Comparison Of Multivariate and Pre-Processing Methods for Quantitative Laser-Induced Breakdown Spectroscopy of Geologic Samples

Comparison Of Multivariate and Pre-Processing Methods for Quantitative Laser-Induced Breakdown Spectroscopy of Geologic Samples

R. B. Anderson1, R.V. Morris,S.M. Clegg, J.F. Bell III,S. D. Humphries, R. C. Wiens,

Introduction: 

The ChemCam instrument selected for the Curiosity rover is capable of remote laser-induced breakdown spectroscopy (LIBS). We used a remote LIBS instrument similar to ChemCam to analyze 197 geologic slab samples and 32 pressed-powder geostandards. The slab samples are well-characterized and have been used to validate the calibration of previous instruments on Mars missions, including CRISM , OMEGA , the MER Pancam , Mini-TES , and Mössbauer  instruments and the Phoenix SSI . The resulting dataset was used to compare multivariate methods for quantitative LIBS and to determine the effect of grain size on calculations. Three multivariate methods - partial least squares (PLS), multilayer perceptron artificial neural networks (MLP ANNs) and cascade correlation (CC) ANNs - were used to generate models and extract the quantitative composition of unknown samples. PLS can be used to predict one element (PLS1) or multiple elements (PLS2) at a time, as can the neural network methods. Although MLP and CC ANNs were successful in some cases, PLS generally produced the most accurate and precise results.

FannTool;

...

CC ANNs, an alternative type of neural network that determine their own structure as they are trained, were also tested, using the FannTool graphical interface to the open-source Fast Artificial Neural Network (FANN) library    ...