Dynamic graph model with ephemeris conditioning forecasts ionospheric irregularities on GNSS lines of sight, achieving BSS 0.49 and PR-AUC 0.75 while outperforming persistence by 35% and 52%.
Pytorch geometric temporal: Spatiotemporal signal processing with neural machine learning models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning
Dynamic graph model with ephemeris conditioning forecasts ionospheric irregularities on GNSS lines of sight, achieving BSS 0.49 and PR-AUC 0.75 while outperforming persistence by 35% and 52%.