Abstract Chebyshev polynomials have shown significant promise as an efficient tool for both classical and quantum neural networks to solve linear and nonlinear differential equations (DEs). In this work, we adapt and generalize this framework in a quantum machine learning setting for a variety of problems, including the 2D Poisson’s equation, second-order linear DE, system of DEs, nonlinear Duffing and Riccati equation. In particular, we propose in the quantum setting a modified Self-Adaptive Physics-Informed Neural Network approach, where self-adaptive weights are applied to problems with multi-objective loss functions. We further explore capturing correlations in our loss function using a quantum-correlated measurement, resulting in improved accuracy for initial value problems. We analyse also the use of entangling layers and their impact on the solution accuracy for second-order DEs. The results indicate a promising approach to the near-term evaluation of DEs on quantum devices.
Abstract Chebyshev polynomials have shown significant promise as an efficient tool for both classical and quantum neural networks to solve linear and nonlinear differential equations (DEs). In this work, we adapt and generalize this framework in a quantum machine learning setting for a variety of problems, including the 2D Poisson’s equation, second-order linear DE, system of DEs, nonlinear Duffing and Riccati equation. In particular, we propose in the quantum setting a modified Self-Adaptive Physics-Informed Neural Network approach, where self-adaptive weights are applied to problems with multi-objective loss functions. We further explore capturing correlations in our loss function using a quantum-correlated measurement, resulting in improved accuracy for initial value problems. We analyse also the use of entangling layers and their impact on the solution accuracy for second-order DEs. The results indicate a promising approach to the near-term evaluation of DEs on quantum devices.
We propose a physics-informed quantum algorithm to solve nonlinear and multidimensional differential equations (DEs) in a quantum latent space. We suggest a strategy for building quantum models as state overlaps, where exponentially large sets of independent basis functions are used for implicitly representing solutions. By measuring the overlaps between states which are representations of DE terms, we construct a loss that does not require independent sequential function evaluations on grid points. In this sense, the solver evaluates the loss in an intrinsically parallel way, utilizing a global type of the model. When the loss is trained variationally, our approach can be related to the differentiable quantum circuit protocol, which does not scale with the training grid size. Specifically, using the proposed model definition and feature map encoding, we represent function- and derivative-based terms of a differential equation as corresponding quantum states. Importantly, we propose an efficient way for encoding nonlinearity, for some bases requiring only an additive linear increase of the system size O(N+p) in the degree of nonlinearity p. By utilizing basis mapping, we show how the proposed model can be evaluated explicitly. This allows to implement arbitrary functions of independent variables, treat problems with various initial and boundary conditions, and include data and regularization terms in the physics-informed machine learning setting. On the technical side, we present toolboxes for exponential Chebyshev and Fourier basis sets, developing tools for automatic differentiation and multiplication, implementing nonlinearity, and describing multivariate extensions. The approach is compatible with, and tested on, a range of problems including linear, nonlinear and multidimensional differential equations.
Physics-informed neural networks (PINNs) have emerged as a versatile approach for solving nonlinear partial differential equations (PDEs), yet achieving high accuracy efficiently using these techniques remains challenging for high-dimensional or multiscale systems. Here, we present a hybrid quantum-classical framework that enhances Quantum PINNs (QPINNs) through adaptive collocation point sampling and loss-aware attention mechanisms. By dynamically prioritizing points in regions with large PDE residuals or steep solution gradients, our method mitigates the spectral bias inherent in conventional PINNs. Current Quantum Physics-Informed Neural Networks are commonly assumed to be limited by the expressive power of quantum circuits. In our work, we observed that, across diverse differential equations, optimization - not only expressivity - can be an important bottleneck. Furthermore, a trainable loss-weighting scheme balances contributions from physics residuals, boundary conditions, and data fidelity during training. Integrating these strategies with quantum computing techniques (including variational quantum circuits and quantum gradient estimation) can yield at least a 60% improvement in solution accuracy under specific regimes for benchmark fluid flows and reaction-diffusion systems. Finally, we argue that merely increasing model expressivity is insufficient for resolving complex PDEs via QPINNs, as they remain constrained by the structural optimization limitations of classical PINNs. This framework provides a scalable pathway for quantum-enhanced scientific machine learning, bridging physics-based modeling with emerging quantum computational capabilities.
Quantum algorithms based on linear-system approaches for solving differential equations demand qubit and precision resources beyond near-term capabilities. To address these challenges, this work proposes a physics-informed quantum machine learning (PIQML) framework with hard constraint embedding, specifically designed for NISQ era. Within this framework, parameterized quantum circuits serve as machine learning models, where the input variable is encoded into a high-dimensional feature space via a Fourier feature map. Subsequently, to eliminate approximation errors in critical physical conditions, the solution is constructed through a rigorously designed function mapper that analytically enforces initial conditions as hard constraints. Crucially, we compute derivatives with respect to the input variable using the parameter-shift rule---a quantum native gradient evaluation technique that avoids classical discretization. Unlike generic loss functions that target abstract data patterns, our loss function focuses on the differential equation residual and reference data. This design ensures that the trained model not only approximates the data but also intrinsically satisfies the physical constraint expressed by the DE itself. Our method is validated on several differential equations, including highly oscillatory ones, demonstrating its capability to tackle challenging nonlinear dynamics. Results demonstrate that our quantum model successfully learns the solution, showing close agreement with a high-precision classical numerical benchmark.
