We present a focused and reproducible study of multi-horizon forecasting on the Lomnicky Stit neutron monitor (LMKS) time series. Our evaluation suite covers simple seasonal baselines, modern deep sequence models, and functional and quantum-inspired architectures, including Seasonal Naive, Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), N-BEATS, Kolmogorov-Arnold Networks (KAN), and two quantum-inspired variants, QiLSTM and QiKAN. We describe the dataset characteristics, diagnostic analysis, preprocessing pipeline, and training procedures, and report aggregate point-forecast performance using mean absolute error (MAE) and root mean squared error (RMSE) for all evaluated models. Our quick-run results indicate that the quantum-inspired KAN variant, QiKAN, achieves the lowest aggregate forecasting error among the evaluated configurations, while the simple Seasonal Naive baseline remains remarkably competitive. These results suggest that, for highly periodic scientific monitoring time series, models incorporating strong seasonal or low-dimensional functional priors can match or outperform substantially more complex sequence architectures. The findings motivate further investigation of parsimonious and decomposable function approximators for forecasting periodic scientific signals.
Comments
14 pages, 3 figures, 1 table, accepted at the Computing Conference 2026
We present a focused and reproducible study of multi-horizon forecasting on the Lomnicky Stit neutron monitor (LMKS) time series. Our evaluation suite covers simple seasonal baselines, modern deep sequence models, and functional and quantum-inspired architectures, including Seasonal Naive, Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), N-BEATS, Kolmogorov-Arnold Networks (KAN), and two quantum-inspired variants, QiLSTM and QiKAN. We describe the dataset characteristics, diagnostic analysis, preprocessing pipeline, and training procedures, and report aggregate point-forecast performance using mean absolute error (MAE) and root mean squared error (RMSE) for all evaluated models. Our quick-run results indicate that the quantum-inspired KAN variant, QiKAN, achieves the lowest aggregate forecasting error among the evaluated configurations, while the simple Seasonal Naive baseline remains remarkably competitive. These results suggest that, for highly periodic scientific monitoring time series, models incorporating strong seasonal or low-dimensional functional priors can match or outperform substantially more complex sequence architectures. The findings motivate further investigation of parsimonious and decomposable function approximators for forecasting periodic scientific signals.
Long short-term memory (LSTM) models are a particular type of recurrent neural networks (RNNs) that are central to sequential modeling tasks in domains such as urban telecommunication forecasting, where temporal correlations and nonlinear dependencies dominate. However, conventional LSTMs suffer from high parameter redundancy and limited nonlinear expressivity. In this work, we propose the Quantum-inspired Kolmogorov-Arnold Long Short-Term Memory (QKAN-LSTM), which integrates Data Re-Uploading Activation (DARUAN) modules into the gating structure of LSTMs. Each DARUAN acts as a quantum variational activation function (QVAF), enhancing frequency adaptability and enabling an exponentially enriched spectral representation without multi-qubit entanglement. The resulting architecture preserves quantum-level expressivity while remaining fully executable on classical hardware. Empirical evaluations on three datasets, Damped Simple Harmonic Motion, Bessel Function, and Urban Telecommunication, demonstrate that QKAN-LSTM achieves superior predictive accuracy and generalization with a 79% reduction in trainable parameters compared to classical LSTMs. We extend the framework to the Jiang-Huang-Chen-Goan Network (JHCG Net), which generalizes KAN to encoder-decoder structures, and then further use QKAN to realize the latent KAN, thereby creating a Hybrid QKAN (HQKAN) for hierarchical representation learning. The proposed HQKAN-LSTM thus provides a scalable and interpretable pathway toward quantum-inspired sequential modeling in real-world data environments.
Traffic matrices (TMs) capture network-wide origin-destination demand and are central to traffic engineering, yet accurate whole-matrix forecasting remains challenging when prediction must be performed under the memory, update, and training-budget constraints of online network control. This paper investigates whether compact quantum-inspired recurrent models can provide effective TM forecasts without relying on dedicated graph, transformer, or diffusion modules. We adapt gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers (QKAN-FWPs) to direct multi-step Abilene TM forecasting, where each model predicts the next 20 five-minute frames of a 144-channel origin-destination (OD) matrix from a two-hour history. We benchmark three QKAN placement variants against a matched-size long short-term memory (LSTM) network, a larger LSTM, and a classical gated fast-weight programmer under a shared fixed-budget training protocol. Among the evaluated recurrent models, G-QKANFWP achieves the best pooled root-mean-square error (RMSE), while using only 22.4% of the larger LSTM. It also outperforms both the matched-size LSTM and the classical G-FWP baseline, indicating that the gain is not due to gated fast-weight framework alone. Convergence and channel-wise analyses further show that the quantum-inspired variants obtain lower validation-loss area under the learning curve (AULC) than matched-size recurrent baselines, while G-QKANFWP and GQKAN-FWP achieve substantially more OD-channel wins. These results identify a classical slow programmer with a quantum-inspired fast programmer as a promising accuracy-efficiency design for resource-conscious network traffic-matrix forecasting.
