381 Figure 2 ROI selection interface for labelling hyperspectral training data 3.2. Result of segmentation In this experiment, the three rock types were assigned labels, and machine learning models were trained. The dataset employed for classification was the hyperspectral dataset delineated in Section 3.1. Hyperspectral images obtained from actual borehole core samples were utilized for training, and the classification model was constructed based on the spectral information obtained. For the hyperspectral images that were not utilized in the training process, the previously constructed model was applied to determine the rock type. The outcomes of this analysis are presented in Figure 3(a). To evaluate the accuracy of the application, a comparison was made between the results of the rock types determined by the naked eye and the results of the machine learning model constructed using a Python script (Figure 3(b)). The correct answer data (labels based on ocular appraisal) used for the comparison is shown in Figure 3(c), and it was confirmed that the results were in high agreement with the judgment results by the application. In addition, the model built on the application was compared with the conventional Python-based model building method, and no significant differences were found between the two results. These results suggest that the applicationbased learning and judgment process performs as well as conventional programming-based methods, supporting its high practicality in the field. Figure 3 Rock classification results using hyperspectral images. (a) Prediction by trained model by the application. (b) Comparison with Python-based method. (c) Ground truth by visual inspection
RkJQdWJsaXNoZXIy MTM0Mzk2