← Back to all news
arXiv Machine Learning By Krishna Bhatia, Shalini Devendrababu, Srinjoy Ganguly

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

Read the original on arXiv Machine Learning →

The paper presents a reproducible study of multi‑horizon forecasting on the Lomnicky Stit neutron monitor (LMKS) time series. It evaluates a range of models—from simple seasonal baselines to modern deep sequence models and quantum‑inspired architectures such as QiLSTM and QiKAN—using MAE and RMSE metrics. Results show that the quantum‑inspired KAN variant (QiKAN) achieves the lowest aggregate error, while the simple Seasonal Naive baseline remains highly competitive, indicating that strong seasonal or low‑dimensional functional priors can rival more complex models for highly periodic scientific data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 18

Recursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature Forecasting

The paper introduces a recursive quantum long short-term memory (QLSTM) architecture and compares it to a standard QLSTM for one-step-ahead daily temperature forecasting. Using Toronto weather data and identical training settings, the recursive model consistently reaches near-optimal test loss earlier, achieves lower mean absolute error and root mean squared error, and shows a smaller generalization gap across input windows of 8, 16, and 32 days over 20 random seeds. These findings suggest that recursive quantum feature transformations can enhance stability and out-of-sample performance in compact hybrid quantum–classical temporal models.

By Mu-En Lee, Yen-Ku Liu, Samuel Yen-Chi Chen, Yun-Cheng Tsai
More like this →
arXiv AI
Jun 16

Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

arXiv:2605. 06734v2 Announce Type: replace-cross Abstract: Fast Weight Programmers (FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states.

By Kuo-Chung Peng, Samuel Yen-Chi Chen, Jiun-Cheng Jiang, Chen-Yu Liu, En-Jui Kuo, Yun-Yuan Wang, Prayag Tiwari, Andrea Ceschini, Chi-Sheng Chen, Yu-Chao Hsu, Chun-Hua Lin, Tai-Yue Li, Antonello Rosato, Massimo Panella, Simon See, Saif Al-Kuwari, Kuan-Cheng Chen, Nan-Yow Chen, Hsi-Sheng Goan
reinforcement-learningbenchmarks
More like this →
arXiv AI
Jul 7

KAN vs LSTM Performance in Time Series Forecasting

arXiv:2511. 18613v2 Announce Type: replace-cross Abstract: This study presents a controlled comparison of baseline Kolmogorov-Arnold Networks (KAN), implemented via PyKAN, and Long Short-Term Memory (LSTM) networks for the forecasting of stochastic, non-stationary financial time series.

By Tabish Ali Rather, S M Mahmudul Hasan Joy, Nadezda Sukhorukova, Federico Frascoli
benchmarkssafety
More like this →