Prominent advances in the field of artificial intelligence during the past decade and the breakthrough of deep learning would be useful for investigating ionospheric weather using ground and space-based ionospheric sensors data. The significance of deep learning algorithms needs to be assessed in forecasting the low latitude ionospheric disturbances (delays) for the global positioning system (GPS) signals. Total electron content (TEC) data sets prepared by taking advantage of GPS satellite radio frequency (RF) signals. This letter provides the application of deep learning models, long short-term memory (LSTM), gated recurrent unit (GRU), and a hybrid model that consists of LSTM combined with convolution neural network (CNN) to forecast the ionospheric delays for GPS signals. The deep learning models implemented using the vertical TEC (VTEC) time-series data estimated from GPS measurements over Bengaluru, Guntur, and Lucknow GPS stations. The LSTM-CNN model performs well when compared to other ionospheric deep learning forecasting algorithms with minimum root-mean-square error (RMSE) of 1.5 TEC units (TECUs) and a high degree of R² = 0.99.

This letter proposes the implementation of ionospheric forecasting model based on the long short-term memory (LSTM) networks. Ionospheric region produces time delay for radio wave propagation of global positioning system (GPS) satellites. The ionospheric delays for GPS signals degrade the position accuracy in the measurements for precise navigation and positioning services. Utilizing the emerging artificial intelligence mathematical tools to forecast ionospheric disturbances using GPS-estimated total electron content (TEC) observations is decisive. In this letter, multi-input LSTM forecasting technique is investigated and tested for evaluating its capability in forecasting the ionospheric delays over Bengaluru station (16.26° N, 80.44° E) using eight years (2009-2016) of GPS measured vertical TEC (VTEC) time-series data. The assessment of the LSTM model performance during geomagnetic quiet and disturbed conditions is carried out in comparison with artificial neural networks model and International Reference Ionosphere (IRI-2016) model based on statistical parameters like root-mean-square error and coefficient of determination ($R²)$. The experimental analysis delineates that the proposed LSTM model has provided the correlation of 0.99 with the GPS-measured VTEC and with a forecasting error of 1-2 TEC units.

Scintillation due to ionospheric plasma irregularities remains a challenging task for the space science community as it can severely threaten the dynamic systems relying on space-based navigation services. In the present paper, we probe the ionospheric current and plasma irregularity characteristics from a latitudinal arrangement of magnetometers and Global Navigation Satellite System (GNSS) stations from the equator to the far low latitude location over the Indian longitudes, during the severe space weather events of 6–10 September 2017 that are associated with the strongest and consecutive solar flares in the 24th solar cycle. The night-time influence of partial ring current signatures in ASYH and the daytime influence of the disturbances in the ionospheric E region electric currents (D_iono) are highlighted during the event. The total electron content (TEC) from the latitudinal GNSS observables indicate a perturbed equatorial ionization anomaly (EIA) condition on 7 September, due to a sequence of M-class solar flares and associated prompt penetration electric fields (PPEFs), whereas the suppressed EIA on 8 September with an inverted equatorial electrojet (EEJ) suggests the driving disturbance dynamo electric current (Ddyn) corresponding to disturbance dynamo electric fields (DDEFs) penetration in the E region and additional contributions from the plausible storm-time compositional changes (O/N2) in the F-region. The concurrent analysis of the D_iono and EEJ strengths help in identifying the pre-reversal effect (PRE) condition to seed the development of equatorial plasma bubbles (EPBs) during the local evening sector on the storm day. The severity of ionospheric irregularities at different latitudes is revealed from the occurrence rate of the rate of change of TEC index (ROTI) variations. Further, the investigations of the hourly maximum absolute error (MAE) and root mean square error (RMSE) of ROTI from the reference quiet days’ levels and the timestamps of ROTI peak magnitudes substantiate the severity, latitudinal time lag in the peak of irregularity, and poleward expansion of EPBs and associated scintillations. The key findings from this study strengthen the understanding of evolution and the drifting characteristics of plasma irregularities over the Indian low latitudes.

Several countries have been developing satellite-based augmentation systems (SBAS) for improving positional accuracy of global positioning system (GPS). India is also developing one such system popularly known as GPS aided geo augmented navigation (GAGAN) system. Modelling of ionospheric effects is one of the major challenges in developing precise and reliable GAGAN. The high values of total electron content (TEC), the large diurnal and seasonal variability and intense irregularities present in the low-latitude ionosphere, lead to unacceptable positional errors in GAGAN service region. Todd Walter et al. of Stanford University, USA have made significant contribution in the area of SBAS ionospheric grid modelling by developing the popularly known planar fit model. It is reported by Walter et al. (2000) that a constant decorrelation value of 35 cm was proposed over the wide area augmentation system (WAAS) service region. To provide accurate estimation of ionospheric delays at user ionospheric pierce points (IPP) during a storm or intense irregularities, an irregularity detector and a decorrelation adaptor are incorporated in the modelling. As planar fit model is not adequate to model intense irregularities of Indian ionosphere, a modified planar fit model is applied for GAGAN data on similar lines as was done for WAAS and the results are encouraging.