Predicting low-latitude ionospheric Total Electron Content (TEC) over the Indian sector under variable space weather conditions using solar wind parameters
Abstract
Accurate prediction of ionospheric Total Electron Content (TEC) during geomagnetically disturbed conditions remains challenging, particularly when empirical models perform poorly during storms and neural network (NN) approaches rely explicitly on geomagnetic indices such as Kp/Ap or Dst/SYM-H. In this study, we develop an NN-based model to predict TEC variations over the Indian longitude sector without incorporating geomagnetic indices as inputs. The model is trained on the full-year (2024) Global Ionospheric Map (GIM) TEC dataset at a 15-minute cadence, together with solar wind parameters: Interplanetary Magnetic Field (IMF) Bz, velocity (Vsw), and density (Np), along with the F10.7 cm solar radio flux. Seasonal and diurnal variability are represented using sinusoidal transformations of Day of Year (DOY) and hour of day (HOD). An optimized architecture with 96 hidden neurons yields strong training performance (R2 ∼ 0.96, RMSE ∼ 5.4, and MAE ∼ 3.8 TECU). Independent predictions for the year 2025 demonstrate robust generalization under both quiet and geomagnetically active conditions. Quiet-time residuals are generally confined within ±10 TECU, while during moderate and strong storm-time conditions, the model maintains comparable error bounds across most of the Indian region, despite not being trained on geomagnetic indices. The results indicate that solar wind parameters, combined with the F10.7 solar flux and cyclical temporal encoding, contain sufficient information to reproduce geomagnetic storm-time TEC variability. This study therefore demonstrates the applicability of the proposed approach for regional TEC prediction and ionospheric nowcasting, with potential applications in GNSS positioning, satellite navigation, radio communication systems, and the future development of operational ionospheric forecasting tools.
Versions
Related
- Modeling of the variability of D-region ionospheric electron density during solar cycle-24
- The ionised interstellar medium of DSFGs revealed by JWST/NIRSpec and ALMA: Super-solar metallicity, low ionisation parameters, and typical electron densities
- On the altitude profile of lower ionospheric D-region response time delay during solar flares
- Temporal Correlation between Ionospheric Storm-Enhanced Density Plume and Plasmaspheric Plume Occurrence
- An autonomous approach to model daytime behavior of sub-ionospheric VLF signals over short and medium propagation paths in India
BibTeX
@misc{chakraborty2026predicting,
title = {{Predicting low-latitude ionospheric Total Electron Content (TEC) over the Indian sector under variable space weather conditions using solar wind parameters}},
author = {Sumanjit Chakraborty and Gopi K. Seemala and A. P. Dimri},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23732},
eprint = {2609.23732},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23732},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Predicting low-latitude ionospheric Total Electron Content (TEC) over the Indian sector under variable space weather conditions using solar wind parameters
AU - Sumanjit Chakraborty
AU - Gopi K. Seemala
AU - A. P. Dimri
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23732
UR - https://arxiv.org/abs/2609.23732
AB - Accurate prediction of ionospheric Total Electron Content (TEC) during geomagnetically disturbed conditions remains challenging, particularly when empirical models perform poorly during storms and neural network (NN) approaches rely explicitly on geomagnetic indices such as Kp/Ap or Dst/SYM-H. In this study, we develop an NN-based model to predict TEC variations over the Indian longitude sector without incorporating geomagnetic indices as inputs. The model is trained on the full-year (2024) Global Ionospheric Map (GIM) TEC dataset at a 15-minute cadence, together with solar wind parameters: Interplanetary Magnetic Field (IMF) B_z, velocity (V_sw), and density (N_p), along with the F10.7 cm solar radio flux. Seasonal and diurnal variability are represented using sinusoidal transformations of Day of Year (DOY) and hour of day (HOD). An optimized architecture with 96 hidden neurons yields strong training performance (R^2 ∼ 0.96, RMSE ∼ 5.4, and MAE ∼ 3.8 TECU). Independent predictions for the year 2025 demonstrate robust generalization under both quiet and geomagnetically active conditions. Quiet-time residuals are generally confined within ±10 TECU, while during moderate and strong storm-time conditions, the model maintains comparable error bounds across most of the Indian region, despite not being trained on geomagnetic indices. The results indicate that solar wind parameters, combined with the F10.7 solar flux and cyclical temporal encoding, contain sufficient information to reproduce geomagnetic storm-time TEC variability. This study therefore demonstrates the applicability of the proposed approach for regional TEC prediction and ionospheric nowcasting, with potential applications in GNSS positioning, satellite navigation, radio communication systems, and the future development of operational ionospheric forecasting tools.
ER -