Deep learning technologies are increasingly used in the fi eld of geophysics,and a variety of algorithms based on shallow convolutional neural networks are more widely used in fault recognition,but these methods are u...Deep learning technologies are increasingly used in the fi eld of geophysics,and a variety of algorithms based on shallow convolutional neural networks are more widely used in fault recognition,but these methods are usually not able to accurately identify complex faults.In this study,using the advantage of deep residual networks to capture strong learning features,we introduce residual blocks to replace all convolutional layers of the three-dimensional(3D)UNet to build a new 3D Res-UNet and select appropriate parameters through experiments to train a large amount of synthesized seismic data.After the training is completed,we introduce the mechanism of knowledge distillation.First,we treat the 3D Res-UNet as a teacher network and then train the 3D Res-UNet as a student network;in this process,the teacher network is in evaluation mode.Finally,we calculate the mixed loss function by combining the teacher model and student network to learn more fault information,improve the performance of the network,and optimize the fault recognition eff ect.The quantitative evaluation result of the synthetic model test proves that the 3D Res-UNet can considerably improve the accuracy of fault recognition from 0.956 to 0.993 after knowledge distillation,and the eff ectiveness and feasibility of our method can be verifi ed based on the application of actual seismic data.展开更多
Analysis of the in situ stress orientation and magnitude in the No.4 Structure of Nanpu Sag was performed on the basis of data obtained from borehole breakout and acoustic emission measurements.On the basis of mechani...Analysis of the in situ stress orientation and magnitude in the No.4 Structure of Nanpu Sag was performed on the basis of data obtained from borehole breakout and acoustic emission measurements.On the basis of mechanical experiments,logging interpretation,and seismic data,a 3 D geological model and heterogeneous rock mechanics field of the reservoir were constructed.Finite element simulation techniques were then used for the detailed prediction of the 3 D stress field.The results indicated that the maximum horizontal stress orientation in the study area was generally NEE-SWW trending,with significant changes in the in situ stress orientation within and between fault blocks.Along surfaces and profiles,stress magnitudes were discrete and the in situ stress belonged to theⅠa-type.Observed inter-strata differences were characterized as five different types of in situ stress profile.Faults were the most important factor causing large distributional differences in the stress field of reservoirs within the complex fault blocks.The next important influence on the stress field was the reservoir’s rock mechanics parameters,which impacted on the magnitudes of in situ stress magnitudes.This technique provided a theoretical basis for more efficient exploration and development of low-permeability reservoirs within complex fault blocks.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
3D structure of the crust and upper mantle in the studied area has been analyzed from surface wave tomography. The velocity distribution in the uppermost crust is symmetrical on two sides of the central line of the se...3D structure of the crust and upper mantle in the studied area has been analyzed from surface wave tomography. The velocity distribution in the uppermost crust is symmetrical on two sides of the central line of the sea, and coincides with the structure of crystalline basement. The essential difference in tectonics between the East China Sea and the Yellow Sea mainly lies in that the velocity structures of their lower crust and upper mantle are identical to those of South China and North China respectively. In the upper mantle there exists a high-velocity zone with a nearly EW strike from the Hangzhou Bay, China, to the Tokara Channel, Japan, along about the latitude of 30°N. It is found that between the East China Sea and the Yellow Sea there are systematical differences in geomorphology, geology, seismicity, heat flow, quality factor and gravity and aeromagnetic anomalies, which is related to both left-lateral shear dislocation and right-lateral tear of the Benioff zone from the Hangzhou Bay to the Tokara Channel.It is inferred that the East China Sea was formed by Cenozoic back-arc extension. The boundary between the North China and South China crustal blocks stretches along the southern piedmont of Mts. Daba-Dabie-Hangzhou Bay-Tokara Channel, and the subduction zone at the Okinawa trench is the eastern boundary of the South China crustal block. The movements of the Pacific plate, Indian plate and upper mantle rather than the Philippine plate subduction have played a dominant role for the modern tectonic movements in East Asia.展开更多
