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

arXiv:2608.23119

Quantum Reservoir Computing with Physics-Informed Correction for Reduced-Order PDE Forecasting

Krishna Bhatia, Harsh, Shalini Devendrababu

quant-phcs.LGSubmitted Aug 24, 2026• Announced Aug 25, 2026
arXivHTMLPDF

Abstract

We study a hybrid proposal--correction architecture for reduced-order PDE forecasting in which a pure-state quantum reservoir computer (QRC) predicts latent coefficient dynamics and a PINN-based physics-informed corrector (PIC) refines local rollout windows. The method is evaluated on Burgers and Kuramoto--Sivashinsky (KS), with KS as the primary chaotic benchmark. On KS, QRC+PIC consistently improves over QRC alone in RMSE, NRMSE, and PDE residual, while Burgers highlights a regime in which simple baselines remain strong. These results suggest that QRC proposals with local physics-informed correction are a viable benchmark-dependent reduced-order forecasting strategy.

Journal reference
Advances in Quantum Neural and Reinforcement Learning, Communications in Computer and Information Science, vol. 3063, Springer Singapore, 2026
Comments
11 pages, 5 figures. Accepted at QNRL@WCCI 2026. To appear in Advances in Quantum Neural and Reinforcement Learning, Communications in Computer and Information Science, vol. 3063, Springer Singapore, 2026

Related papers

Higher Order Quantum Reservoir Computing for Non-Intrusive Reduced-Order Models

Vinamr Jain, Romit Maulik

Forecasting dynamical systems is of importance to numerous real-world applications. Typically, these are obtained using first-principles-based models such as through the use of differential equations. When these equations are unknown, non-intrusive techniques must be utilized to build predictive models from data alone. Machine learning (ML) methods have recently been used for such tasks with the added advantage of significant reductions in time-to-solution for predictions during deployment. However, many state-of-the-art ML-based methods for forecasting rely on neural networks, which are expensive to train and require large amounts of memory. In this work, we propose a quantum mechanics inspired ML strategy for forecasting nonlinear dynamical systems that results in reduced training time and memory requirements. This approach, denoted the quantum reservoir computing technique (QRC), is a hybrid quantum-classical framework employing an ensemble of interconnected small quantum systems via classical linear feedback connections. By mapping the dynamical state to a suitable quantum representation amenable to unitary operations, QRC is able to predict complex nonlinear dynamical systems in a stable and accurate manner. We demonstrate the efficacy of this framework through benchmark forecasts of the NOAA Optimal Interpolation Sea Surface Temperature dataset and compare the performance of QRC to other ML methods.

arXiv:2407.21602•AIAA SciTech Forum•Jan 8, 2026•1 citation

Leveraging Metrologically Useful States in Quantum Reservoir Networks

Erik L. Connerty, Margarite LaBorde, Ethan N. Evans

Interest in using quantum computers for the purpose of predicting chaotic partial differential equations (PDEs) has been growing with the advent of newer low-error quantum computers and robust simulation tools. In this paper, we present a method that utilizes a quantum reservoir network (QRN) to predict latent space representations of the high-dimensional chaotic 1-D Kuramoto-Sivashinksy (KS) system. This hybrid approach takes advantage of advancements in classical machine learning (ML) through the use of a classical autoencoder as well as techniques from quantum metrology through the use of a unitary that creates metrologically-useful states. Through rigorous simulation and analysis, we show that the proposed method outperforms alternative QRN implementations without this metrologically-useful state preparation, and also show better performance than classical echo-state networks when weight regularization is not used. Finally, we bring to light potential issues that can arise when using autoencoders within QRC pipelines.

quant-pharXiv:2607.06500•Jul 8, 2026•1 citation

Memory-Augmented Hybrid Quantum Reservoir Computing

J. Settino, L. Salatino, L. Mariani +9 more

Reservoir computing (RC) is an effective method for predicting chaotic systems by using a high-dimensional dynamic reservoir with fixed internal weights, while keeping the learning phase linear, which simplifies training and reduces computational complexity compared to fully trained recurrent neural networks (RNNs). Quantum reservoir computing (QRC) uses the exponential growth of Hilbert spaces in quantum systems, allowing for greater information processing, memory capacity, and computational power. However, the original QRC proposal requires coherent injection of inputs multiple times, complicating practical implementation. We present a hybrid quantum-classical approach that implements memory through classical post-processing of quantum measurements. This approach avoids the need for multiple coherent input injections and is evaluated on benchmark tasks, including the chaotic Mackey-Glass time series prediction. We tested our model on two physical platforms: a fully connected Ising model and a Rydberg atom array. The optimized model demonstrates promising predictive capabilities, achieving a higher number of steps compared to previously reported approaches.

