Simultaneous determination of lithology and major elements in rocks using laser-induced breakdown spectroscopy (LIBS) coupled with a deep convolutional neural network

Abstract

Accurate lithological recognition and quantitative determination of the multiple chemical elements have a wide market application prospect in geological and geochemical exploration. In recent years, with the development of machine...

A hybrid wavelength selection strategy-based quantitative analysis model for LIBS data from standard ground samples of the Curiosity rover on Mars

“…LIBS data contain thousands of wavelengths, which decrease the efficiency of analytical models. 41 Thus, wavelength selection is a crucial step before establishing chemometric models and helps reduce the quantity of data. The intensity and position of spectral lines reflect the differences among samples, and the emission lines presented in the previous study 42 are summarized in Table 2.…”

Rapid quantitative analysis of raw rocks by LIBS coupled with feature-based transfer learning

“…The detailed denitions of these metrics are explained in the relevant literature. 18,35 The coefficient of determination is a measure of how well the model ts the training data, the mean absolute error represents the average absolute difference between the predicted and true values, and the root mean squared error is used to observe the degree of dispersion between the predicted and true values.…”

Atomic spectrometry update – a review of advances in environmental analysis

“…As a consequence, much effort has been devoted to chemometric methods for handling LIBS data . These included: a convolutional neural network model for the analysis of phosphate ore slurry; 225 a convolutional neural network model with a 2D algorithm for the determination of the lithology and major element compositions in rocks; 226 rapid LIBS multielement imaging combined with deep-learning theory for the classification of rocks; 227 and machine-learning algorithms to determine structural water in rocks. 228…”