Prediction of the activity concentrations of Th-232, U-238 and K-40 in geological materials using radial basis function neural network

In this paper, three individual models and one generalized radial basis function neural network (RBFNN) model were developed for the prediction of the activity concentrations of primordial radionuclides, namely, Th-232, U-238 and K-40. To achieve this, gamma spectrometry measurements of 126 different geological materials were used in the development of the RBFNN models. The results indicated that individual and generalized RBFNN models are quite efficient in predicting the activity concentrations of Th-232, U-238 and K-40 of geological materials