Tommaso Del Nero
Understanding turbulence via Machine Learning.
Rel. Alfredo Braunstein, Sergio Chibbaro. Politecnico di Torino, Corso di laurea magistrale in Physics Of Complex Systems (Fisica Dei Sistemi Complessi), 2026
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (8MB) | Preview |
Abstract
Fluid turbulence is one of the most extensively studied problems in classical mechanics, yet it remains fundamentally unresolved. This work focuses on the turbulent dynamics of the SABRA shell model using data-driven machine learning techniques. A learnability analysis of the model's governing equations is performed through sparse linear regression following the framework of the SINDy algorithm. This is followed by a causality study investigating shell-to-shell response functions under localized perturbations. Furthermore, the integration of a CD-ROM (Reduced-Order Model) architecture is explored to reconstruct the underlying multiscale dynamics and the corresponding high-dimensional state trajectories.
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
