EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Dual-Channel XGBoost–Transformer–LSTM Fusion Method for GNSS Ionospheric Scintillation Forecasting

Yuanfa Ji, Shifeng Liu, Xiyan Sun, Wenjie Sun, Wenbin Liang, Kamarul Hawari bin Ghazali, Qiang Fu, Yihua Huang

Atmosphere · 23.07.2026 · 17 (8) · 711

DOI: 10.3390/atmos17080711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Atmosphere, online erschienen am 23.07.2026. Verfasst von Yuanfa Ji und 7 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangxi Science and Technology Department, Guangxi University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-latitude ionospheric irregularities cause rapid fluctuations in GNSS signal amplitude and phase, threatening receiver tracking and services. We propose a dual-channel XGBoost–Transformer–LSTM fusion model to address rare events, missed-detection costs, and the difficulty of combining physics-informed and profile-structure information. Data from the HKOH station and geospace products spanning 1 January 2020–21 March 2024 were used. Space-weather variables, temporal factors, previous-day scintillation status, and a TEC120 latitude–UT grid at 06:00–11:00 UT were used to predict GPS L1 amplitude scintillation during 11:00–14:00 UT. The XGBoost channel used the raw TEC grid, first-order latitudinal and hourly TEC differences, and background variables, whereas the Transformer–LSTM channel extracted within-day structure. Channel probabilities were combined by soft voting, with the weight and threshold selected on the validation set. Chronological test results were recall = 0.8788, F1-score = 0.5949, ROC-AUC = 0.8263, PR-AUC = 0.6097, CSI = 0.4234, TSS = 0.4511, and MCC = 0.4096. Fusion raised recall from 0.8030 to 0.8788 but reduced precision from 0.4609 to 0.4496. Paired bootstrap analysis supported a stable improvement only in recall. The model therefore suits warning applications prioritizing detection over minimizing false alarms.

Förderung

  • National Natural Science Foundation of China
  • Guangxi Science and Technology Department
  • Guangxi University
  • Guilin University of Electronic Technology
  • Ministry of Science and Technology of the People's Republic of China

Zitieren

APA

Ji, Y., Liu, S., Sun, X., Sun, W., Liang, W., Ghazali, K. H. B., Fu, Q., & Huang, Y. (2026). A Dual-Channel XGBoost–Transformer–LSTM Fusion Method for GNSS Ionospheric Scintillation Forecasting. Atmosphere, 17(8), 711. https://doi.org/10.3390/atmos17080711

Vancouver

Ji Y, Liu S, Sun X, Sun W, Liang W, Ghazali KHB, et al. A Dual-Channel XGBoost–Transformer–LSTM Fusion Method for GNSS Ionospheric Scintillation Forecasting. Atmosphere. 2026;17(8):711. doi:10.3390/atmos17080711

BibTeX
@article{Ji2026,
  author = {Ji, Yuanfa and Liu, Shifeng and Sun, Xiyan and Sun, Wenjie and Liang, Wenbin and Ghazali, Kamarul Hawari bin and Fu, Qiang and Huang, Yihua},
  title = {A Dual-Channel XGBoost–Transformer–LSTM Fusion Method for GNSS Ionospheric Scintillation Forecasting},
  journal = {Atmosphere},
  year = {2026},
  volume = {17},
  number = {8},
  pages = {711},
  doi = {10.3390/atmos17080711}
}
Kostenlos starten →