Comparison of Convolutional and Conventional Artificial Neural Networks for Laser-Induced Breakdown Spectroscopy Quantitative Analysis

The introduction of "deep learning" algorithms for feature identification in digital imaging has paved the way for artificial intelligence applications that up to a decade ago were considered technologically impossible to achieve, from the development of driverless vehicles to the fully automated diagnostics of cancer and other diseases from histological images. The success of deep learning applications has, in turn, attracted the attention of several researchers for the possible use of these methods in chemometrics, applied to the analysis of complex phenomena as, for example, the optical emission of laser-induced plasmas. In this paper, we will discuss the advantages and disadvantages of convolutional neural networks, one of the most diffused deep learning techniques, in laser-induced breakdown spectroscopy (LIBS) applications (classification and quantitative analysis), to understand the real potential of "deep LIBS" in practical everyday use. In particular, the comparison with the results obtained using "shallow" artificial neural networks will be presented and discussed, taking as a case study the analysis of six bronze samples of known composition.