Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Machine Intelligence and Smart Innovation (ICMISI)

Benchmarking Quantum and Classical Solvers for the 1D Burgers' Equation: QTN, HSE, and PINN

Vanshaj Kerni, A H Helmi Ahmed, Syed Ali Asghar

Published May 9, 2026• 0 citations
Publisher

Abstract

We present a comprehensive benchmarking of quantum-inspired, quantum native, and deep learning algorithms against classical baselines for solving the 1D viscous Burgers equation in a shock-dominated regime. We compared the Quantum Tensor Networks (QTN), the Hydrodynamic Schrödinger Equation (HSE), and Physics Informed Neural Networks (PINN) against classical GMRES and spectral solvers. Evaluated the results on accuracy, runtime scaling, and hardware resource overhead across spatial resolutions ranging from$N=4$to$N=128$, our results show a hierarchy in solver performance. The QTN exhibits precision with an$L_{2}$error$\sim 10^{-7}$and exhibits near constant runtime scaling. In the HSE algorithm, while the finite difference HSE remains robust, the spectral HSE method exhibits catastrophic numerical instability at high resolutions, diverging significantly at$N=128$due to the prohibitive circuit depth overhead of global quantum operators. PINNs offer a flexible, mesh-free framework; the standard implementation suffers from severe spectral bias and remains constrained to lower accuracy tiers with$L_{2}$errors near${10}^{-1}$. We also observed that advanced architectures, like PirateNets, though outperforms standard PINNs, they still exhibit a notable performance lag in absolute$L_{2}$error compared to the QTN implementation for smaller qubit numbers. Ultimately, this study demonstrates that while quantum and neural paradigms offer profound representational advantages for low-resolution or specialised geometries, they do not currently yield a strict computational advantage over mature classical fluid dynamics solvers without the advent of fault-tolerant hardware or significant algorithmic breakthroughs in nonlinear processing.

DOI
10.1109/icmisi69868.2026.11584077

Related papers

Benchmarking Quantum and Classical Algorithms for the 1D Burgers Equation: QTN, HSE, and PINN

Vanshaj Kerni, Abdelrahman E. Ahmed, Syed Ali Asghar

We present a comparative benchmark of Quantum Tensor Networks (QTN), the Hydrodynamic Schrödinger Equation (HSE), and Physics-Informed Neural Networks (PINN) for simulating the 1D Burgers' equation. Evaluating these emerging paradigms against classical GMRES and Spectral baselines, we analyse solution accuracy, runtime scaling, and resource overhead across grid resolutions ranging from $N=4$ to $N=128$. Our results reveal a distinct performance hierarchy. The QTN solver achieves superior precision ($L_2 \sim 10^{-7}$) with remarkable near-constant runtime scaling, effectively leveraging entanglement compression to capture shock fronts. In contrast, while the Finite-Difference HSE implementation remains robust, the Spectral HSE method suffers catastrophic numerical instability at high resolutions, diverging significantly at $N=128$. PINNs demonstrate flexibility as mesh-free solvers but stall at lower accuracy tiers ($L_2 \sim 10^{-1}$), limited by spectral bias compared to grid-based methods. Ultimately, while quantum methods offer novel representational advantages for low-resolution fluid dynamics, this study confirms they currently yield no computational advantage over classical solvers without fault tolerance or significant algorithmic breakthroughs in handling non-linear feedback.

quant-pharXiv:2602.04239•Feb 5, 2026•0 citations

Hybrid quantum-classical physics-informed neural networks for solving nonlinear PDEs: when and where hybridization is effective?

Kaveh Zabihi, Hamid Montazeri, Akke S. J. Suiker

Physics-informed neural networks (PINNs) often struggle on nonlinear partial differential equations (PDEs) with sharp gradients, stiff dynamics, high-frequency content, or multiscale structure. Such limitations, rooted in spectral bias, ill-conditioned optimization, and unstable convergence, restrict PINN accuracy in regimes where advanced solvers are most needed. In this work, we develop a hybrid quantum-classical physics-informed neural network (HQPINN) that integrates a classical neural-network backbone with a parameterized quantum circuit (PQC) to enrich the solution representation. The framework is benchmarked against a classical PINN on three representative nonlinear PDEs: Burgers' equation, the Allen-Cahn equation, and the Korteweg-de Vries (KdV) equation. The framework is further examined through a systematic sensitivity analysis of qubit count, circuit depth, PQC placement, collocation density, and classical-network width. Across all benchmarks, HQPINNs exhibit smoother training dynamics, reduced loss oscillations, and improved final accuracy, with the largest gains occurring in stiff and multiscale regimes. Relative L2 error decreases by about fourfold for Burgers' equation and fivefold for the Allen-Cahn equation, while improvements for the KdV equation are more moderate. Overall, the results demonstrate that carefully co-designed hybrid quantum-classical architectures can mitigate key limitations of classical PINNs and provide practical design guidance for near-term quantum-enhanced PDE solvers.

