Neural network analysis of Rutherford backscattering data

A neural network algorithm dedicated to recognition of Rutherford backscatt ering (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 bo th Ge amount and depth of less than 3% could be reached on generated spectr a. We then applied the trained neural network to real experimental data, wi th excellent results. After the initial training phase, the time required f or the recognition of each spectrum is practically instantaneous, opening t he doors to on-line automated data analysis and optimisation of the experim ental conditions. (C) 2000 Elsevier Science B.V. All rights reserved.