Extraction of fractures in shale CT images using improved U-Net

作     者：Xiang Wu Fei Wang Xiaoqiu Zhang Bohua Han Qianru Liu Yonghao Zhang 

作者机构：College of Geology Engineering and GeomaticsChang'an UniversityXi'anShaanxi710054China Qinghai Oilfield Exploration and Development Research InstituteDunhuangGansu736202China China Petroleum Logging Co.Ltd.Xi'anShaanxi710077China 

出 版 物：《Energy Geoscience》 (能源地球科学（英文）)

年 卷 期：2024年第5卷第2期

页      面：240-248页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：funded by the Natural Science Basis Research Plan in Shaanxi Province of China(No.2022JM-147) 

主　　题：CT slices Fracture segmentation Shale U-Net Deep learning 

摘      要：Accurate extraction of pores and fractures is a prerequisite for constructing digital rocks for physical property simulation and microstructural response ***,fractures in CT images are similar in grayscale to the rock matrix,and traditional algorithms have difficulty to achieve accurate segmentation *** this study,a dataset containing multiscale fracture information was constructed,and a U-Net semantic segmentation model with a scSE attention mechanism was used to classify shale CT images at the pixel level and compare the results with traditional *** results showed that the CLAHE algorithm effectively removed noise and enhanced the fracture information in the dark parts,which is beneficial for further fracture *** Canny edge detection algorithm had significant false positives and failed to recognize the internal information of the *** Otsu algorithm only extracted fractures with a significant difference from the background and was not sensitive enough for fine *** MEF algorithm enhanced the edge information of the fractures and was also sensitive to fine fractures,but it overestimated the aperture of the *** U-Net was able to identify almost all fractures with good continuity,with an MIou and Recall of 0.80 and 0.82,*** the image resolution increases,more fine fracture information can be extracted.