Analyzing line scan EELS data with neural pattern recognition

Neural Pattern Recognition was used for extracting chemical state information from electron energy-loss (EEL) spectra. The purpose was to obtain a quantitative composition profile from sets of low-loss and core-loss EEL spectra measured along a line across an amorphous inclusion at a grain boundary in a silicon bicrystal. The spectra were presented serially to the artificial neural network to obtain the number and shape of the spectra, whose linear combinations reproduce each single spectrum. The results indicate the existence of a different chemical environment at the interfaces between inclusion and crystal. The data analysis proved to be fast, robust, relatively immune to noise or artifacts and capable of extracting relevant information from subtle spectral features.