Spatiotemporally Invariant Ionospheric Feature Learning For Cross-Regional Earthquake Prediction

Earthquake prediction remains one of the central unsolved problems in geophysics, and ionospheric variability offers a promising yet debated window into the earthquake preparation process through lithosphere–atmosphere–ionosphere coupling. Progress has been hindered by methodological limitations in prior studies, including the use of inappropriate performance metrics for highly imbalanced seismic data, the reliance on geographically and temporally narrow data, and inclusion of inherent spatial or temporal features that artificially inflate model performance while preventing the discovery of genuine ionospheric precursors. To address these challenges, we introduce a global, temporally validated machine learning framework grounded in thirty-five years of ionospheric observations from thirty-seven stations with hundreds of thousands of seismic events. Our framework eliminates lookahead bias through strict temporal partitioning, evaluates precursor sensitivity through systematic relaxation of the Dobrovolsky radius, and applies ensemble-based feature vetting that excludes spatial and temporal identifiers to prevent leakage and coincidence effects. Extensive cross-regional benchmarking shows that gradient boosting models yield the strongest classification skill, with a weighted F1 score of 77%, and that ionospheric parameters account for a substantial portion of earthquake magnitude variability. These findings provide quantitative support for LAIC processes while revealing the multivariate nature of seismic precursors. Our study confirms the existence of learnable, spatiotemporally invariant ionospheric precursors.