Identification of Settling Velocity with Physics Informed Neural Networks For Sediment Laden Flows

Physics-Informed Neural Networks (PINNs) have shown great potential in the context of fluid dynamics simulations, particularly in reconstructing flow fields and identifying key parameters. In this study, we explore the application of PINNs to recover the dimensionless settling velocity for sedimenta...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-04
Main Authors: Delcey, Mickaël, Cheny, Yoann, Keck, Jean-Baptiste, Gans, Adrien, Sébastien Kiesgen De Richter
Format: Article
Language:English
Subjects:
Computer simulation
Fluid dynamics
Fresh water
Mathematical models
Neural networks
Parameter identification
Robustness (mathematics)
Saline water
Salinity
Sediment transport
Settling velocity
Transport equations
Velocity distribution
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Physics-Informed Neural Networks (PINNs) have shown great potential in the context of fluid dynamics simulations, particularly in reconstructing flow fields and identifying key parameters. In this study, we explore the application of PINNs to recover the dimensionless settling velocity for sedimentation flow. The flow involves sediment-laden fresh water overlying salt water, which is described by Navier-Stokes equations coupled with sediment concentration and salinity transport equations. Two cases are investigated: one where the training data contains the salinity and sediment concentration fields, and another where it contains the velocity field. For both cases, we investigate several flow regimes and show that the model is capable of inferring the unknown parameter and reconstructing the hydrodynamic field of the flow. The quality of the model inference is assessed by comparing it with numerical simulations from a high-fidelity semi-Lagrangian solver. We demonstrate the model's robustness to noise by training it with data corrupted by noise of varying magnitudes, highlighting the potential of PINNs for real-world applications.
ISSN:2331-8422