QLIF-CAST: Quantum Leaky-Integrate-and-Fire for Time-Series Weather Forecasting

2026-05-18

AI Summary

This study addresses the challenges of accuracy and efficiency in multivariate time series weather forecasting by proposing a hybrid quantum-classical recurrent architecture, which extends the quantum leaky integrate-and-fire (QLIF) spiking neural network to continuous-valued regression tasks for the first time. The approach encodes neuronal activation states using single-qubit superposition and models quantum neuron dynamics through Rx rotation gates combined with T1 relaxation mechanisms. Experimental results demonstrate that, compared to a parameter-matched classical LIF model, the proposed method achieves a 15.4% reduction in mean squared error (MSE) and a 4.4% reduction in mean absolute error (MAE). Furthermore, it reduces training time by up to 94% relative to QLSTM and standard quantum neural networks (QNNs), while achieving high-fidelity execution on IBM’s 156-qubit quantum processor, thereby validating the superiority of quantum neurons in regression tasks.

Abstract

Accurate and efficient time-series forecasting remains a challenging problem for both classical and quantum neural architectures, particularly in multivariate environmental settings. This work adapts the Quantum Leaky Integrate-and-Fire (QLIF) spiking neural network for time-series regression tasks, specifically short-term multivariate weather forecasting. We extend QLIF beyond classification and demonstrate its applicability to continuous-valued prediction problems. The QLIF-CAST model encodes neuron excitation states as single-qubit quantum superpositions, driven by Rx rotation gates and T1 relaxation decay, and is embedded within a hybrid quantum-classical recurrent architecture. We conduct two distinct evaluations. First, a controlled comparison against a parameter-matched classical LIF baseline on a multivariate weather dataset shows that QLIF-CAST achieves 15.4% lower MSE and 4.4% lower MAE, demonstrating that quantum neuronal dynamics reduce prediction error over classical equivalents. Second, a cross-domain comparative analysis with state-of-the-art quantum LSTM (QLSTM) and quantum neural network (QNN) models on air quality and wind speed benchmarks reveals that QLIF-CAST converges in up to 94% less training time, occupying a distinct position in the speed-error trade-off space. Hardware verification on IBM Marrakesh (156-qubit QPU) confirms reliable circuit execution with only 1.2% average deviation from simulation.

Problem

• time-series forecasting
• weather prediction
• quantum neural networks
• multivariate environmental data
• short-term forecasting

Innovation

• Quantum Spiking Neural Network
• Time-Series Forecasting
• Hybrid Quantum-Classical Architecture
• QLIF
• Quantum Machine Learning