This paper proposes a novel approach for solving nonlinear partial differential equations (PDEs) with a quantum computer, the trainable embedding quantum physics informed neural network (TE-QPINN). We combine quantum machine learning (QML) with physics informed neural networks (PINNs) in a hybrid approach. By leveraging the advantages of classical and quantum computers, we can create algorithms that have a potential to be run on noisy intermediate-scale quantum devices (NISQ). We use feedforward neural networks (FNN) as problem-agnostic embedding functions, giving the used quantum circuit greater expressibility than previously introduced embedding. This expressibility allows us to solve a wide range of problems without using a problem specific ansatz. Additionally, we introduce a hybrid backpropagation algorithm that allows efficient updates of the used weights and biases in the FNN embedding functions. In this paper we showcase the capabilities of TE-QPINNs of a wide range of problems, including the two-dimensional Poisson, Burgers and Navier-Stokes equations. In direct comparison with classical PINNs, this approach showed an ability to achieve superior results while using the same number of parameters, highlighting their potential for more efficient optimization in high-dimensional parameter spaces, which could be transformative for future applications.
Recently, physics-informed neural networks (PINNs) have aroused an upsurge in the field of scientific computing including solving partial differential equations (PDEs), which convert the task of solving PDEs into an optimization challenge by adopting governing equations and definite conditions or observation data as loss functions. Essentially, the underlying logic of PINNs is based on the universal approximation and differentiability properties of classical neural networks (NNs). Recent research has revealed that quantum neural networks (QNNs), known as parameterized quantum circuits, also exhibit universal approximation and differentiability properties. This observation naturally suggests the application of PINNs to QNNs. In this work, we introduce a physics-informed quantum neural network (PI-QNN) by employing the QNN as the function approximator for solving forward and inverse problems of PDEs. The performance of the proposed PI-QNN is evaluated by various forward and inverse PDE problems. Numerical results indicate that PI-QNN demonstrates superior convergence over PINN when solving PDEs with exact solutions that are strongly correlated with trigonometric functions. Moreover, its accuracy surpasses that of PINN by two to three orders of magnitude, while requiring fewer trainable parameters. However, the computational time of PI-QNN exceeds that of PINN due to its operation on classical computers. This limitation may improve with the advent of commercial quantum computers in the future. Furthermore, we briefly investigate the impact of network architecture on PI-QNN performance by examining two different QNN architectures. The results suggest that increasing the number of trainable network layers can enhance the expressiveness of PI-QNN. However, an excessive number of data encoding layers significantly increases computational time, rendering the marginal gains in performance insufficient to compensate for the shortcomings in computational efficiency.
In recent years, Quantum Computing has revolutionized the field of physics by enabling researchers to tackle complex problems that were previously unsolvable. The ability to simulate and analyze phenomena at a quantum level has led to significant breakthroughs in our understanding of the universe. In this article, we describe and discuss how quantum computers are being used for cutting-edge research in quantum physics. The time-independent Schrödinger equation is a cornerstone of quantum mechanics, yet its solution for complex systems is a formidable computational challenge. Quantum Physics-Informed Neural Networks (QPINNs) have emerged as a promising paradigm, leveraging Quantum Neural Networks (QNNs) as a wavefunction ansatz within a physics-informed machine learning framework. A critical and often overlooked aspect of training these models is the management of the multi-term loss function, which balances adherence to the governing Partial Differential Equation (PDE) with physical constraints such as normalization. This paper presents a comprehensive implementation and comparative analysis of two distinct Dynamic Loss Weighting (DLW) strategies for training QPINNs to solve the 1D time-independent Schrödinger equation. The first strategy is an adaptive, gradient-based method that dynamically balances loss components based on their real-time impact on model parameters. The second is a pre-scheduled annealing method that follows a curriculum-like approach, prioritizing different physical constraints at different stages of training. We apply these methods to two benchmark systems: the Quantum Harmonic Oscillator (QHO) and the Finite Square Well. Our results demonstrate that the adaptive, gradient-based DLW, when paired with a physic informed wavefunction ansatz for the QHO, achieves remarkable accuracy, converging to the exact ground state energy of E=0.5. Conversely, the scheduled annealing strategy applied to Square Well, using a more generic ansatz, converges to a plausible energy but with a higher residual loss. This comparative analysis reveals a crucial insight: the effectiveness of a DLW strategy is deeply intertwined with the physical-informedness of the underlying wavefunction ansatz. This suggests that a synergistic co-design philosophy, which considers the interplay between the quantum model's architecture and the adaptive training algorithm, is essential for developing robust and accurate QPINN-based solvers for quantum systems.