Leveraging High-Resolution Long-Wave Infrared Hyperspectral Laboratory Imaging Data for Mineral Identification Using Machine Learning Methods

Abstract

Laboratory-based hyperspectral imaging (HSI) is an optical non-destructive technology used to extract mineralogical information from bedrock drill cores. In the present study, drill core scanning in the long-wave infrared (LWIR; 8000–12,000 nm) wavelength region was used to map the dominant minerals in HSI pixels. Machine learning classification algorithms, including random forest (RF) and support vector machine, have previously been applied to the mineral characterization of drill core hyperspectral data. The objectives of this study are to expand semi-automated mineral mapping by investigating the mapping accuracy, generalization potential, and classification ability of cutting-edge methods, such as various ensemble machine learning algorithms and deep learning semantic segmentation. In the present study, the mapping of quartz, talc, chlorite, and mixtures thereof in HSI data was performed using the ENVINet5 algorithm, which is based on the U-net deep learning network and four decision tree ensemble algorithms, including RF, gradient-boosting decision tree (GBDT), light gradient-boosting machine (LightGBM), AdaBoost, and bagging. Prior to training the classification models, endmember selection was employed using the Sequential Maximum Angle Convex Cone endmember extraction method to prepare the samples used in the model training and evaluation of the classification results. The results show that the GBDT and LightGBM classifiers outperformed the other classification models with overall accuracies of 89.43% and 89.22%, respectively. The results of the other classifiers showed overall accuracies of 87.32%, 87.33%, 82.74%, and 78.32% for RF, bagging, ENVINet5, and AdaBoost, respectively. Therefore, the findings of this study confirm that the ensemble machine learning algorithms are efficient tools to analyze drill core HSI data and map dominant minerals. Moreover, the implementation of deep learning methods for mineral mapping from HSI drill core data should be further explored and adjusted.

Main–Sub Transformer With Spectral–Spatial Separable Convolution for Hyperspectral Image Classification

“…H YPERSPECTRAL images (HSI) contain rich information [1], which has two spatial dimensions and one spectral dimension. Compared with ordinary RGB images, it has richer spectral information [2] and can be used in precision agriculture [3], modern medical detection [4], military security [5], and other fields [6], [7], [8]. The process of HSI classification encompasses the identification of each pixel within a scene and The authors are with the College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China (e-mail: gaojingpeng@hrbeu.edu.cn; jixiangyu@hrbeu.edu.cn; chengengic@hrbeu.edu.cn; 983402243@hrbeu.edu.cn).…”

Estimation of the dolomite content of carbonate rock outcrops based on spectral knowledge and machine learning

“…By contrast, hyperspectral techniques, effectively utilize the spectral differences between minerals for mineralogical analysis (van der Meer et al, 2012;Hecker et al, 2019). Thus, hyperspectral approaches have advantages in terms of speed, efficiency, cost, and non-destructiveness (Zaini et al, 2014;Hamedianfar et al, 2023). Commonly used hyperspectral devices for outcrop studies include ground-based hyperspectral imagers and field spectrometers, such as analytical spectral devices (ASD).…”