TriQXNet: Forecasting Dst Index from Photo voltaic Wind Knowledge Utilizing an Interpretable Parallel Classical-Quantum Framework with Uncertainty Quantification
Authors: Md Abrar Jahin, M. F. Mridha, Zeyar Aung, Nilanjan Dey, R. Simon Sherratt
Summary: Geomagnetic storms, attributable to photo voltaic wind vitality switch to Earth’s magnetic area, can disrupt essential infrastructure like GPS, satellite tv for pc communications, and energy grids. The disturbance storm-time (Dst) index measures storm depth. Regardless of developments in empirical, physics-based, and machine-learning fashions utilizing real-time photo voltaic wind knowledge, precisely forecasting excessive geomagnetic occasions stays difficult resulting from noise and sensor failures. This analysis introduces TriQXNet, a novel hybrid classical-quantum neural community for Dst forecasting. Our mannequin integrates classical and quantum computing, conformal prediction, and explainable AI (XAI) inside a hybrid structure. To make sure high-quality enter knowledge, we developed a complete preprocessing pipeline that included function choice, normalization, aggregation, and imputation. TriQXNet processes preprocessed photo voltaic wind knowledge from NASA’s ACE and NOAA’s DSCOVR satellites, predicting the Dst index for the present hour and the subsequent, offering important advance discover to mitigate geomagnetic storm impacts. TriQXNet outperforms 13 state-of-the-art hybrid deep-learning fashions, reaching a root imply squared error of 9.27 nanoteslas (nT). Rigorous analysis by means of 10-fold cross-validated paired t-tests confirmed its superior efficiency with 95% confidence. Conformal prediction methods present quantifiable uncertainty, which is crucial for operational selections, whereas XAI strategies like ShapTime improve interpretability. Comparative evaluation reveals TriQXNet’s superior forecasting accuracy, setting a brand new degree of expectations for geomagnetic storm prediction and highlighting the potential of classical-quantum hybrid fashions in area climate forecastin
