Technical Article

An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting

¹ Istituto Nazionale di Geofisica e Vulcanologia, Via di Vigna Murata 605, 00143 Rome, Italy
² Sapienza Università di Roma, Piazzale Aldo Moro 5, 00185 Rome, Italy
³ Observatori de l’Ebre, University Ramon Llull – CSIC, Ctra. de l'Observatori 3, 43520 Roquetes, Tarragona, Spain
⁴ University of Massachusetts Lowell, 220 Pawtucket St, Lowell, 01854 MA, USA
⁵ HUN-REN Institute of Earth Physics and Space Science, Csatkai E. u. 6-8., 9400 Sopron, Hungary
⁶ Royal Meteorological Institute of Belgium, Solar Terrestrial Centre of Excellence, Av. Circulaire 3, BE-1180 Brussels, Belgium
⁷ National Observatory of Athens, IAASARS, Vas. Pavlou & I. Metaxa, GR-15 236 Penteli, Greece

^* Corresponding author: vincenzo.ventriglia@ingv.it; vincenzo.ventriglia@outlook.com

Received: 27 August 2024
Accepted: 7 May 2025

Abstract

Large-Scale Travelling Ionospheric Disturbances (LSTIDs) are wave-like ionospheric fluctuations, generally triggered by geomagnetic storms, which play a critical role in space weather dynamics. In this work, we present a machine learning model able to forecast the occurrence of LSTIDs over the European continent up to three hours in advance. The model is based on CatBoost, a gradient boosting framework. It is trained on a human-validated LSTID catalogue with the various physical drivers, including ionogram information, geomagnetic, and solar activity indices. There are three forecasting modes depending on the demanded scenarios with varying relative costs of false positives and false negatives. It is crucial to make the model predictions explainable, so that the output contribution of each physical factor input is visualised through the game-theoretic SHapley Additive exPlanation (SHAP) formalism. The validation procedure consists of a global-level evaluation and interpretation step, firstly, followed by an event-level validation against independent detection methods, which highlights the model’s predictive robustness and suggests its potential for real-time space weather forecasting. Depending on the operating mode, we report an improvement ranging from +72% to +93% over the performance of a rule-based benchmark. Our study concludes with a comprehensive analysis of future research directions and actions to be taken towards full operability. We discuss probabilistic forecasting approaches from a cost-sensitive learning perspective, along with performance-centric model monitoring. Finally, through the lens of the conformal prediction framework, we further comment on the uncertainty quantification for end-user risk management and mitigation.