Belehaki, Anna
Preferred name
Belehaki, Anna
ORCID
2 results
Settings
The search returned 2 results
Now showing 1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , An explainable Machine Learning model for Large-Scale Travelling Ionospheric Disturbances forecasting
(Les Ulis : EDP sciences, 2011-, 2025-05-07); ; ; ; 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.7 19 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Restricted , Oblique-incidence ionospheric soundings over Central Europe and their application for testing now casting and long term prediction models
(2009-06-02); ; ; ; After a first oblique-incidence ionospheric sounding campaign over Central Europe performed during the period 2003–2004 over the radio links between Inskip (UK, 53.5°N, 2.5°W) and Rome (Italy, 41.8°N, 12.5°E) and between Inskip and Chania (Crete, 35.7°N, 24.0°E), new and more extensive analysis of systematic MUF measurements from January 2005 to December 2006 have been performed. MUF measurements collected during moderately disturbed days (17 ≤ Ap ≤ 32), disturbed days (32 < Ap ≤ 50) and very disturbed days (Ap > 50), have been used to test the long term prediction models (ASAPS, ICEPAC and SIRM&LKW), and the now casting models (SIRMUP&LKW and ISWIRM&LKW). The performances of the different prediction methods in terms of r.m.s are shown for selected range of geomagnetic activity and for each season.634 35
