Estimation of Lateral Distribution of High Energy Showers using Artificial Neural Networks

The lateral distribution function (LDF) of extensive air shower (EAS)s play an important role in the analysis of the shower events and the particle content in it. These studies involve a collection of experimental works which at times turns out to be tedious. In many situations, while studying EAS, reconstruction of its constituents become important usually carried out using certain traditional approaches. Artificial Neural Network (ANN) can be used in these cases because of the fact that these are non-parametric tools with the ability to learn from the environment and use the knowledge for subsequent stages. Here, we propose a system based on ANN which is configured to accept high energy EAS shower sizes as an input parameter and provide the lateral distributions of the electronic component of the shower upto certain distance. A feedforward ANN is trained for the purpose which acts as a reliable system for estimating LDF for a range of shower events between 1019.5 to 1020.5 eV of primary energy.