Neural network analysis of Rutherford backscattering data

A neural network algorithm dedicated to recognition of Rutherford backscattering (RBS) data was developed. The algorithm was applied to one important particular case, namely the determination of the amount of Ge implanted in Si samples and the depth at which the Ge is located. An average error on both Ge amount and depth of less than 3% could be reached on generated spectra. We then applied the trained neural network to real experimental data, with excellent results. After the initial training phase, the time required for the recognition of each spectrum is practically instantaneous, opening the doors to on-line automated data analysis and optimisation of the experimental conditions. (C) 2000 Elsevier Science B.V. All rights reserved.