Artificial neural network analysis of multiple IBA spectra

We have previously developed artificial neural networks (ANN) dedicated to the analysis of RBS spectra. One of the limitations of the ANNs so far developed was that one single spectrum could be analysed from each sample. When more than one spectrum is collected, each had to be analysed separately, leading to different results and hence reduced accuracy. Here we develop an ANN that can analyse multiple Rutherford backscattering and elastic recoil detection analysis spectra collected from the same sample. The ANN is applied to a simple case, namely the composition of TiNOH films. We report on the optimisation of the network architecture and training. We show that the information present in the different spectra can be integrated to produce a highly accurate final result.