Quantum Fourier Transform Based Kernel for Solar Irrandiance Forecasting
By: Nawfel Mechiche-Alami , Eduardo Rodriguez , Jose M. Cardemil and more
Potential Business Impact:
Predicts future weather patterns with better accuracy.
This study proposes a Quantum Fourier Transform (QFT)-enhanced quantum kernel for short-term time-series forecasting. Each signal is windowed, amplitude-encoded, transformed by a QFT, then passed through a protective rotation layer to avoid the QFT/QFT adjoint cancellation; the resulting kernel is used in kernel ridge regression (KRR). Exogenous predictors are incorporated by convexly fusing feature-specific kernels. On multi-station solar irradiance data across Koppen climate classes, the proposed kernel consistently improves median R2 and nRMSE over reference classical RBF and polynomials kernels, while also reducing bias (nMBE); complementary MAE/ERMAX analyses indicate tighter average errors with remaining headroom under sharp transients. For both quantum and classical models, the only tuned quantities are the feature-mixing weights and the KRR ridge alpha; classical hyperparameters (gamma, r, d) are fixed, with the same validation set size for all models. Experiments are conducted on a noiseless simulator (5 qubits; window length L=32). Limitations and ablations are discussed, and paths toward NISQ execution are outlined.
Similar Papers
Federated Quantum Kernel Learning for Anomaly Detection in Multivariate IoT Time-Series
Machine Learning (CS)
Finds weird problems in machines using quantum power.
On the similarity of bandwidth-tuned quantum kernels and classical kernels
Quantum Physics
Quantum computers can't beat regular computers here.
A Quantum Tensor Network-Based Viewpoint for Modeling and Analysis of Time Series Data
Machine Learning (CS)
Makes smart computers understand their mistakes.