Multi-stream physics hybrid networks for solving Navier-Stokes equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sedykh, Aleksandr, Protasevich, Tatjana, Surmach, Mikhail, Senokosov, Arsenii, Anoshin, Matvei, Sagingalieva, Asel, Melnikov, Alexey
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912918504734720
author Sedykh, Aleksandr
Protasevich, Tatjana
Surmach, Mikhail
Senokosov, Arsenii
Anoshin, Matvei
Sagingalieva, Asel
Melnikov, Alexey
author_facet Sedykh, Aleksandr
Protasevich, Tatjana
Surmach, Mikhail
Senokosov, Arsenii
Anoshin, Matvei
Sagingalieva, Asel
Melnikov, Alexey
contents Understanding and solving fluid dynamics equations efficiently remains a fundamental challenge in computational physics. Traditional numerical solvers and physics-informed neural networks struggle to capture the full range of frequency components in partial differential equation solutions, limiting their accuracy and efficiency. Here, we propose the Multi-stream Physics Hybrid Network, a novel neural architecture that integrates quantum and classical layers in parallel to improve the accuracy of solving fluid dynamics equations, namely ''Kovasznay flow'' problem. This approach decomposes the solution into separate frequency components, each predicted by independent Parallel Hybrid Networks, simplifying the training process and enhancing performance. We evaluated the proposed model against a comparable classical neural network, the Multi-stream Physics Classical Network, in both data-driven and physics-driven scenarios. Our results show that the Multi-stream Physics Hybrid Network achieves a reduction in root mean square error by 36% for velocity components and 41% for pressure prediction compared to the classical model, while using 24% fewer trainable parameters. These findings highlight the potential of hybrid quantum-classical architectures for advancing computational fluid dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-stream physics hybrid networks for solving Navier-Stokes equations
Sedykh, Aleksandr
Protasevich, Tatjana
Surmach, Mikhail
Senokosov, Arsenii
Anoshin, Matvei
Sagingalieva, Asel
Melnikov, Alexey
Fluid Dynamics
Computational Physics
Quantum Physics
Understanding and solving fluid dynamics equations efficiently remains a fundamental challenge in computational physics. Traditional numerical solvers and physics-informed neural networks struggle to capture the full range of frequency components in partial differential equation solutions, limiting their accuracy and efficiency. Here, we propose the Multi-stream Physics Hybrid Network, a novel neural architecture that integrates quantum and classical layers in parallel to improve the accuracy of solving fluid dynamics equations, namely ''Kovasznay flow'' problem. This approach decomposes the solution into separate frequency components, each predicted by independent Parallel Hybrid Networks, simplifying the training process and enhancing performance. We evaluated the proposed model against a comparable classical neural network, the Multi-stream Physics Classical Network, in both data-driven and physics-driven scenarios. Our results show that the Multi-stream Physics Hybrid Network achieves a reduction in root mean square error by 36% for velocity components and 41% for pressure prediction compared to the classical model, while using 24% fewer trainable parameters. These findings highlight the potential of hybrid quantum-classical architectures for advancing computational fluid dynamics.
title Multi-stream physics hybrid networks for solving Navier-Stokes equations
topic Fluid Dynamics
Computational Physics
Quantum Physics
url https://arxiv.org/abs/2504.01891