Forecasting weather is critical in different application sectors and affects decision-making and resource distribution. Long Short-Term Memory (LSTM) models are popular, but they can be improved even further with the use of quantum computing techniques. This paper discusses a Quantum Long Short-Term Memory (QLSTM) simulated in PennyLane-based simulators. According to the experimental results, the suggested QLSTM model produced a mean absolute error (MAE) of 0.009066, a test mean square error (MSE) of 0.000162, and a coefficient of determination (R2) of 0.999846, surpassing both quantum models and classical baselines. These results highlight the potential of quantum-assisted architectures to improve accuracy in weather prediction. The research advances weather forecasting and contributes to quantum computing applications, guiding researchers in developing precise weather prediction models and enhancing decision-making in weather-sensitive domains. The proposed 4-qubit quantum model was tested with noise models, and it demonstrated high learning efficiency and strong robustness against realistic NISQ-level noise, maintaining stable optimization and low error even under moderate perturbations. • Quantum LSTM Development: The classical LSTM was extended into the quantum domain using Variational Quantum Circuits (VQCs) for feature extraction and data compression, applied to weather prediction tasks. • Experimental Evaluation: Three QLSTM variants (4, 6, and 8 qubit) were tested on two weather datasets and compared with classical LSTM and state-of-the-art QLSTM models. • Performance and Robustness: The QLSTM models outperformed baseline models, with the 4-qubit model showing strong learning efficiency and robustness under realistic NISQ-level noise.
Hybrid quantum-classical recurrent architectures have been proposed for capturing non-stationary, fat-tailed dynamics typical of financial time series, but most published evaluations compare a Quantum Long Short-Term Memory network only against plain Long Short-Term Memory on a single asset. This study contributes a controlled multi-baseline benchmark using four synthetic asset classes generated by calibrated Generalised Autoregressive Conditional Heteroskedasticity processes, comparing six architectures at a matched parameter budget below three hundred and fifty trainable parameters across five random seeds. The comparison set includes Long Short-Term Memory, Bidirectional Long Short-Term Memory, a compact Patch Time Series Transformer, Neural Basis Expansion Analysis, an Inverted Transformer, and a four-qubit Quantum Long Short-Term Memory with two variational blocks. Significance is established through Wilcoxon signed-rank tests, walk-forward validation across three expanding folds, depolarising-noise robustness sweeps, and a variational circuit depth ablation. The principal empirical finding is that compact classical recurrence dominates the benchmark on root mean squared error, while the quantum model exhibits the lowest seed-to-seed variance and the highest directional accuracy on the most volatile asset class.
Multi-output time-series forecasting in energy systems is challenging because of nonlinear dynamics, multi-scale seasonality, and strong dependencies across correlated series. In this work, we investigate two hybrid quantum-classical frameworks for multi-stream time-series forecasting on a real Smart Meter dataset comprising 103 household electricity consumption time-series, with experiments executed on the ibm_marrakesh superconducting quantum processor. The first model, Kernelized Quantum Reservoir Computing with Repeated Measurement (KQRC-RM), combines coupled quantum reservoirs, ancilla-assisted repeated measurement, and kernelized readouts to model temporal dynamics and cross-stream correlations jointly. For a 3-stream time-series input and output, the KQRC-RM model using 114 qubits achieves an MAE of 0.0811 on MPS simulator (36.92\% improvement over its classical analog) whereas performance degrades to an MAE of 0.1524 on hardware. The second, a Projected Quantum Kernel Gaussian Process (QGP), replaces fidelity-based kernels with projected kernels constructed from local reduced-state statistics. Using a topology-aware 100-qubit QGP model to predict 100 multi-output time-series values, we observe 49\% of time-series outputs achieve high-accuracy predictions (MAE <0.15), with an average MAE of 0.082 for this low-error group. The medium-error regime (MAE 0.15-0.35) has an average MAE of 0.229, while the high-error regime (MAE >0.35) has an average MAE of 0.664. Overall, this reduces the average MAE relative to the classical GP baseline by 62.01\% on MPS simulator and 40.37\% on hardware. Together, these results demonstrate the feasibility of hybrid quantum machine learning for multi-input, multi-output time-series forecasting at the 100+ qubit scale on NISQ devices.
Time-series forecasting is vital across sectors such as finance, energy, and environmental science, where accurate future predictions drive informed decision-making. Traditional statistical methods and deep learning models like LSTM and Transformers, while effective, often struggle with high-dimensional data and long-term dependencies. In this paper, we propose a hybrid quantum-classical model that utilizes Parameterized Quantum Circuits (PQCs) to capture complex temporal patterns in multivariate time-series data. Our architecture integrates a classical encoder, a quantum variational processor, and a classical decoder, trained end-to-end using gradient-based optimization. Experiments conducted on benchmark datasets—electricity load, stock prices, and weather forecasting—demonstrate that the hybrid model consistently outperforms classical baselines in terms of Mean Squared Error (MSE), Mean Absolute Error (MAE), and R² score. Robustness analysis confirms the model’s resilience to moderate quantum noise, while an ablation study highlights the performance gain from quantum components. This work showcases the potential of hybrid quantum-classical approaches on Noisy Intermediate-Scale Quantum (NISQ) devices and lays a foundation for scalable, real-world quantum machine learning applications.