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

TL;DR

This paper introduces QLIF-CAST, a quantum neural network model for time-series weather forecasting that outperforms classical models in accuracy and training speed, verified on real quantum hardware.

Contribution

It extends the Quantum Leaky Integrate-and-Fire model to regression tasks and demonstrates its advantages over classical and other quantum models in weather prediction.

Findings

QLIF-CAST achieves 15.4% lower MSE than classical LIF models.

It converges up to 94% faster than quantum LSTM and QNN models.

Hardware tests show reliable execution with minimal deviation.

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.