Classification and statistical analysis of hydrothermal seafloor rocks measured underwater using laser‐induced breakdown spectroscopy

Abstract

This study investigates the use of statistical methods for the classification of laser‐induced breakdown spectroscopy (LIBS) measurements of water‐immersed rocks with respect to their labels and geological groups. The analysis is performed on deep‐sea hydrothermal deposit rocks. These rocks are categorized on the basis of the relative ratio of Zn‐Pb‐Cu on a ternary diagram. The proposed method demonstrates that the accurate classification of rocks with respect to their labels and geological group from the LIBS data can be successfully achieved by combining principal component analysis (PCA), which reduces the dimensionality of the data, with classification algorithms such as the support vector machine (SVM), k‐nearest neighbor search (KNN), and artificial neural network (ANN) methods. The performance of the classification algorithms depends on the size of the dataset. Additionally, removing the linear trend from the data enhances the performance of the classification in terms of sensitivity. The best classification performance concerning the rock label is obtained using an SVM linear kernel algorithm with 95% sensitivity. The best classification performance concerning the geological group is obtained using the SVM method with 98% accuracy. The one‐sided Wilcoxon signed rank test is applied to the classification results in the rock label and group cases, and the results indicate that the SVM algorithm has statistical significance over the other algorithms while classifying the rock labels and rock group.

Spectral characteristic of laser-induced plasma in soil

“…Laser-induced breakdown spectroscopy (LIBS) [3,4] has several advantages such as fast analysis, no sample pretreatment, easy operation and analysis of different specimens. In recent years, researchers have carried out related research work on environment [5][6][7][8][9], steel [10][11][12][13], food [14][15][16], ocean [17][18][19], energy [20,21], space exploration [22,23], and biology [24,25]. However, LIBS is also faced with difficulties of low quantitative accuracy and high detection limit.…”

Review of In-Situ Online LIBS Detection in the Atmospheric Environment

“…Currently, the most common algorithms used in LIBS analysis are principal component analysis (PCA), [82][83][84][85] linear discriminant analysis (LDA), [86][87][88] support vector machine (SVM), [89][90][91] random forest (RF), [92][93][94] and artificial neural networks (ANN). [95][96][97][98] For the classification of pollutants, these methods work equally well. Lu et al applied PCA, 99 SVM, and back-propagation artificial neural networks (BP-ANN) for realtime in-situ detection and classification of some typical pollutants.…”

Effect of repeated irradiation on laser-induced breakdown spectroscopy of copper immersed in a sodium chloride aqueous solution and normalization with bubble collapse time

“…The examples of signal preprocessing reported in underwater LIBS are as follows: normalization with internal standard lines, 1,2,29,36–39 total integrated intensity, 19,23,25,40 background intensity, 31 acoustic signals, 41,42 plasma image information, 42–44 data selection using threshold values, 23,45,46 baseline correction, 47 temperature segmentation, 40,48 data augmentation, 49 and detrend operation. 50…”

“…The examples of signal preprocessing reported in underwater LIBS are as follows: normalization with internal standard lines, 1,2,29,[36][37][38][39] total integrated intensity, 19,23,25,40 background intensity, 31 acoustic signals, 41,42 plasma image information, [42][43][44] data selection using threshold values, 23,45,46 baseline correction, 47 temperature segmentation, 40,48 data augmentation, 49 and detrend operation. 50 Simultaneous detection of some sort of parameter and its use for the normalization of LIBS signals is a simple way to reduce the signal uctuation. It is valuable to investigate possible parameters to meet the various situations of underwater applications.…”