Multivariate Time Series Forecasting with Gate-Based Quantum Reservoir Computing on NISQ Hardware
This work addresses the problem of efficient multivariate forecasting for quantum computing applications, offering a practical approach on current hardware, though it is incremental in adapting existing quantum reservoir techniques.
The paper tackles multivariate time series forecasting by developing a gate-based quantum reservoir computing method optimized for near-term quantum hardware, achieving mean square errors of 0.0087 on Lorenz-63 and 0.0036 on ENSO datasets, performing competitively with classical methods and showing that hardware noise can act as a regularizer.
Quantum reservoir computing (QRC) offers a hardware-friendly approach to temporal learning, yet most studies target univariate signals and overlook near-term hardware constraints. This work introduces a gate-based QRC for multivariate time series (MTS-QRC) that pairs injection and memory qubits and uses a Trotterized nearest-neighbor transverse-field Ising evolution optimized for current device connectivity and depth. On Lorenz-63 and ENSO, the method achieves a mean square error (MSE) of 0.0087 and 0.0036, respectively, performing on par with classical reservoir computing on Lorenz and above learned RNNs on both, while NVAR and clustered ESN remain stronger on some settings. On IBM Heron R2, MTS-QRC sustains accuracy with realistic depths and, interestingly, outperforms a noiseless simulator on ENSO; singular value analysis indicates that device noise can concentrate variance in feature directions, acting as an implicit regularizer for linear readout in this regime. These findings support the practicality of gate-based QRC for MTS forecasting on NISQ hardware and motivate systematic studies on when and how hardware noise benefits QRC readouts.