Article Dans Une Revue Physical Review Letters Année : 2024

Interpreting neural operators: how nonlinear waves propagate in non-reciprocal solids

Jonathan Colen
Vincenzo Vitelli

Résumé

We present a data-driven pipeline for model building that combines interpretable machine learning, hydrodynamic theories, and microscopic models. The goal is to uncover the underlying processes governing nonlinear dynamics experiments. We exemplify our method with data from microfluidic experiments where crystals of streaming droplets support the propagation of nonlinear waves absent in passive crystals. By combining physics-inspired neural networks, known as neural operators, with symbolic regression tools, we generate the solution, as well as the mathematical form, of a nonlinear dynamical system that accurately models the experimental data. Finally, we interpret this continuum model from fundamental physics principles. Informed by machine learning, we coarse grain a microscopic model of interacting droplets and discover that non-reciprocal hydrodynamic interactions stabilise and promote nonlinear wave propagation.

Fichier principal
Vignette du fichier
2404.12918v1.pdf (2.84 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04743537 , version 1 (18-10-2024)

Licence

Identifiants

Citer

Jonathan Colen, Alexis Poncet, Denis Bartolo, Vincenzo Vitelli. Interpreting neural operators: how nonlinear waves propagate in non-reciprocal solids. Physical Review Letters, 2024, 133 (10), pp.107301. ⟨10.1103/PhysRevLett.133.107301⟩. ⟨hal-04743537⟩
33 Consultations
90 Téléchargements

Altmetric

Partager

  • More