Seasonal and Quantum-inspired Models for Neutron Monitor Time Series Forecasting

The paper presents a reproducible forecasting study for the Lomnicky Stit neutron monitor time series, a geophysical neutron-monitoring dataset. Its evaluation covers Seasonal Naive, LSTM, TCN, N-BEATS, Kolmogorov-Arnold Networks, and the quantum-inspired QiLSTM and Qi architectures. The focus is on comparing these approaches for multi-horizon neutron monitor time series prediction.