Saved in:
Bibliographic Details
Main Authors: Qi, Miao, Idoughi, Ramzi, Heidrich, Wolfgang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.08570
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909223047135232
author Qi, Miao
Idoughi, Ramzi
Heidrich, Wolfgang
author_facet Qi, Miao
Idoughi, Ramzi
Heidrich, Wolfgang
contents Flow estimation problems are ubiquitous in scientific imaging. Often, the underlying flows are subject to physical constraints that can be exploited in the flow estimation; for example, incompressible (divergence-free) flows are expected for many fluid experiments, while irrotational (curl-free) flows arise in the analysis of optical distortions and wavefront sensing. In this work, we propose a Physics- Inspired Neural Network (PINN) named HDNet, which performs a Helmholtz decomposition of an arbitrary flow field, i.e., it decomposes the input flow into a divergence-only and a curl-only component. HDNet can be trained exclusively on synthetic data generated by reverse Helmholtz decomposition, which we call Helmholtz synthesis. As a PINN, HDNet is fully differentiable and can easily be integrated into arbitrary flow estimation problems.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08570
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HDNet: Physics-Inspired Neural Network for Flow Estimation based on Helmholtz Decomposition
Qi, Miao
Idoughi, Ramzi
Heidrich, Wolfgang
Machine Learning
Artificial Intelligence
Flow estimation problems are ubiquitous in scientific imaging. Often, the underlying flows are subject to physical constraints that can be exploited in the flow estimation; for example, incompressible (divergence-free) flows are expected for many fluid experiments, while irrotational (curl-free) flows arise in the analysis of optical distortions and wavefront sensing. In this work, we propose a Physics- Inspired Neural Network (PINN) named HDNet, which performs a Helmholtz decomposition of an arbitrary flow field, i.e., it decomposes the input flow into a divergence-only and a curl-only component. HDNet can be trained exclusively on synthetic data generated by reverse Helmholtz decomposition, which we call Helmholtz synthesis. As a PINN, HDNet is fully differentiable and can easily be integrated into arbitrary flow estimation problems.
title HDNet: Physics-Inspired Neural Network for Flow Estimation based on Helmholtz Decomposition
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.08570