# Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning

arXiv: https://arxiv.org/abs/2604.18379 · HTML: https://mlsanity.com/paper/2604.18379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 54 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https://mlsanity.com/paper/2104.07788/) (2021)
- [LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/2306.08259/) (2023)
- [Dynamic Graph Representation Learning with Neural Networks: A Survey](https://mlsanity.com/paper/2304.05729/) (2023)
- [TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2510.07586/) (2025)
- [IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics](https://mlsanity.com/paper/2511.15004/) (2025)
- [Global 4D Ionospheric STEC Prediction based on DeepONet for GNSS Rays](https://mlsanity.com/paper/2404.15284/) (2024)

## Abstract (arXiv)

Most data-driven ionospheric models operate on gridded products, which do not preserve the time-varying sampling structure of satellite-based sensing. We instead model the ionosphere as a dynamic graph over ionospheric pierce points, with connectivity that evolves as satellite positions change. Because satellite trajectories are predictable, the graph topology over the forecast horizon can be constructed in advance. We exploit this property to condition forecasts on the future graph structure, which we term ephemeris conditioning. This enables prediction on lines of sight (LoS) that appear only in the forecast horizon. We evaluate our framework on Global Navigation Satellite System data from a co-located receiver pair in Singapore spanning 2023 to 2025. The task is forecasting irregularities defined by the Rate of TEC Index (ROTI) up to 2 hours ahead as per-node binary classification. The resulting model, IonoDGNN, achieves a Brier Skill Score (BSS) of 0.55 and an area under the precision-recall curve (PR-AUC) of 0.77. These correspond to improvements over persistence of 53% in BSS and 58% in PR-AUC, with larger gains at longer lead times. Ablations confirm that graph structure and ephemeris conditioning each contribute meaningfully. Under simulated coverage dropout, the model retains predictive skill on affected nodes through spatial message passing from observed neighbors. Compared to interpolation baselines, the proposed model achieves better recovery, especially at higher dropout levels. These results suggest that dynamic graph forecasting on evolving LoS is a viable alternative for ionospheric modeling. The project and the dataset are available at https://github.com/Mert-chan/IonoDGNN.