In situ rapid classification of rock lithology is crucial in various fields, including geological exploration and petroleum logging. Laser-induced breakdown spectroscopy (LIBS) is particularly well-suited for in situ online analysis due to its rapid response time and minimal sample preparation requirements. To facilitate in situ raw rock discrimination analysis, a portable LIBS device was developed specifically for outdoor use. This device built upon a previous multi-directional optimization scheme and integrated machine learning to classify seven types of original rock samples: mudstone, basalt, dolomite, sandstone, conglomerate, gypsolyte, and shale from oil logging sites. Initially, spectral data were collected from random areas of each rock sample, and a series of pre-processing steps and data dimensionality reduction were performed to enhance the accuracy and efficiency of the LIBS device. Subsequently, four classification algorithms—linear discriminant analysis (LDA), K-nearest neighbor (KNN), support vector machine (SVM), and extreme gradient boosting (XGBoost)—were employed for classification discrimination. The results were evaluated using a confusion matrix. The final average classification accuracies achieved were 95.71%, 93.57%, 92.14%, and 98.57%, respectively. This work not only demonstrates the effectiveness of the portable LIBS device in classifying various original rock types, but it also highlights the potential of the XGBoost algorithm in improving LIBS analytical performance in field scenarios and geological applications, such as oil logging sites.

Rocks are an extremely important and indispensable part of the Earth's crust, with wide applications in various fields such as geology, environmental monitoring, and industry. Traditional methods often rely on a single analytical technique or visual inspection, but this may not achieve the accuracy required for thorough classification. Laser-induced breakdown spectroscopy (LIBS) technology mainly provides information on the composition and content of rock elements, while images can provide appearance information such as color and texture. The multilayer perceptron (MLP) and DenseNet121 models were selected for processing preprocessed LIBS and image data, respectively. When using LIBS and images separately for classification, the accuracy rates were 93.63% and 90.90%, respectively. However, after fusing the bimodal data using LIBS and images, we achieved a significant performance improvement of 97.27% in accuracy. This study indicates that advanced neural network models can effectively integrate LIBS and image data and improve the performance of rock classification.

In situ classification of rock lithology is of great importance in several fields such as geological exploration and petroleum logging. Laser induced breakdown spectroscopy (LIBS) is well suited for in situ on-line analysis due to its fast response and little or no sample preparation. In order to implement in-situ rock discrimination analysis, a portable LIBS system that can be used outdoors was built based on the previous multi-directional optimization scheme, and combined with machine learning to classify the seven types of original rock samples (mudstone, volcanic, dolomite, sandstone, conglomerate, gypsolyte and shale) without any sample pre-processing in the field. Firstly, spectral data were collected from random areas of each rock sample, and a series of pre-processing and data dimensionality reduction were performed on the spectral data in order to improve the accuracy and efficiency of the analyzing system; Next, four classification algorithms, including linear discriminant analysis (LDA), K-nearest neighbor (KNN), support vector machine (SVM), and extreme gradient boosting (XGBoost), were used for classification discrimination. The confusion matrix was used to evaluate the analysis results. The final average classification accuracies were 95.71%, 93.57%, 92.14%, and 98.57%, respectively. The results showed that XGBoost is expected to help LIBS become a competitive technique for in situ lithology rapid identification.