Artificial neural network analysis of RBS and ERDA spectra of multilayered multielemental samples

We have developed artificial neural networks (ANNs) for simultaneous analysis of Rutherford backscattering spectrometry and elastic recoil detection analysis data. The ANNs developed were applied to a highly complex problem, namely the analysis of multilayered silica–titania films doped with Ag and Er, where 11 parameters are required to describe the samples. Extensive optimization of network architecture, connectivity and pre-processing is presented. The optimized ANN was applied to experimental data leading to accurate results.