quant-pharXiv:2606.04679•Jun 4, 2026•0 citations

Benchmarking Quantum-Assisted PINN (QA-PINN) for Computational Fluid Dynamics

Jay Shah, Rut Lineswala, Abhishek Chopra

Physics-Informed Neural Network (PINN) is a powerful method in computer-aided engineering (CAE), especially for design space exploration studies (like surrogate modeling and design of experiments), that combines deep learning with physics-based modeling. Though PINN is in a nascent stage, its success hinges on two key factors - generalizability and training efficiency. One common aspect of these factors is trainable parameters. The goal of this study is to improve these two factors by the introduction of Quantum Machine Learning in a classical PINN framework. This study proposes a Quantum-Assisted PINN (QA-PINN) to reduce the trainable parameters while maintaining accuracy. The study utilized a standard forward problem of simulating partial differential equations (PDEs) from the field of Computational Fluid Dynamics (CFD), a well-understood area with classical PINN. A comparative analysis was performed between QA-PINN, equivalent classical vanilla PINN (c-PINN), and state-of-the-art classical PINN - Globally Adaptive Activation Function PINN (GAAF-PINN). All methods were benchmarked against the ground-truth analytical solution for 1D Burger's equation. The analysis is conducted for 3, 4, and 5-qubit QA-PINN architectures. In comparison to c-PINN and GAAF-PINN, 4 and 5-qubit QA-PINN is shown to reduce the number of trainable parameters of the network by 20%, and while maintaining the accuracy. The reduced number of trainable parameters indicates the reduced complexity of the model and the reduced risk of overfitting, making it more generalizable. Thus, the proposed approach can have a significant impact on PINNs enhancing generalization and improving training efficiency for deploying the model for real-world applications.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•1 citation

Quantum Error Mitigation with Attention Graph Transformers for Burgers Equation Solvers on NISQ Hardware

Seyed Mohamad Ali Tousi, Adib Bazgir, Yuwen Zhang +1 more

We present a hybrid quantum-classical framework augmented with learned error mitigation for solving the viscous Burgers equation on noisy intermediate-scale quantum (NISQ) hardware. Using the Cole-Hopf transformation, the nonlinear Burgers equation is mapped to a diffusion equation, discretized on uniform grids, and encoded into a quantum state whose time evolution is approximated via Trotterized nearest-neighbor circuits implemented in Qiskit. Quantum simulations are executed on noisy Aer backends and IBM superconducting quantum devices and are benchmarked against high-accuracy classical solutions obtained using a Krylov-based solver applied to the corresponding discretized Hamiltonian. From measured quantum amplitudes, we reconstruct the velocity field and evaluate physical and numerical diagnostics, including the L2 error, shock location, and dissipation rate, both with and without zero-noise extrapolation (ZNE). To enable data-driven error mitigation, we construct a large parametric dataset by sweeping viscosity, time step, grid resolution, and boundary conditions, producing matched tuples of noisy, ZNE-corrected, hardware, and classical solutions together with detailed circuit metadata. Leveraging this dataset, we train an attention-based graph neural network that incorporates circuit structure, light-cone information, global circuit parameters, and noisy quantum outputs to predict error-mitigated solutions. Across a wide range of parameters, the learned model consistently reduces the discrepancy between quantum and classical solutions beyond what is achieved by ZNE alone. We discuss extensions of this approach to higher-dimensional Burgers systems and more general quantum partial differential equation solvers, highlighting learned error mitigation as a promising complement to physics-based noise reduction techniques on NISQ devices.

quant-pharXiv:2512.23817•Dec 31, 2025•2 citations

Demonstration of Scalability and Accuracy of Variational Quantum Linear Solver for Computational Fluid Dynamics