quant-pharXiv:2409.09886•Physical Review Applied•Sep 17, 2024•21 citations

QRCKAN: Kolmogorov–Arnold Readouts for Quantum Reservoir Computing of Chaotic Dynamics

Brianna Jones, Harshita Dua, Harini Muthurengan +1 more

Quantum reservoir computing (QRC) offers a train-light approach to temporal learning by keeping the quantum dynamics fixed and training only a classical readout. Most QRC studies use linear readouts, potentially leaving nonlinear structure in measured reservoir states under-exploited. Inspired by recent reservoir-computing Kolmogorov–Arnold networks (RCKAN), we study Kolmogorov–Arnold Network (KAN)-style spline readouts for stateful QRC. Our QRCKAN architecture combines a refreshed-input, persistent-memory density-matrix reservoir with correlation observables, a shallow spline KAN readout, an optional current-state skip, and a residual formulation that adds a validation-weighted nonlinear correction to ridge regression. We summarize five seeded runs on Lorenz-63 and Mackey–Glass against matched linear QRC, stateless quantum feature maps, no-QRC controls, echo-state networks (ESNs), lag-based regressors, LSTM, and Transformer baselines. On Lorenz-63, residual QRCKAN reduces mean one-step NRMSE by 51.6% relative to QRC+Linear+Skip (0.000820 vs. 0.001696) and raises mean valid prediction time (VPT) from 102 to 218 steps. On Mackey–Glass, QRCKAN reduces mean one-step NRMSE by 78.2% and rollout NRMSE by 81.0%, while increasing mean VPT from 118 to 262 steps. Matched no-skip QRC–QFF comparisons and matched no-QRC controls support contributions from temporal state and reservoir features under the tested configurations. Because seed 0 informed architecture selection and is included in these summaries, all intervals and tests are exploratory rather than independent confirmatory inference. Strong ESNs remain superior in one-step accuracy. We claim an exploratory nonlinear-readout improvement within simulated QRC, not a general quantum advantage.

Proceedings of the AAAI Symposium Series•Nov 6, 2026•0 citations

Hybrid LLM-Guided Search for Quantum Reservoir Architecture Design

Krishna Bhatia, Gautami Sanjay Naik

Quantum reservoir computing (QRC) uses fixed quantum dynamics as a high-dimensional temporal feature map and trains only a lightweight classical readout. QRC is attractive for near-term quantum machine learning, but its performance depends strongly on architecture choices such as input encoding, reservoir depth, entanglement topology, measurement features, state-reset policy, feature construction, and readout regularization. We introduce \method, a simulator-based benchmark that formulates QRC design as constrained black-box architecture search and evaluates whether large language models can act as proposal controllers for this search problem. The benchmark compares five policies under identical evaluation budgets: random search, evolutionary search, Bayesian/TPE optimization, a feedback-based LLM agent, and \hybrid, which combines LLM proposals with memory, mutation, crossover, duplicate avoidance, and exploration. On NARMA10, Mackey-Glass forecasting, and temporal parity, \hybrid{} is the most consistent policy: it ranks first on NARMA10 and temporal parity and second on Mackey-Glass, narrowly behind evolutionary search. Under a 25-evaluation budget and three seeds, \hybrid{} improves over random search on all tasks, including a 23.6\% relative reduction in Mackey-Glass error. The results do not show that LLMs are universal QRC optimizers; rather, they show that generative models can be useful high-level controllers when embedded inside validated, reproducible hybrid search loops.

