Evaluation of the suitability of neural network method for prediction of uranium activity ratio in environmental alpha spectra

•The suitability of RBF network method for the prediction of 234U/238U activity ratio was evaluated.•The average of 2 consecutive channels of a partial uranium raw spectrum was plotted as the average curve.•The points that their slopes are of the order of 0–1% per 10 channels, were used as inputs to the RBF.•The network was trained by the simulated spectra library, could accurately predict the activity ratio.•The network was trained by the real spectra library, could reasonably predict the activity ratio.

Applying Artificial Neural Network to an alpha spectrometry system is a good idea to discriminate the composition of environmental and non-environmental materials by the estimation of the 234U/238U activity ratio. Because it eliminates limitations of classical approaches by the extraction the desired information from the average of a partial uranium raw spectrum. The network was trained by an alpha spectrum library which was developed in this work. The results indicated that there was a small difference between the target values and the predictions. These results were acceptable, because the thickness of samples and the inferring elements were different in the real library.