Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186034,
        author = {G V Avanija Mahalakshmi and Gottapu Sasibhushana Rao and Bharati Bidikar},
        title = {LSTM-Based Prediction of Ionospheric Total Electron Content in the Indian Equatorial Region},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {3683-3686},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186034},
        abstract = {Global Positioning System (GPS) signals are pivotal for navigation and positioning applications but are adversely influenced by ionospheric dispersive media that result in signal delays and phase shifts. These perturbations correlate directly with the Total Electron Content (TEC) of the ionosphere, which fluctuates dynamically due to solar and geomagnetic activity. Accurate TEC prediction is crucial for mitigating GPS positioning errors, ensuring dependable navigation, and supporting space weather forecasting. This study introduces a data-driven Long Short-Term Memory (LSTM) neural network model developed to predict TEC variations over the Indian equatorial region, leveraging multi-year GNSS data and solar flux indices. Comparative evaluation with conventional machine learning regressors establishes the LSTM model’s superiority in capturing temporal dependencies and nonlinear ionospheric behaviors. The findings affirm the LSTM framework’s proficiency in generating precise, adaptive TEC forecasts essential for enhancing GPS reliability in low-latitude environments characterized by complex ionospheric variability.},
        keywords = {Deep Learning, Equatorial Ionization Anomaly (EIA), GNSS, Ionosphere, LSTM, Machine Learning, Random Forest, Total Electron Content (TEC)},
        month = {October},
        }