quant-pharXiv:2607.19506•Jul 23, 2026•0 citations

A Quantum Reservoir for Neurodynamical Forecasting

Annemarie Wolff, Kathleen Hamilton, Kahn Rhrissorrakrai +3 more

Forecasting neural activity from short recordings remains a fundamental challenge. Reservoir computing may offer an efficient paradigm for temporal prediction, however classical reservoirs typically underperform in small-data regimes. Here we investigate whether quantum reservoir computing (QRC) can help overcome this limitation. Building on recent advances, we introduce a quantum reservoir based on a transverse-field Ising model, combined with heterogeneous quantum measurements and polynomial ridge regression. On a standard benchmark task, results show that the quantum reservoir outperforms a classical counterpart overall, with prediction accuracy strongly dependent on reservoir parameters. We further demonstrate feasibility by running the same task on quantum hardware. To assess performance on biological signals, we evaluate QRC on simulated human electroencephalography (EEG) data with a parallel reservoir architecture. On this challenging task, the tested quantum reservoir did not match the performance of the classical one, but it produced stable, convergent predictions. This is a meaningful first step toward forecasting of biologically realistic neural data using a quantum reservoir. Overall, our findings indicate that although current quantum hardware and parallel reservoir architectures do not yet surpass classical methods on complex neural signals, QRC can be executed on near-term devices and does converge with realistic EEG-like data. This work establishes a practical baseline for future algorithmic and hardware developments aimed at clinical time-series forecasting with quantum systems.

