AI and the World's Hard Problems · Earth & climate science · arXiv · 2026-10-22
Space weather dependence of decameter-scale ionospheric irregularities spatial distribution
A nowcast and forecast model was built for high-latitude decameter ionospheric irregularities using SuperDARN and SECIRA radar data and space weather parameters. The method relies on self-learning pattern recognition in space weather dynamics, with a neural network inspired by graph neural networks approximating the spatial distribution of irregularities. Trained and tested on data from 11 radars over 2010-2025, the model achieves acceptable forecast quality up to 7-9 hours ahead, with the best performance for the nowcast.