Analysis of 7Be behaviour in the air by using a multilayer perceptron neural network

Abstract

A multilayer perceptron artificial neural network (ANN) model for the prediction of the Be-7 behaviour in the air as the function of meteorological parameters was developed. The model was optimized and tested using Be-7 activity concentrations obtained by standard gamma-ray spectrometric analysis of air samples collected in Belgrade (Serbia) during 2009-2011 and meteorological data for the same period. Good correlation (r = 0.91) between experimental values of Be-7 activity concentrations and those predicted by ANN was obtained. The good performance of the model in prediction of Be-7 activity concentrations could provide basis for construction of models which would forecast behaviour of other airborne radionuclides. (C) 2014 Elsevier Ltd. All rights reserved.