t-STEP: An interpretable model for Total Electron Content predictions and irregularities estimations

2026-06-28

AI Summary

Existing ionospheric total electron content (TEC) models struggle to simultaneously satisfy physical constraints and achieve high temporal resolution, limiting their ability to effectively capture small-scale irregularities. This work proposes the t-STEP model, which enables 30-second high-resolution TEC forecasting within a unified framework and directly estimates irregularity indices such as ROT and ROTI without requiring separate models tailored to specific transient events. By integrating GPS observations and employing interpretable SHAP analysis alongside dynamic time warping evaluation, t-STEP significantly outperforms IRI-2020 and attention-based LSTM models. During the high solar activity period of 2015, it achieves a prediction accuracy of 91% (MAE = 4.38 TECU), with 35% higher hourly accuracy, 57% lower error, and a 54% improvement in skill score, while more accurately characterizing irregular structures during geomagnetic storms.

Abstract

Earth system infrastructures relying on satellite-based technologies, such as Global Positioning System (GPS) communications, are affected by ionospheric Total Electron Content (TEC) gradients. Modeling these gradients under physical constraints remains challenging due to their dynamic and transient nature. While existing machine learning (ML) models can predict hourly TEC variations, it remains unclear whether their temporal resolution is sufficient to preserve small-scale TEC irregularities within predicted signals. To address this gap, we introduce an interpretable ML-based model, t-STEP, designed to predict TEC at a 30-second resolution and estimate irregularity signatures from the modeled signals. This high cadence enables the derivation of Rate of TEC changes (ROT) and the ROT Index (ROTI) as diagnostic indicators of ionospheric variability. The model is developed using GPS observations from solar cycle 24 at a station located at 5.49°S, 47.49°W. A multi-metric evaluation framework, including dynamic time warping, is used for robustness assessment, while SHAP (SHapley Additive exPlanations) provides insight into feature contributions. The 30-second TEC predictions achieve 91% accuracy with a mean absolute error (MAE) of 4.38 TECU during high solar activity (2015). Compared with the International Reference Ionosphere (IRI-2020), the hourly model improves accuracy by 35%, reduces absolute errors by 57%, and increases prediction skill by 54%. More importantly, the 30-second model captures TEC irregularity dynamics and morphologies during geomagnetic storms of different intensities, outperforming an attention-based Long Short-Term Memory model under the same experimental conditions. This study demonstrates the potential of a single TEC prediction framework for scalable irregularity monitoring without requiring separate models for individual transient events.

Problem

• Total Electron Content
• ionospheric irregularities
• temporal resolution
• TEC gradients
• space weather

Innovation

• high-temporal-resolution TEC prediction
• ionospheric irregularity estimation
• interpretable machine learning
• ROT/ROTI diagnostics
• single-model scalable monitoring