AdaBoost-powered multi-class classification of pre-earthquake ionospheric anomalies using GNSS network in Türkiye: A comparison with random forest
Yazarlar (3)
Doç. Dr. Seçil KARATAY Kastamonu Üniversitesi, Türkiye
Zeynep Mantaroğlu
Kastamonu Üniversitesi, Türkiye
Kastamonu Üniversitesi, Türkiye
Esra Nur Şerbetli
Kastamonu Üniversitesi, Türkiye
Kastamonu Üniversitesi, Türkiye
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Earth Science Informatics (Q2) | ||
| Dergi ISSN | 1865-0473 Wos Dergi Scopus Dergi | ||
| Dergi Tarandığı Indeksler | SCI-Expanded | ||
| Makale Dili | Türkçe | Basım Tarihi | 04-2026 |
| Cilt / Sayı / Sayfa | 19 / 5 / 1–31 | DOI | 10.1007/s12145-026-02109-7 |
| Makale Linki | https://doi.org/10.1007/s12145-026-02109-7 | ||
| UAK Araştırma Alanları |
Makine Öğrenmesi
İşaret İşleme
|
||
| Özet |
| This study presents a novel Machine Learning framework for detecting pre-earthquake ionospheric anomalies using the Adaptive Boosting (AdaBoost) ensemble algorithm, applied to high-resolution Total Electron Content (TEC) data derived from Türkiye’s dense TNPGN-Active GNSS network. Within the Lithosphere-Atmosphere-Ionosphere Coupling (LAIC) paradigm, we address key challenges in earthquake precursor research by implementing a three-class classification scheme to distinguish genuine seismo-ionospheric disturbances (Class-2: three days preceding earthquakes) from baseline variability under geomagnetically quiet (Class-0) and disturbed (Class-1) conditions, while incorporating geomagnetic indices (Kp, Ap, Dst) to filter space weather effects. IONOLAB-TEC estimates are analyzed for three M ≥ 6.0 earthquakes in Türkiye: Elazığ (Mw 6.7, 24 January 2020), İzmir (Mw 7.0, 30 October 2020 … |
| Anahtar Kelimeler |
| AdaBoost ensemble | Geomagnetic activity filtering | GNSS | Machine Learning | Remote sensing | Seismo-ionospheric precursors | Total Electron Content (TEC) |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Scopus | 1 |