基金supported by the National Natural Science Foundation of China(No.42072169)。
文摘Deep learning technologies are increasingly used in the fi eld of geophysics,and a variety of algorithms based on shallow convolutional neural networks are more widely used in fault recognition,but these methods are usually not able to accurately identify complex faults.In this study,using the advantage of deep residual networks to capture strong learning features,we introduce residual blocks to replace all convolutional layers of the three-dimensional(3D)UNet to build a new 3D Res-UNet and select appropriate parameters through experiments to train a large amount of synthesized seismic data.After the training is completed,we introduce the mechanism of knowledge distillation.First,we treat the 3D Res-UNet as a teacher network and then train the 3D Res-UNet as a student network;in this process,the teacher network is in evaluation mode.Finally,we calculate the mixed loss function by combining the teacher model and student network to learn more fault information,improve the performance of the network,and optimize the fault recognition eff ect.The quantitative evaluation result of the synthetic model test proves that the 3D Res-UNet can considerably improve the accuracy of fault recognition from 0.956 to 0.993 after knowledge distillation,and the eff ectiveness and feasibility of our method can be verifi ed based on the application of actual seismic data.
基金financially supported by the National Oil and Gas Major Project(2016ZX05047-003,2016ZX05014002-006)the National Natural Science Foundation of China(41572124)the Fundamental Research Funds for the Central Universities(17CX05010)
文摘Analysis of the in situ stress orientation and magnitude in the No.4 Structure of Nanpu Sag was performed on the basis of data obtained from borehole breakout and acoustic emission measurements.On the basis of mechanical experiments,logging interpretation,and seismic data,a 3 D geological model and heterogeneous rock mechanics field of the reservoir were constructed.Finite element simulation techniques were then used for the detailed prediction of the 3 D stress field.The results indicated that the maximum horizontal stress orientation in the study area was generally NEE-SWW trending,with significant changes in the in situ stress orientation within and between fault blocks.Along surfaces and profiles,stress magnitudes were discrete and the in situ stress belonged to theⅠa-type.Observed inter-strata differences were characterized as five different types of in situ stress profile.Faults were the most important factor causing large distributional differences in the stress field of reservoirs within the complex fault blocks.The next important influence on the stress field was the reservoir’s rock mechanics parameters,which impacted on the magnitudes of in situ stress magnitudes.This technique provided a theoretical basis for more efficient exploration and development of low-permeability reservoirs within complex fault blocks.
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.
基金The study (Project No. 85078) was supported by the Joint Foundation of Seismic Science.
文摘3D structure of the crust and upper mantle in the studied area has been analyzed from surface wave tomography. The velocity distribution in the uppermost crust is symmetrical on two sides of the central line of the sea, and coincides with the structure of crystalline basement. The essential difference in tectonics between the East China Sea and the Yellow Sea mainly lies in that the velocity structures of their lower crust and upper mantle are identical to those of South China and North China respectively. In the upper mantle there exists a high-velocity zone with a nearly EW strike from the Hangzhou Bay, China, to the Tokara Channel, Japan, along about the latitude of 30°N. It is found that between the East China Sea and the Yellow Sea there are systematical differences in geomorphology, geology, seismicity, heat flow, quality factor and gravity and aeromagnetic anomalies, which is related to both left-lateral shear dislocation and right-lateral tear of the Benioff zone from the Hangzhou Bay to the Tokara Channel.It is inferred that the East China Sea was formed by Cenozoic back-arc extension. The boundary between the North China and South China crustal blocks stretches along the southern piedmont of Mts. Daba-Dabie-Hangzhou Bay-Tokara Channel, and the subduction zone at the Okinawa trench is the eastern boundary of the South China crustal block. The movements of the Pacific plate, Indian plate and upper mantle rather than the Philippine plate subduction have played a dominant role for the modern tectonic movements in East Asia.
