arXiv 2605.183332026-10-08quant-phcs.LG

QLIF-CAST：用于时间序列天气预报的量子泄漏积分-放电神经网络

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

eBrain Lab, Division of Engineering, New York University Abu Dhabi（eBrain实验室，工程系，纽约大学阿布扎克分校）；Center for Quantum and Topological Systems, NYUAD Research Institute, New York University Abu Dhabi（量子与拓扑系统中心，NYUAD研究学院，纽约大学阿布扎克分校）

Alberto Marchisio, Aayan Ebrahim, Nouhaila Innan, Muhammad Kashif, Muhammad Shafique

备注：: To appear at the IEEE International Conference on Quantum Artificial Intelligence (QAI), Nottingham, UK, December 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出QLIF-CAST模型，将量子泄漏积分-放电神经网络应用于多变量天气短期预报，通过量子神经动态降低预测误差，且在训练时间与精度之间取得良好平衡。

摘要：

准确且高效的时序预测仍然是经典和量子神经架构在多变量环境设置中的挑战性问题。本文将量子泄漏积分-放电（QLIF）脉冲神经网络适应于时序回归任务，特别是短期多变量天气预报。我们扩展了QLIF的应用范围，证明其适用于连续值预测问题。QLIF-CAST模型将神经元激发状态编码为单量子比特的量子叠加态，由Rx旋转门和T1弛豫衰减驱动，并嵌入在混合量子-经典递归架构中。我们进行了两项不同的评估。首先，与参数匹配的经典LIF基线在多变量天气数据集上的受控比较显示，QLIF-CAST在MSE和MAE上分别降低了15.4%和4.4%，证明量子神经动态在预测误差上优于经典等效模型。其次，在空气质量与风速基准上与最先进的量子LSTM（QLSTM）和量子神经网络（QNN）模型的跨领域比较显示，QLIF-CAST在训练时间内最多减少了94%，在速度-误差权衡空间中占据独特位置。在IBM Marrakesh（156量子比特QPU）上的硬件验证确认了电路执行的可靠性，仅存在1.2%的平均偏差。

英文摘要：

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 R_x 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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。