Artificial Neural Networks based global Ionospheric Model (ANNIM)

WHY IN NEWS

Researchers from Indian Institute of Geomagnetism (IIG) have developed a global model to predict the ionospheric electron density with larger data coverage.

ABOUT Artificial Neural Networks based global Ionospheric Model (ANNIM)

• Tracking the variability of the Ionosphere is important for communication and navigation.
• Scientists have tried to model the ionosphere using theoretical and empirical techniques; however, the accurate prediction of electron density is still a challenging task.
• Artificial Neural Networks (ANNs) are showing potential to handle more complex and non-linear problems. Keeping these aspects in mind, a novel machine learning approach was implemented in the ionospheric model development using global ionospheric observations.
• ANNIM uses long-term ionospheric observations to predict the ionospheric electron density and the peak parameters.
• Artificial Neural Networks (ANN) replicate the processes in the human brain (or biological neurons) to solve problems such as pattern recognition, classification, clustering, generalization, linear and nonlinear data fitting, and time series prediction.
• The researchers developed a neural network-based global ionospheric model by using an extensive database consisting of:
  • Nearly two decades of global Digisonde (an instrument that measures real-time on-site electron density of the ionosphere by sending the radiofrequency pulses)
  • Global Navigation Satellite System (GNSS) radio occultation
  • Universal Time, latitude, longitude, zonal and meridional neutral winds etc.

•  The data was trained with the ANNs using high-performance computer at IIG to develop the ANNIM.