Analysis of sapphire implanted with different elements using artificial neural networks

Five elements (Ti, Fe, Co, Er and An) were implanted in sapphire to fluences between 8 x 10(13) and 5 x 10(17) at/cm(2), and energies between 200 and 800 keV. We used Rutherford backscattering to determine the dose and depth of the implanted elements. The data analysis is performed using an artificial neural network (ANN). Here we report a generalisation of previous works where ANNs were successfully applied for specific implantations such as Er in sapphire and Ge in Si. We have now developed a code that it is able to analyse data from implantations of any element with Z between 18 and 83 into sapphire. Although this problem is considerably more complex than single-system ANNs, the ANN developed produced excellent results when applied to experimental data. We discuss the reliability of the ANN and its applicability to the analysis of large batches of implanted samples. (C) 2002 Elsevier Science B.V. All rights reserved.