quant-pharXiv:2608.00139•Aug 3, 2026•0 citations
We study a hybrid proposal--correction architecture for reduced-order PDE forecasting in which a pure-state quantum reservoir computer (QRC) predicts latent coefficient dynamics and a PINN-based physics-informed corrector (PIC) refines local rollout windows. The method is evaluated on Burgers and Kuramoto--Sivashinsky (KS), with KS as the primary chaotic benchmark. On KS, QRC+PIC consistently improves over QRC alone in RMSE, NRMSE, and PDE residual, while Burgers highlights a regime in which simple baselines remain strong. These results suggest that QRC proposals with local physics-informed correction are a viable benchmark-dependent reduced-order forecasting strategy.
Forecasting dynamical systems is of importance to numerous real-world applications. Typically, these are obtained using first-principles-based models such as through the use of differential equations. When these equations are unknown, non-intrusive techniques must be utilized to build predictive models from data alone. Machine learning (ML) methods have recently been used for such tasks with the added advantage of significant reductions in time-to-solution for predictions during deployment. However, many state-of-the-art ML-based methods for forecasting rely on neural networks, which are expensive to train and require large amounts of memory. In this work, we propose a quantum mechanics inspired ML strategy for forecasting nonlinear dynamical systems that results in reduced training time and memory requirements. This approach, denoted the quantum reservoir computing technique (QRC), is a hybrid quantum-classical framework employing an ensemble of interconnected small quantum systems via classical linear feedback connections. By mapping the dynamical state to a suitable quantum representation amenable to unitary operations, QRC is able to predict complex nonlinear dynamical systems in a stable and accurate manner. We demonstrate the efficacy of this framework through benchmark forecasts of the NOAA Optimal Interpolation Sea Surface Temperature dataset and compare the performance of QRC to other ML methods.
Interest in using quantum computers for the purpose of predicting chaotic partial differential equations (PDEs) has been growing with the advent of newer low-error quantum computers and robust simulation tools. In this paper, we present a method that utilizes a quantum reservoir network (QRN) to predict latent space representations of the high-dimensional chaotic 1-D Kuramoto-Sivashinksy (KS) system. This hybrid approach takes advantage of advancements in classical machine learning (ML) through the use of a classical autoencoder as well as techniques from quantum metrology through the use of a unitary that creates metrologically-useful states. Through rigorous simulation and analysis, we show that the proposed method outperforms alternative QRN implementations without this metrologically-useful state preparation, and also show better performance than classical echo-state networks when weight regularization is not used. Finally, we bring to light potential issues that can arise when using autoencoders within QRC pipelines.
Reservoir computing (RC) is an effective method for predicting chaotic systems by using a high-dimensional dynamic reservoir with fixed internal weights, while keeping the learning phase linear, which simplifies training and reduces computational complexity compared to fully trained recurrent neural networks (RNNs). Quantum reservoir computing (QRC) uses the exponential growth of Hilbert spaces in quantum systems, allowing for greater information processing, memory capacity, and computational power. However, the original QRC proposal requires coherent injection of inputs multiple times, complicating practical implementation. We present a hybrid quantum-classical approach that implements memory through classical post-processing of quantum measurements. This approach avoids the need for multiple coherent input injections and is evaluated on benchmark tasks, including the chaotic Mackey-Glass time series prediction. We tested our model on two physical platforms: a fully connected Ising model and a Rydberg atom array. The optimized model demonstrates promising predictive capabilities, achieving a higher number of steps compared to previously reported approaches.
Quantum reservoir computing (QRC) offers a train-light approach to temporal learning by keeping the quantum dynamics fixed and training only a classical readout. Most QRC studies use linear readouts, potentially leaving nonlinear structure in measured reservoir states under-exploited. Inspired by recent reservoir-computing Kolmogorov–Arnold networks (RCKAN), we study Kolmogorov–Arnold Network (KAN)-style spline readouts for stateful QRC. Our QRCKAN architecture combines a refreshed-input, persistent-memory density-matrix reservoir with correlation observables, a shallow spline KAN readout, an optional current-state skip, and a residual formulation that adds a validation-weighted nonlinear correction to ridge regression. We summarize five seeded runs on Lorenz-63 and Mackey–Glass against matched linear QRC, stateless quantum feature maps, no-QRC controls, echo-state networks (ESNs), lag-based regressors, LSTM, and Transformer baselines. On Lorenz-63, residual QRCKAN reduces mean one-step NRMSE by 51.6% relative to QRC+Linear+Skip (0.000820 vs. 0.001696) and raises mean valid prediction time (VPT) from 102 to 218 steps. On Mackey–Glass, QRCKAN reduces mean one-step NRMSE by 78.2% and rollout NRMSE by 81.0%, while increasing mean VPT from 118 to 262 steps. Matched no-skip QRC–QFF comparisons and matched no-QRC controls support contributions from temporal state and reservoir features under the tested configurations. Because seed 0 informed architecture selection and is included in these summaries, all intervals and tests are exploratory rather than independent confirmatory inference. Strong ESNs remain superior in one-step accuracy. We claim an exploratory nonlinear-readout improvement within simulated QRC, not a general quantum advantage.
Quantum reservoir computing (QRC) uses fixed quantum dynamics as a high-dimensional temporal feature map and trains only a lightweight classical readout. QRC is attractive for near-term quantum machine learning, but its performance depends strongly on architecture choices such as input encoding, reservoir depth, entanglement topology, measurement features, state-reset policy, feature construction, and readout regularization. We introduce \method, a simulator-based benchmark that formulates QRC design as constrained black-box architecture search and evaluates whether large language models can act as proposal controllers for this search problem. The benchmark compares five policies under identical evaluation budgets: random search, evolutionary search, Bayesian/TPE optimization, a feedback-based LLM agent, and \hybrid, which combines LLM proposals with memory, mutation, crossover, duplicate avoidance, and exploration. On NARMA10, Mackey-Glass forecasting, and temporal parity, \hybrid{} is the most consistent policy: it ranks first on NARMA10 and temporal parity and second on Mackey-Glass, narrowly behind evolutionary search. Under a 25-evaluation budget and three seeds, \hybrid{} improves over random search on all tasks, including a 23.6\% relative reduction in Mackey-Glass error. The results do not show that LLMs are universal QRC optimizers; rather, they show that generative models can be useful high-level controllers when embedded inside validated, reproducible hybrid search loops.
Forecasting neural activity from short recordings remains a fundamental challenge. Reservoir computing may offer an efficient paradigm for temporal prediction, however classical reservoirs typically underperform in small-data regimes. Here we investigate whether quantum reservoir computing (QRC) can help overcome this limitation. Building on recent advances, we introduce a quantum reservoir based on a transverse-field Ising model, combined with heterogeneous quantum measurements and polynomial ridge regression. On a standard benchmark task, results show that the quantum reservoir outperforms a classical counterpart overall, with prediction accuracy strongly dependent on reservoir parameters. We further demonstrate feasibility by running the same task on quantum hardware. To assess performance on biological signals, we evaluate QRC on simulated human electroencephalography (EEG) data with a parallel reservoir architecture. On this challenging task, the tested quantum reservoir did not match the performance of the classical one, but it produced stable, convergent predictions. This is a meaningful first step toward forecasting of biologically realistic neural data using a quantum reservoir. Overall, our findings indicate that although current quantum hardware and parallel reservoir architectures do not yet surpass classical methods on complex neural signals, QRC can be executed on near-term devices and does converge with realistic EEG-like data. This work establishes a practical baseline for future algorithmic and hardware developments aimed at clinical time-series forecasting with quantum systems.