The combination of Laser Induced Breakdown Spectroscopy and artificial neural network for concentration analysis of Ti in soil

Laser-Induced Breakdown Spectroscopy (LIBS) has been proposed for heavy metal analysis in soil with the great potential to perform measurement in real time. Recently, artificial neural network (ANN) has been used in many applications. Its classification and prediction capabilities are especially useful for spectral analysis. In this article, a back-propagation (BP) algorithm with adaptive learning rate and momentum coefficient was used and served as a calibration strategy for LIBS. The concentration of Ti in soil samples was predicted using the combination method of LIBS and an ANN. The quantitative results and relative standard deviation (RSD) of 30 times repeated predictions were derived. The RSD was less than 5.24%. And the relative error was less than 9.58%. Quantitative results were compared with those obtained by conventional calibration curve method. The presented results demonstrate that the combination method of LIBS with ANN performs better than conventional calibration curve method in quantitative detection of Ti in soil with improved accuracy and measurement precision in terms of relative standard deviation.