**Abstract**

Monitoring and prediction of space weather phenomena and associated effects requires an understanding of the ionospheric response related to ionospheric electron content and electron density redistribution. These ionospheric response effects to space weather over time have been quantified by ground station measurements (ionosondes, radars, and GPS), satellite and rocket measurements, and estimations from ionospheric models. However, the progressive development of ionospheric models has had inconsistences in trying to describe the redistribution of electron density in response to extreme space weather conditions. In this chapter, we review and discuss the recent developments, progress, improvements, and existing challenges in the developed ionospheric models for prediction and forecasting space weather events and the need for continuous validation. The utilization of deep learning and neural network techniques in developing more flexible, reliable, and accurate data-driven ionospheric models for space weather prediction is also discussed. We also emphasized the roles of International and national Organizations like COSPAR, URSI, ITU, CCIR, and other research and education institutions in supporting and maintaining observatories for real-time monitoring and measurements of ionospheric electron density and TEC.

**Keywords:** IRI, ionospheric electron density, TEC, ionospheric storms, space weather, equatorial regions, neural networks
