Electric Potential Patterns Forecasting in the Southern Hemisphere with Deep Learning Techniques

2026-09-25

AI Summary

This study addresses the challenge of real-time, accurate prediction of the spatial structure of the high-latitude ionosphere in the Southern Hemisphere by introducing conditional probabilistic diffusion models into full-spatial-structure forecasting for the first time. Methodologically, a U-Net-based architecture is employed to integrate multi-source data from SuperDARN radars and L1 solar wind observations, with systematic comparisons conducted between deterministic baselines and diffusion models regarding long-term forecasting performance. The results demonstrate that this probabilistic generative framework significantly outperforms conventional deterministic approaches in extended-horizon predictions and highly dynamic scenarios, such as severe geomagnetic storms. Consequently, this work establishes a novel paradigm for operational space weather forecasting.

Abstract

Space weather disturbances driven by the solar wind can degrade satellite navigation, disrupt radio communications, and threaten power infrastructure, making accurate forecasting of the high-latitude ionosphere's response a critical operational need. Existing approaches, empirical climatological models and physics-based magnetohydrodynamic simulations, either smooth out the ionosphere's time-dependent, non-linear response or are too computationally expensive for real-time use, while prior machine learning efforts have mostly targeted scalar indices rather than the full spatial structure of ionospheric convection. Here we train and compare three deep learning architectures, a probabilistic diffusion model conditioned on multi-variate solar wind and interplanetary magnetic field measurements at the L1 Lagrange point, an unconditioned diffusion ablation, and a deterministic U-Net baseline, to forecast Southern Hemisphere high-latitude electric potential maps derived from SuperDARN radar observations. Using five years (2020--2025) of SuperDARN data synchronised with DSCOVR L1 measurements, we evaluate the models under a single-pass regime, an extended autoregressive rollout of up to 350 frames, and an out-of-distribution case study on the intense March 2015 St.\ Patrick's Day storm, unseen during training. We find that the relative advantage of the deterministic and probabilistic approaches is not fixed: the deterministic model is competitive over short horizons and calm conditions, while the diffusion model's advantage grows and eventually dominates as the forecast horizon lengthens and the event becomes more dynamic, evidence that probabilistic, sample-based generative models are the more promising direction for operational, long-horizon space weather forecasting.

Problem

• space weather forecasting
• ionospheric electric potential
• high-latitude ionosphere
• solar wind

Innovation

• Diffusion Model
• Space Weather Forecasting
• Electric Potential Patterns
• SuperDARN
• Probabilistic Generative Model