Ferdin Sagai Don Bosco, S, Dhamotharan, Rut Lineswala +1 more

The solution for non-linear, complex partial differential Equations (PDEs) is achieved through numerical approximations, which yield a linear system of equations. This approach is prevalent in Computational Fluid Dynamics (CFD), but it restricts the mesh size since the solution of the linear system becomes computationally intractable when the mesh resolution increases. The reliance on the ability of High-Performance Computers (HPC) to scale up and meet these requirements is myopic; such very high-fidelity simulations require a paradigm shift in computing. This paper presents an exploration of quantum methodologies aimed at achieving high accuracy in solving such a large system of equations. Leveraging recent works in Quantum Linear Solver Algorithms (QLSA) and variational algorithms suitable for Quantum Simulation in HPC, we aspire to push the boundaries of CFD-relevant problems that can be solved on hybrid quantum-classical framework. To this end, we consider the 2D, transient, incompressible, viscous, non-linear coupled Burgers equation as a test problem and investigate the accuracy of our approach by comparing results with a classical linear system of equation solvers, such as the Generalized Minimal RESidual method (GMRES). Through rigorous testing, our findings demonstrate that our quantum methods yield results comparable in accuracy to traditional approaches. Additionally, we demonstrate the accuracy, scalability, and consistency of our quantum method. Lastly, we present an insightful estimation of the resources our quantum algorithm needs to solve systems with nearly 2 billion mesh points.

arXiv:2409.03241•Sep 5, 2024•11 citations

Solving transport equations on quantum computers—potential and limitations of physics-informed quantum circuits

Pia Siegl, Simon Wassing, Dirk Markus Mieth +2 more

Abstract Quantum circuits with trainable parameters, paired with classical optimization routines can be used as machine learning models. The recently popularized physics-informed neural network (PINN) approach is a machine learning algorithm that solves differential equations by incorporating them into a loss function. Being a mesh-free method, it is a promising approach for computational fluid dynamics. The question arises whether the properties of quantum circuits can be leveraged for a quantum physics-informed machine learning model. In this study, we compare the classical PINN-ansatz and its quantum analog, which we name the physics-informed quantum circuit (PIQC). The PIQC simulations are performed on a noise-free quantum computing simulator. Studying various differential equations, we compare expressivity, accuracy and convergence properties. We find that one-dimensional problems, such as the linear transport of a Gaussian-pulse or Burgers’ equation, allow a successful approximation with the classical and the quantum ansatz. For these examples, the PIQC overall performs similarly to PINN and converges more consistently and for Burgers’ equations even faster. While this is promising, the chosen quantum circuit approach struggles to approximate discontinuous solutions which the classical PINN-ansatz can represent. Based on this comparison, we extrapolate that the required number of qubits for solving two-dimensional problems in aerodynamics may already be available in the next few years. However, the acceleration potential is currently unclear and challenges like noisy circuits and approximations of discontinuous solutions have to be overcome.

