Abstract
In this paper the results of an attempt to model the auroral daytime lower ionosphere using the procedure of Neural Networks(NNs) are presented. Data from the European Incoherent Scatter facility (EISCAT) combined with rocket borne measurements were used to provide a database of reliable lower ionosphere data for NN modelling. Combinations of various input parameters known to produce a response in the daytime lower ionosphere were investigated as potential contributors to the input space. These parameters consisted of day number, hour, solar activity, riometer absorption, magnetic activity and an indication of the altitude. The output was the electron density for a given set of input parameters. Therefore, an average electron density profile describing the shape and location of the D- and E-regions at high latitudes can be determined for a particular set of inputs. A process of minimisation of mean squared errors was used to optimise the NNs. Predicted profiles are compared with actual data as well as an existing ionospheric model built from the same data. Results show that the NN can predict reasonable average electron density profiles for the high latitude lower ionosphere within the limits of the input space.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
