Artificial neural network applications in ionospheric studies

L. R. Cander

Abstract


The ionosphere of Earth exhibits considerable spatial changes and has large temporal variability of various timescales related to the mechanisms of creation, decay and transport of space ionospheric plasma. Many techniques for modelling electron density profiles through entire ionosphere have been developed in order to solve the "age-old problem" of ionospheric physics which has not yet been fully solved. A new way to address this problem is by applying artificial intelligence methodologies to current large amounts of solar-terrestrial and ionospheric data. It is the aim of this paper to show by the most recent examples that modern development of numerical models for ionospheric monthly median long-term prediction and daily hourly short-term forecasting may proceed successfully applying the artificial neural networks. The performance of these techniques is illustrated with different artificial neural networks developed to model and predict the temporal and spatial variations of ionospheric critical frequency, f0F2 and Total Electron Content (TEC). Comparisons between results obtained by the proposed approaches and measured f0F2 and TEC data provide prospects for future applications of the artificial neural networks in ionospheric studies.

Keywords


electromagnetic waves;ionospheric modelling;prediction;forecasting;artificial neural networks;time series analysis

Full Text:

PDF

References


DOI: https://doi.org/10.4401/ag-3817
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it (Read more).
Ok


Published by INGV, Istituto Nazionale di Geofisica e Vulcanologia - ISSN: 2037-416X