An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting
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 Europ...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | Journal of Space Weather and Space Climate |
| Subjects: | |
| Online Access: | https://www.swsc-journal.org/articles/swsc/full_html/2025/01/swsc240048/swsc240048.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839639363727654912 |
|---|---|
| author | Ventriglia Vincenzo Guerra Marco Cesaroni Claudio Spogli Luca Altadill David Segarra Antoni Galkin Ivan Barta Veronika Verhulst Tobias G.W. de Paula Víctor Navas-Portella Víctor Berényi Kitti A. Belehaki Anna |
| author_facet | Ventriglia Vincenzo Guerra Marco Cesaroni Claudio Spogli Luca Altadill David Segarra Antoni Galkin Ivan Barta Veronika Verhulst Tobias G.W. de Paula Víctor Navas-Portella Víctor Berényi Kitti A. Belehaki Anna |
| author_sort | Ventriglia Vincenzo |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-794c47eed26c4613966d12b51b795b4d |
| institution | Matheson Library |
| issn | 2115-7251 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | Journal of Space Weather and Space Climate |
| spelling | doaj-art-794c47eed26c4613966d12b51b795b4d2025-07-04T09:36:18ZengEDP SciencesJournal of Space Weather and Space Climate2115-72512025-01-01152510.1051/swsc/2025020swsc240048An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecastingVentriglia Vincenzo0https://orcid.org/0009-0008-6017-2118Guerra Marco1https://orcid.org/0000-0001-9993-2366Cesaroni Claudio2https://orcid.org/0000-0003-2268-4389Spogli Luca3https://orcid.org/0000-0003-2310-0306Altadill David4https://orcid.org/0000-0001-7730-385XSegarra Antoni5Galkin Ivan6Barta Veronika7https://orcid.org/0000-0001-9135-5533Verhulst Tobias G.W.8de Paula Víctor9https://orcid.org/0000-0002-5810-9901Navas-Portella Víctor10https://orcid.org/0000-0002-1077-0952Berényi Kitti A.11https://orcid.org/0000-0002-8799-5850Belehaki Anna12https://orcid.org/0000-0002-9270-5387Istituto Nazionale di Geofisica e VulcanologiaIstituto Nazionale di Geofisica e VulcanologiaIstituto Nazionale di Geofisica e VulcanologiaIstituto Nazionale di Geofisica e VulcanologiaObservatori de l’Ebre, University Ramon Llull – CSICObservatori de l’Ebre, University Ramon Llull – CSICUniversity of Massachusetts LowellHUN-REN Institute of Earth Physics and Space ScienceRoyal Meteorological Institute of Belgium, Solar Terrestrial Centre of ExcellenceObservatori de l’Ebre, University Ramon Llull – CSICObservatori de l’Ebre, University Ramon Llull – CSICHUN-REN Institute of Earth Physics and Space ScienceNational Observatory of Athens, IAASARSLarge-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.https://www.swsc-journal.org/articles/swsc/full_html/2025/01/swsc240048/swsc240048.htmllarge scale travelling ionospheric disturbancesionosphereforecastingexplainable artificial intelligencemachine learning |
| spellingShingle | Ventriglia Vincenzo Guerra Marco Cesaroni Claudio Spogli Luca Altadill David Segarra Antoni Galkin Ivan Barta Veronika Verhulst Tobias G.W. de Paula Víctor Navas-Portella Víctor Berényi Kitti A. Belehaki Anna An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting Journal of Space Weather and Space Climate large scale travelling ionospheric disturbances ionosphere forecasting explainable artificial intelligence machine learning |
| title | An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting |
| title_full | An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting |
| title_fullStr | An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting |
| title_full_unstemmed | An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting |
| title_short | An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting |
| title_sort | explainable machine learning model for large scale travelling ionospheric disturbances forecasting |
| topic | large scale travelling ionospheric disturbances ionosphere forecasting explainable artificial intelligence machine learning |
| url | https://www.swsc-journal.org/articles/swsc/full_html/2025/01/swsc240048/swsc240048.html |
| work_keys_str_mv | AT ventrigliavincenzo anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT guerramarco anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT cesaroniclaudio anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT spogliluca anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT altadilldavid anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT segarraantoni anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT galkinivan anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT bartaveronika anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT verhulsttobiasgw anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT depaulavictor anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT navasportellavictor anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT berenyikittia anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT belehakianna anexplainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT ventrigliavincenzo explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT guerramarco explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT cesaroniclaudio explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT spogliluca explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT altadilldavid explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT segarraantoni explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT galkinivan explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT bartaveronika explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT verhulsttobiasgw explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT depaulavictor explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT navasportellavictor explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT berenyikittia explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting AT belehakianna explainablemachinelearningmodelforlargescaletravellingionosphericdisturbancesforecasting |