This study presents a framework for the semi-automatic detection of rock discontinuities using a threedimensional(3D)point cloud(PC).The process begins by selecting an appropriate neighborhood size,a critical step for...This study presents a framework for the semi-automatic detection of rock discontinuities using a threedimensional(3D)point cloud(PC).The process begins by selecting an appropriate neighborhood size,a critical step for feature extraction from the PC.The effects of different neighborhood sizes(k=5,10,20,50,and 100)have been evaluated to assess their impact on classification performance.After that,17 geometric and spatial features were extracted from the PC.Next,ensemble methods,AdaBoost.M2,random forest,and decision tree,have been compared with Artificial Neural Networks to classify the main discontinuity sets.The McNemar test indicates that the classifiers are statistically significant.The random forest classifier consistently achieves the highest performance with an accuracy exceeding 95%when using a neighborhood size of k=100,while recall,F-score,and Cohen's Kappa also demonstrate high success.SHapley Additive exPlanations(SHAP),an Explainable AI technique,has been used to evaluate feature importance and improve the explainability of black-box machine learning models in the context of rock discontinuity classification.The analysis reveals that features such as normal vectors,verticality,and Z-values have the greatest influence on identifying main discontinuity sets,while linearity,planarity,and eigenvalues contribute less,making the model more transparent and easier to understand.After classification,individual discontinuity sets were detected using a revised DBSCAN from the main discontinuity sets.Finally,the orientation parameters of the plane fitted to each discontinuity were derived from the plane parameters obtained using the Random Sample Consensus(RANSAC).Two real-world datasets(obtained from SfM and LiDAR)and one synthetic dataset were used to validate the proposed method,which successfully identified rock discontinuities and their orientation parameters(dip angle/direction).展开更多
The results of quantitative analysis of fracture orientation distribution according to the pair of stereonet windows among 05 different survey sites along the segment Tien Yen-Mui Chua, belong to Cao Bang-Tien Yen fau...The results of quantitative analysis of fracture orientation distribution according to the pair of stereonet windows among 05 different survey sites along the segment Tien Yen-Mui Chua, belong to Cao Bang-Tien Yen fault zone, Quang Ninh province, Viet Nam showed that, the correlation values are over 0.80 corresponding to 50%, over 0.75 corresponding to 30% and over 0.65 corresponding to 20%. These values are quite consistent with over 60% of the fracture number in the direction of NW-SE. Especially, the compatibility is clearly reflected in the determination of the frequency of fracture measurements within the division intervals of 20 degrees for dip direction and 10 degrees for dip angle at 05 different survey sites.展开更多
The high-resolution azimuthal resistivity laterolog response in a fractured formation was numerically simulated using a three-dimensional finite element method. Simulation results show that the azimuthal resistivity i...The high-resolution azimuthal resistivity laterolog response in a fractured formation was numerically simulated using a three-dimensional finite element method. Simulation results show that the azimuthal resistivity is determined by fracture dipping as well as dipping direction, while the amplitude differences between deep and shallow laterolog resistivities are mainly controlled by the former. A linear relationship exists between the corrected apparent conductivities and fracture aperture. With the same fracture aperture, the deep and shallow laterolog resistivities present small values with negative separations for low-angle fractures, while azimuthal resistivities have large variations with positive separations for high-angle fractures that intersect the borehole. For dipping fractures, the variation of the azimuthal resistivity becomes larger when the fracture aperture increases. In addition, for high-angle fractures far from the borehole, a negative separation between the deep and shallow resistivities exists when fracture aperture is large as well as high resistivity contrast exists between bedrock and fracture fluid. The decreasing amplitude of dual laterolog resistivity can indicate the aperture of low-angle fractures, and the variation of the deep azimuthal resistivity can give information of the aperture of high-angle fractures and their position relative to the borehole.展开更多
文摘This study presents a framework for the semi-automatic detection of rock discontinuities using a threedimensional(3D)point cloud(PC).The process begins by selecting an appropriate neighborhood size,a critical step for feature extraction from the PC.The effects of different neighborhood sizes(k=5,10,20,50,and 100)have been evaluated to assess their impact on classification performance.After that,17 geometric and spatial features were extracted from the PC.Next,ensemble methods,AdaBoost.M2,random forest,and decision tree,have been compared with Artificial Neural Networks to classify the main discontinuity sets.The McNemar test indicates that the classifiers are statistically significant.The random forest classifier consistently achieves the highest performance with an accuracy exceeding 95%when using a neighborhood size of k=100,while recall,F-score,and Cohen's Kappa also demonstrate high success.SHapley Additive exPlanations(SHAP),an Explainable AI technique,has been used to evaluate feature importance and improve the explainability of black-box machine learning models in the context of rock discontinuity classification.The analysis reveals that features such as normal vectors,verticality,and Z-values have the greatest influence on identifying main discontinuity sets,while linearity,planarity,and eigenvalues contribute less,making the model more transparent and easier to understand.After classification,individual discontinuity sets were detected using a revised DBSCAN from the main discontinuity sets.Finally,the orientation parameters of the plane fitted to each discontinuity were derived from the plane parameters obtained using the Random Sample Consensus(RANSAC).Two real-world datasets(obtained from SfM and LiDAR)and one synthetic dataset were used to validate the proposed method,which successfully identified rock discontinuities and their orientation parameters(dip angle/direction).
文摘The results of quantitative analysis of fracture orientation distribution according to the pair of stereonet windows among 05 different survey sites along the segment Tien Yen-Mui Chua, belong to Cao Bang-Tien Yen fault zone, Quang Ninh province, Viet Nam showed that, the correlation values are over 0.80 corresponding to 50%, over 0.75 corresponding to 30% and over 0.65 corresponding to 20%. These values are quite consistent with over 60% of the fracture number in the direction of NW-SE. Especially, the compatibility is clearly reflected in the determination of the frequency of fracture measurements within the division intervals of 20 degrees for dip direction and 10 degrees for dip angle at 05 different survey sites.
基金co-funded by the National Natural Science Foundation of China(41174099,41474100)the Fundamental Research Funds for the Central Universities (14CX06077A)National Major Science & Technology Projects of China(2011ZX05003,2011ZX05009,2011ZX05020,2011ZX 05035)
文摘The high-resolution azimuthal resistivity laterolog response in a fractured formation was numerically simulated using a three-dimensional finite element method. Simulation results show that the azimuthal resistivity is determined by fracture dipping as well as dipping direction, while the amplitude differences between deep and shallow laterolog resistivities are mainly controlled by the former. A linear relationship exists between the corrected apparent conductivities and fracture aperture. With the same fracture aperture, the deep and shallow laterolog resistivities present small values with negative separations for low-angle fractures, while azimuthal resistivities have large variations with positive separations for high-angle fractures that intersect the borehole. For dipping fractures, the variation of the azimuthal resistivity becomes larger when the fracture aperture increases. In addition, for high-angle fractures far from the borehole, a negative separation between the deep and shallow resistivities exists when fracture aperture is large as well as high resistivity contrast exists between bedrock and fracture fluid. The decreasing amplitude of dual laterolog resistivity can indicate the aperture of low-angle fractures, and the variation of the deep azimuthal resistivity can give information of the aperture of high-angle fractures and their position relative to the borehole.