CEAS Aeronautical Journal•Oct 30, 2024•9 citations
We present a comprehensive benchmarking of quantum-inspired, quantum native, and deep learning algorithms against classical baselines for solving the 1D viscous Burgers equation in a shock-dominated regime. We compared the Quantum Tensor Networks (QTN), the Hydrodynamic Schrödinger Equation (HSE), and Physics Informed Neural Networks (PINN) against classical GMRES and spectral solvers. Evaluated the results on accuracy, runtime scaling, and hardware resource overhead across spatial resolutions ranging fromN=4N=4N=4toN=128N=128N=128, our results show a hierarchy in solver performance. The QTN exhibits precision with anL2L_{2}L2​error∼10−7\sim 10^{-7}∼10−7and exhibits near constant runtime scaling. In the HSE algorithm, while the finite difference HSE remains robust, the spectral HSE method exhibits catastrophic numerical instability at high resolutions, diverging significantly atN=128N=128N=128due to the prohibitive circuit depth overhead of global quantum operators. PINNs offer a flexible, mesh-free framework; the standard implementation suffers from severe spectral bias and remains constrained to lower accuracy tiers withL2L_{2}L2​errors near10−1{10}^{-1}10−1. We also observed that advanced architectures, like PirateNets, though outperforms standard PINNs, they still exhibit a notable performance lag in absoluteL2L_{2}L2​error compared to the QTN implementation for smaller qubit numbers. Ultimately, this study demonstrates that while quantum and neural paradigms offer profound representational advantages for low-resolution or specialised geometries, they do not currently yield a strict computational advantage over mature classical fluid dynamics solvers without the advent of fault-tolerant hardware or significant algorithmic breakthroughs in nonlinear processing.
We present a comparative benchmark of Quantum Tensor Networks (QTN), the Hydrodynamic Schrödinger Equation (HSE), and Physics-Informed Neural Networks (PINN) for simulating the 1D Burgers' equation. Evaluating these emerging paradigms against classical GMRES and Spectral baselines, we analyse solution accuracy, runtime scaling, and resource overhead across grid resolutions ranging from N=4N=4N=4 to N=128N=128N=128. Our results reveal a distinct performance hierarchy. The QTN solver achieves superior precision (L2∼10−7L_2 \sim 10^{-7}L2​∼10−7) with remarkable near-constant runtime scaling, effectively leveraging entanglement compression to capture shock fronts. In contrast, while the Finite-Difference HSE implementation remains robust, the Spectral HSE method suffers catastrophic numerical instability at high resolutions, diverging significantly at N=128N=128N=128. PINNs demonstrate flexibility as mesh-free solvers but stall at lower accuracy tiers (L2∼10−1L_2 \sim 10^{-1}L2​∼10−1), limited by spectral bias compared to grid-based methods. Ultimately, while quantum methods offer novel representational advantages for low-resolution fluid dynamics, this study confirms they currently yield no computational advantage over classical solvers without fault tolerance or significant algorithmic breakthroughs in handling non-linear feedback.
Physics-informed neural networks (PINNs) often struggle on nonlinear partial differential equations (PDEs) with sharp gradients, stiff dynamics, high-frequency content, or multiscale structure. Such limitations, rooted in spectral bias, ill-conditioned optimization, and unstable convergence, restrict PINN accuracy in regimes where advanced solvers are most needed. In this work, we develop a hybrid quantum-classical physics-informed neural network (HQPINN) that integrates a classical neural-network backbone with a parameterized quantum circuit (PQC) to enrich the solution representation. The framework is benchmarked against a classical PINN on three representative nonlinear PDEs: Burgers' equation, the Allen-Cahn equation, and the Korteweg-de Vries (KdV) equation. The framework is further examined through a systematic sensitivity analysis of qubit count, circuit depth, PQC placement, collocation density, and classical-network width. Across all benchmarks, HQPINNs exhibit smoother training dynamics, reduced loss oscillations, and improved final accuracy, with the largest gains occurring in stiff and multiscale regimes. Relative L2 error decreases by about fourfold for Burgers' equation and fivefold for the Allen-Cahn equation, while improvements for the KdV equation are more moderate. Overall, the results demonstrate that carefully co-designed hybrid quantum-classical architectures can mitigate key limitations of classical PINNs and provide practical design guidance for near-term quantum-enhanced PDE solvers.
Physics-Informed Neural Network (PINN) is a powerful method in computer-aided engineering (CAE), especially for design space exploration studies (like surrogate modeling and design of experiments), that combines deep learning with physics-based modeling. Though PINN is in a nascent stage, its success hinges on two key factors - generalizability and training efficiency. One common aspect of these factors is trainable parameters. The goal of this study is to improve these two factors by the introduction of Quantum Machine Learning in a classical PINN framework. This study proposes a Quantum-Assisted PINN (QA-PINN) to reduce the trainable parameters while maintaining accuracy. The study utilized a standard forward problem of simulating partial differential equations (PDEs) from the field of Computational Fluid Dynamics (CFD), a well-understood area with classical PINN. A comparative analysis was performed between QA-PINN, equivalent classical vanilla PINN (c-PINN), and state-of-the-art classical PINN - Globally Adaptive Activation Function PINN (GAAF-PINN). All methods were benchmarked against the ground-truth analytical solution for 1D Burger's equation. The analysis is conducted for 3, 4, and 5-qubit QA-PINN architectures. In comparison to c-PINN and GAAF-PINN, 4 and 5-qubit QA-PINN is shown to reduce the number of trainable parameters of the network by 20%, and while maintaining the accuracy. The reduced number of trainable parameters indicates the reduced complexity of the model and the reduced risk of overfitting, making it more generalizable. Thus, the proposed approach can have a significant impact on PINNs enhancing generalization and improving training efficiency for deploying the model for real-world applications.
