhysicsScience Advances
- 2021

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

- Computer ScienceChaos
- 2021

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

- Computer SciencePhysical Review Fluids
- 2021

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

- PhysicsPhysical Review Fluids
- 2019

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

- Computer ScienceContemporary Physics
- 2019

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

- MathematicsChaos
- 2019

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

- Computer Science, Environmental ScienceJ. Comput. Sci.
- 2020

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

- Computer ScienceAnnual Review of Fluid Mechanics
- 2020

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.