X
Advance Search
  • Bingkun Yu, Penghao Tian, Xianghui Xue, Christopher J. Scott, Hailun Ye, Jianfei Wu, Wen Yi, Tingdi Chen, Xiankang Dou. 2024: Comparative Analysis of Empirical and Deep Learning Models for Ionospheric Sporadic E layer Prediction. Earth and Planetary Physics. DOI: 10.26464/epp2024048
    Citation: Bingkun Yu, Penghao Tian, Xianghui Xue, Christopher J. Scott, Hailun Ye, Jianfei Wu, Wen Yi, Tingdi Chen, Xiankang Dou. 2024: Comparative Analysis of Empirical and Deep Learning Models for Ionospheric Sporadic E layer Prediction. Earth and Planetary Physics. DOI: 10.26464/epp2024048
Open Access    

Comparative Analysis of Empirical and Deep Learning Models for Ionospheric Sporadic E layer Prediction

  • The ionospheric sporadic E (Es) layers, characterized by intense plasma irregularities in the E region at altitudes of 90–130 km, significantly influence radio communications and navigation systems. Therefore, accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite systems. In this study, we present the model predictions of an empirical model and a deep learning model. The empirical and deep learning model predictions are compared with the satellite RO measurements and the ground-based ionsonde observations. The deep learning model exhibits better performance, as indicated by a higher correlation coefficient (r = 0.87) between RO observations and predictions, compared to the empirical model (r = 0.53). The study offers a comprehensive analysis of empirical and deep learning models for the Es layer prediction, highlighting the importance of integrating artificial intelligence technology into ionosphere modelling.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return