We present a hybrid quantum-classical framework augmented with learned error mitigation for solving the viscous Burgers equation on noisy intermediate-scale quantum (NISQ) hardware. Using the Cole-Hopf transformation, the nonlinear Burgers equation is mapped to a diffusion equation, discretized on uniform grids, and encoded into a quantum state whose time evolution is approximated via Trotterized nearest-neighbor circuits implemented in Qiskit. Quantum simulations are executed on noisy Aer backends and IBM superconducting quantum devices and are benchmarked against high-accuracy classical solutions obtained using a Krylov-based solver applied to the corresponding discretized Hamiltonian. From measured quantum amplitudes, we reconstruct the velocity field and evaluate physical and numerical diagnostics, including the L2 error, shock location, and dissipation rate, both with and without zero-noise extrapolation (ZNE). To enable data-driven error mitigation, we construct a large parametric dataset by sweeping viscosity, time step, grid resolution, and boundary conditions, producing matched tuples of noisy, ZNE-corrected, hardware, and classical solutions together with detailed circuit metadata. Leveraging this dataset, we train an attention-based graph neural network that incorporates circuit structure, light-cone information, global circuit parameters, and noisy quantum outputs to predict error-mitigated solutions. Across a wide range of parameters, the learned model consistently reduces the discrepancy between quantum and classical solutions beyond what is achieved by ZNE alone. We discuss extensions of this approach to higher-dimensional Burgers systems and more general quantum partial differential equation solvers, highlighting learned error mitigation as a promising complement to physics-based noise reduction techniques on NISQ devices.
The solution for non-linear, complex partial differential Equations (PDEs) is achieved through numerical approximations, which yield a linear system of equations. This approach is prevalent in Computational Fluid Dynamics (CFD), but it restricts the mesh size since the solution of the linear system becomes computationally intractable when the mesh resolution increases. The reliance on the ability of High-Performance Computers (HPC) to scale up and meet these requirements is myopic; such very high-fidelity simulations require a paradigm shift in computing. This paper presents an exploration of quantum methodologies aimed at achieving high accuracy in solving such a large system of equations. Leveraging recent works in Quantum Linear Solver Algorithms (QLSA) and variational algorithms suitable for Quantum Simulation in HPC, we aspire to push the boundaries of CFD-relevant problems that can be solved on hybrid quantum-classical framework. To this end, we consider the 2D, transient, incompressible, viscous, non-linear coupled Burgers equation as a test problem and investigate the accuracy of our approach by comparing results with a classical linear system of equation solvers, such as the Generalized Minimal RESidual method (GMRES). Through rigorous testing, our findings demonstrate that our quantum methods yield results comparable in accuracy to traditional approaches. Additionally, we demonstrate the accuracy, scalability, and consistency of our quantum method. Lastly, we present an insightful estimation of the resources our quantum algorithm needs to solve systems with nearly 2 billion mesh points.
Abstract Quantum circuits with trainable parameters, paired with classical optimization routines can be used as machine learning models. The recently popularized physics-informed neural network (PINN) approach is a machine learning algorithm that solves differential equations by incorporating them into a loss function. Being a mesh-free method, it is a promising approach for computational fluid dynamics. The question arises whether the properties of quantum circuits can be leveraged for a quantum physics-informed machine learning model. In this study, we compare the classical PINN-ansatz and its quantum analog, which we name the physics-informed quantum circuit (PIQC). The PIQC simulations are performed on a noise-free quantum computing simulator. Studying various differential equations, we compare expressivity, accuracy and convergence properties. We find that one-dimensional problems, such as the linear transport of a Gaussian-pulse or Burgers’ equation, allow a successful approximation with the classical and the quantum ansatz. For these examples, the PIQC overall performs similarly to PINN and converges more consistently and for Burgers’ equations even faster. While this is promising, the chosen quantum circuit approach struggles to approximate discontinuous solutions which the classical PINN-ansatz can represent. Based on this comparison, we extrapolate that the required number of qubits for solving two-dimensional problems in aerodynamics may already be available in the next few years. However, the acceleration potential is currently unclear and challenges like noisy circuits and approximations of discontinuous solutions have to be overcome.