Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Ou...Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.展开更多
3D geological modeling is an inevitable choice for coal exploration to adapt to the transformation of coal mining for green, fine, transparent and Intelligent mining. In the traditional Coalfield exploration geologica...3D geological modeling is an inevitable choice for coal exploration to adapt to the transformation of coal mining for green, fine, transparent and Intelligent mining. In the traditional Coalfield exploration geological reports, the spatial expression form for the coal seams and their surrounding rocks are 2D maps. These 2D maps are excellent data sources for constructing 3D geological models of coal field exploration areas. How to construct 3D models from these 2D maps has been studying in coal exploration industry for a long time, and still no breakthrough has been achieved so far. This paper discusses the principle, method and software design idea of constructing 3D geological model of an exploration area with 2D maps made by AutoCAD/MapGIS. At first, the paper analyzes 3D geological surface expression mode in 3D geological modeling software. It is pointed out that although contour method has unique advantages in coal field exploration, TIN (Triangular Irregular Network) is still the standard configuration of 3D modeling software for coal field. Then, the paper discusses the method of 2D line features obtaining elevation and upgrading 2D curve to 3D curve. Next, the method of semi-automatic partition is introduced to build the boundary ring of the surface patch, that is, the user clicks and selects the line feature to build the outer boundary ring of the surface patch. Then, Auto-process method for fault line inside of the outer boundary ring is discussed, it including construction of fault ring, determining fault ring being normal fault ring or reverse fault ring and an algorithm of dealing with normal fault ring. An algorithm of dealing with reverse fault ring is discussed detailly, the method of expanding reverse fault ring and dividing the duplicate area in reverse fault into two portions is introduced. The paper also discusses the method of extraction ridge line/valley line, the construction of fault plane, the construction of stratum and coal body. The above ideas and methods have been initially implemented in the “3D modeling platform for coal field exploration” software, and applied to the 3D modeling practice of data from several coal field exploration areas in Ningxia, Shanxi, Qinghai, etc.展开更多
Based on data of fault movement surveying, we simulate the evolution process of three dimensional stress field in North China by three dimensional finite element method. Evolutional patterns in one-year time scale fro...Based on data of fault movement surveying, we simulate the evolution process of three dimensional stress field in North China by three dimensional finite element method. Evolutional patterns in one-year time scale from 1986 to 1997 have been illustrated and the evolution characteristics of stress field have been analyzed. In comparison with the seismic activity among that time interval in North China, we have primarily discussed the relationship between the evolution of stress field and seismic activity.展开更多
The capabilities of GIS in modeling fault patterns are explored for Irkutsk city in East Siberia with implications for ground stability. The neotectonic structure of the area is visualized in three dimension (3D) ta...The capabilities of GIS in modeling fault patterns are explored for Irkutsk city in East Siberia with implications for ground stability. The neotectonic structure of the area is visualized in three dimension (3D) taking into account fault dips, using the ArcGIS, GlobalMapper and Paradigm Geophysical packages. The study area is divided into blocks of different size classes according to the length-based ranks of the bounding faults, which are of five classes distinguished with the equal interval method. The blocks show different deformation patterns, with different densities and strikes of crossing and bounding faults. The data are statistically processed using GIS to estimate the deformation degrees of blocks in arbitrary units per square kilometer using the attributes of rank and crossing/bounding position of faults and the size of blocks. The deformation degrees are then compared with available estimates of ground stability measured as a score of points corresponding to destabilizing factors. Although the comparison generally confirms some linkage between the deformation degree of blocks and their ground stability, the correlation is intricate and ambiguous. In order to enhance the advantages of GIS in building and analyzing 3D models of fault patterns for estimating ground stability and mitigating geological hazards, it is expected in the future to proceed from the reported initial step of visualization to more advanced analysis.展开更多
文摘Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.
文摘3D geological modeling is an inevitable choice for coal exploration to adapt to the transformation of coal mining for green, fine, transparent and Intelligent mining. In the traditional Coalfield exploration geological reports, the spatial expression form for the coal seams and their surrounding rocks are 2D maps. These 2D maps are excellent data sources for constructing 3D geological models of coal field exploration areas. How to construct 3D models from these 2D maps has been studying in coal exploration industry for a long time, and still no breakthrough has been achieved so far. This paper discusses the principle, method and software design idea of constructing 3D geological model of an exploration area with 2D maps made by AutoCAD/MapGIS. At first, the paper analyzes 3D geological surface expression mode in 3D geological modeling software. It is pointed out that although contour method has unique advantages in coal field exploration, TIN (Triangular Irregular Network) is still the standard configuration of 3D modeling software for coal field. Then, the paper discusses the method of 2D line features obtaining elevation and upgrading 2D curve to 3D curve. Next, the method of semi-automatic partition is introduced to build the boundary ring of the surface patch, that is, the user clicks and selects the line feature to build the outer boundary ring of the surface patch. Then, Auto-process method for fault line inside of the outer boundary ring is discussed, it including construction of fault ring, determining fault ring being normal fault ring or reverse fault ring and an algorithm of dealing with normal fault ring. An algorithm of dealing with reverse fault ring is discussed detailly, the method of expanding reverse fault ring and dividing the duplicate area in reverse fault into two portions is introduced. The paper also discusses the method of extraction ridge line/valley line, the construction of fault plane, the construction of stratum and coal body. The above ideas and methods have been initially implemented in the “3D modeling platform for coal field exploration” software, and applied to the 3D modeling practice of data from several coal field exploration areas in Ningxia, Shanxi, Qinghai, etc.
基金State Natural Science Foundation of China (49574223)Key Project (95-04-04-03-01) from China Seismological Bureau under (Nint
文摘Based on data of fault movement surveying, we simulate the evolution process of three dimensional stress field in North China by three dimensional finite element method. Evolutional patterns in one-year time scale from 1986 to 1997 have been illustrated and the evolution characteristics of stress field have been analyzed. In comparison with the seismic activity among that time interval in North China, we have primarily discussed the relationship between the evolution of stress field and seismic activity.
文摘The capabilities of GIS in modeling fault patterns are explored for Irkutsk city in East Siberia with implications for ground stability. The neotectonic structure of the area is visualized in three dimension (3D) taking into account fault dips, using the ArcGIS, GlobalMapper and Paradigm Geophysical packages. The study area is divided into blocks of different size classes according to the length-based ranks of the bounding faults, which are of five classes distinguished with the equal interval method. The blocks show different deformation patterns, with different densities and strikes of crossing and bounding faults. The data are statistically processed using GIS to estimate the deformation degrees of blocks in arbitrary units per square kilometer using the attributes of rank and crossing/bounding position of faults and the size of blocks. The deformation degrees are then compared with available estimates of ground stability measured as a score of points corresponding to destabilizing factors. Although the comparison generally confirms some linkage between the deformation degree of blocks and their ground stability, the correlation is intricate and ambiguous. In order to enhance the advantages of GIS in building and analyzing 3D models of fault patterns for estimating ground stability and mitigating geological hazards, it is expected in the future to proceed from the reported initial step of visualization to more advanced analysis.