Estimation of fusion-evaporation cross sections by artificial neural networks

Abstract

Accurate determination of fusion-evaporation reaction cross section is important in experimental nuclear physics studies. In this study, by using artificial neural network (ANN) method, we have estimated the cross section values for different reactions. The related root mean square errors have been obtained as 18.5 and 110.4mb for training and test data which correspond to 1.8% and 10.5% deviations from the experimental values, respectively.This order of deviations is lower than the cross section value from most common theoretical calculations. The results of this study indicate that ANN method is capable for the estimation of cross section values of fusion-evaporation reactions.