Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations

• URL: http://arxiv.org/abs/2504.01891v1
• Date: Wed, 02 Apr 2025 16:50:54 GMT
• Title: Multi-stream Physics Hybrid Networks for solving Navier-Stokes equations
• Authors: Tatjana Protasevich, Mikhail Surmach, Aleksandr Sedykh, Olga Tsurkan, Matvei Anoshin, Vadim Lopatkin, Leonid Fedichkin,
• Abstract summary: Multi-stream Physics Hybrid Network is a novel neural architecture that integrates quantum and classical layers in parallel.<n>This approach decomposes the solution into separate frequency components, each predicted by independent Parallel Hybrid Networks.<n>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.
• Score: 36.136619420474766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Explaining the advantage of quantum-enhanced physics-informed neural networks [0.05997422707234518]
  Partial differential equations (PDEs) form the backbone of simulations of many natural phenom- ena.<n>We show how quantum computing can improve the ability of physics-informed neural networks to solve PDEs.
  arXiv  Detail & Related papers  (2026-01-21T14:50:17Z)
• Quantum-Classical Physics-Informed Neural Networks for Solving Reservoir Seepage Equations [1.376408511310322]
  Solving partial differential equations (PDEs) for reservoir seepage is critical for optimizing oil and gas field development and predicting production performance.<n>Traditional numerical methods suffer from mesh-dependent errors and high computational costs, while classical Physics-Informed Neural Networks (PINNs) face bottlenecks in parameter efficiency, high-dimensional expression, and strong nonlinear fitting.<n>We propose a Discrete Variable (DV)-Circuit Quantum-Classical Physics-Informed Neural Network (QCPINN) and apply it to three typical reservoir seepage models for the first time.
  arXiv  Detail & Related papers  (2025-12-03T16:14:16Z)
• MixFunn: A Neural Network for Differential Equations with Improved Generalization and Interpretability [0.0]
  MixFunn is a novel neural network architecture designed to solve differential equations with enhanced precision, interpretability, and generalization capability. The architecture comprises two key components: the mixed-function neuron, which integrates multiple parameterized nonlinear functions, and the second-order neuron, which combines a linear transformation of its inputs with a quadratic term to capture cross-combinations of input variables.
  arXiv  Detail & Related papers  (2025-03-28T15:31:15Z)
• QCPINN: Quantum Classical Physics-Informed Neural Networks for Solving PDEs [0.70224924046445]
  Physics-informed neural networks (PINNs) have emerged as promising methods for solving partial differential equations (PDEs) by embedding physical laws into neural architectures.<n>We propose a quantum-classical physics-informed neural network (CPIQNN) combining quantum and classical components to solve PDEs with fewer parameters while maintaining comparable accuracy and training convergence.
  arXiv  Detail & Related papers  (2025-03-20T19:52:26Z)
• Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes [37.69303106863453]
  We present a hybrid quantum physics-informed neural network that simulates laminar fluid flows in 3D Y-shaped mixers. Our approach combines the expressive power of a quantum model with the flexibility of a physics-informed neural network, resulting in a 21% higher accuracy compared to a purely classical neural network.
  arXiv  Detail & Related papers  (2023-04-21T20:49:29Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations [64.78260098263489]
  In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs) We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases. We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
  arXiv  Detail & Related papers  (2022-10-14T15:01:32Z)
• Neural Basis Functions for Accelerating Solutions to High Mach Euler Equations [63.8376359764052]
  We propose an approach to solving partial differential equations (PDEs) using a set of neural networks. We regress a set of neural networks onto a reduced order Proper Orthogonal Decomposition (POD) basis. These networks are then used in combination with a branch network that ingests the parameters of the prescribed PDE to compute a reduced order approximation to the PDE.
  arXiv  Detail & Related papers  (2022-08-02T18:27:13Z)
• Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations [62.81701992551728]
  We present a physics-informed framework for solving time-dependent partial differential equations. Our model utilizes discrete cosine transforms to encode spatial and recurrent neural networks. We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations.
  arXiv  Detail & Related papers  (2022-02-24T20:46:52Z)
• One-Shot Transfer Learning of Physics-Informed Neural Networks [2.6084034060847894]
  We present a framework for transfer learning PINNs that results in one-shot inference for linear systems of both ordinary and partial differential equations. This means that highly accurate solutions to many unknown differential equations can be obtained instantaneously without retraining an entire network.
  arXiv  Detail & Related papers  (2021-10-21T17:14:58Z)
• Physics-informed neural networks for the shallow-water equations on the sphere [0.0]
  Physics-informed neural networks are trained to satisfy the differential equations along with the prescribed initial and boundary data. We propose a simple multi-model approach to tackle test cases of comparatively long time intervals.
  arXiv  Detail & Related papers  (2021-04-01T16:47:40Z)
• Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction [79.81193813215872]
  We develop a hybrid (graph) neural network that combines a traditional graph convolutional network with an embedded differentiable fluid dynamics simulator inside the network itself. We show that we can both generalize well to new situations and benefit from the substantial speedup of neural network CFD predictions.
  arXiv  Detail & Related papers  (2020-07-08T21:23:19Z)
• Physics-informed deep learning for incompressible laminar flows [13.084113582897965]
  We propose a mixed-variable scheme of physics-informed neural network (PINN) for fluid dynamics. A parametric study indicates that the mixed-variable scheme can improve the PINN trainability and the solution accuracy.
  arXiv  Detail & Related papers  (2020-02-24T21:51:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.