Formation pore pressure is the foundation of well plan,and it is related to the safety and efficiency of drilling operations in oil and gas development.However,the traditional method for predicting formation pore pres...Formation pore pressure is the foundation of well plan,and it is related to the safety and efficiency of drilling operations in oil and gas development.However,the traditional method for predicting formation pore pressure involves applying post-drilling measurement data from nearby wells to the target well,which may not accurately reflect the formation pore pressure of the target well.In this paper,a novel method for predicting formation pore pressure ahead of the drill bit by embedding petrophysical theory into machine learning based on seismic and logging-while-drilling(LWD)data was proposed.Gated recurrent unit(GRU)and long short-term memory(LSTM)models were developed and validated using data from three wells in the Bohai Oilfield,and the Shapley additive explanations(SHAP)were utilized to visualize and interpret the models proposed in this study,thereby providing valuable insights into the relative importance and impact of input features.The results show that among the eight models trained in this study,almost all model prediction errors converge to 0.05 g/cm^(3),with the largest root mean square error(RMSE)being 0.03072 and the smallest RMSE being 0.008964.Moreover,continuously updating the model with the increasing training data during drilling operations can further improve accuracy.Compared to other approaches,this study accurately and precisely depicts formation pore pressure,while SHAP analysis guides effective model refinement and feature engineering strategies.This work underscores the potential of integrating advanced machine learning techniques with domain-specific knowledge to enhance predictive accuracy for petroleum engineering applications.展开更多
A non-return-to-zero （NRZ） to pseudo-return-to-zero （PRZ） converter consisting of a semiconductor optical amplifier （SOA） and an arrayed waveguide grating （AWG） is proposed, by which the enhancement of clock f...A non-return-to-zero （NRZ） to pseudo-return-to-zero （PRZ） converter consisting of a semiconductor optical amplifier （SOA） and an arrayed waveguide grating （AWG） is proposed, by which the enhancement of clock frequency component and clock-to-data suppression ratio of the XRZ data are evidently achieved. All- optical clock recovery from XRZ data at 10 Gb/s is successfully demonstrated with the proposed XRZ-to- PRZ converter and a mode-locked SOA fiber laser. Furthermore, XRZ-to-RZ format conversion of 10 Gb/s is realized bv using the recovered clock as the control light of terahertz optical asymmetric demultiplexer （TOAD）, which further proves that the proposed clock recovery scheme is applicable.展开更多
To solve the problems in restoring sedimentary facies and predicting reservoirs in loose gas-bearing sediment,based on seismic sedimentologic analysis of the first 9-component S-wave 3D seismic dataset of China,a four...To solve the problems in restoring sedimentary facies and predicting reservoirs in loose gas-bearing sediment,based on seismic sedimentologic analysis of the first 9-component S-wave 3D seismic dataset of China,a fourth-order isochronous stratigraphic framework was set up and then sedimentary facies and reservoirs in the Pleistocene Qigequan Formation in Taidong area of Qaidam Basin were studied by seismic geomorphology and seismic lithology.The study method and thought are as following.Firstly,techniques of phase rotation,frequency decomposition and fusion,and stratal slicing were applied to the 9-component S-wave seismic data to restore sedimentary facies of major marker beds based on sedimentary models reflected by satellite images.Then,techniques of seismic attribute extraction,principal component analysis,and random fitting were applied to calculate the reservoir thickness and physical parameters of a key sandbody,and the results are satisfactory and confirmed by blind testing wells.Study results reveal that the dominant sedimentary facies in the Qigequan Formation within the study area are delta front and shallow lake.The RGB fused slices indicate that there are two cycles with three sets of underwater distributary channel systems in one period.Among them,sandstones in the distributary channels of middle-low Qigequan Formation are thick and broad with superior physical properties,which are favorable reservoirs.The reservoir permeability is also affected by diagenesis.Distributary channel sandstone reservoirs extend further to the west of Sebei-1 gas field,which provides a basis to expand exploration to the western peripheral area.展开更多
Pore pressure is a decisive measure to assess the reservoir’s geomechanical properties,ensures safe and efficient drilling operations,and optimizes reservoir characterization and production.The conventional approache...Pore pressure is a decisive measure to assess the reservoir’s geomechanical properties,ensures safe and efficient drilling operations,and optimizes reservoir characterization and production.The conventional approaches sometimes fail to comprehend complex and persistent relationships between pore pressure and formation properties in the heterogeneous reservoirs.This study presents a novel machine learning optimized pore pressure prediction method with a limited dataset,particularly in complex formations.The method addresses the conventional approach's limitations by leveraging its capability to learn complex data relationships.It integrates the best Gradient Boosting Regressor(GBR)algorithm to model pore pressure at wells and later utilizes ContinuousWavelet Transformation(CWT)of the seismic dataset for spatial analysis,and finally employs Deep Neural Network for robust and precise pore pressure modeling for the whole volume.In the second stage,for the spatial variations of pore pressure in the thin Khadro Formation sand reservoir across the entire subsurface area,a three-dimensional pore pressure prediction is conducted using CWT.The relationship between the CWT and geomechanical properties is then established through supervised machine learning models on well locations to predict the uncertainties in pore pressure.Among all intelligent regression techniques developed using petrophysical and elastic properties for pore pressure prediction,the GBR has provided exceptional results that have been validated by evaluation metrics based on the R^(2) score i.e.,0.91 between the calibrated and predicted pore pressure.Via the deep neural network,the relationship between CWT resultant traces and predicted pore pressure is established to analyze the spatial variation.展开更多
The Canglangpu Stage of Lower Cambrian Series is widely distributed along both sides of the Tanlu (Tancheng-Lujiang) Fault Zone in the Jiao-Liao-Xu-Huai regions. In the Liaodong Peninsula, the Canglangpu Stage consist...The Canglangpu Stage of Lower Cambrian Series is widely distributed along both sides of the Tanlu (Tancheng-Lujiang) Fault Zone in the Jiao-Liao-Xu-Huai regions. In the Liaodong Peninsula, the Canglangpu Stage consists of three formations, i.e. Gejiatun, Dalinzi and Jianchang formations in ascending order (lying on the eastern side of the Tanlu Fault Zone). The Dalinzi Formation, developing in a littoral Sabkha environment, is full of catastrophic event records of violent seism, such as liquefied muddy-sandy veins, hydroplastic folds, hydroplastic micro-faults (three forming an organic whole), liquefied crinkled deformations, liquefied breccia and sandy dikes. Based on such records, the seismic liquified sequence of argillaceous rocks in Sabkha is built up. In northern Jiangsu and Anhui provinces, however, there hardly observe seismic records in the Canglangpu Stage, which consists of Jinshanzhai and lower Gouhou and upper Gouhou formations (lying on the western side of the Tanlu Fault Zone). Even if the Gouhou Formation, developing in a lagoon-dry environment, is in the same climate zone as the Dalinzi Formation, and 4 depositional sequences have been identified in the Canglangpu Stage in Northern Jiangsu and Anhui provinces, however, in the same stage in the Liaodong Peninsula, there exist only 3 ones. Therefore, it is not supported by the above mentioned evidence (such as catastrophic events, sequences stratigraphy and lithologic correlation of formations) that the Canglangpu Stage in the Liaodong Peninsula came from northern Jiangsu and Anhui provinces through a long-distance, about hundreds kilometers, left-hand displacement of the Tanlu Fault in the Mesozoic era.展开更多
The northern Sichuan Basin,spreading in the northern section of the Longmenshan Fault Fold Belt,is characterized by dramatic fluctuations in the surface landforms,development of abdominal faults,and low-quality seismi...The northern Sichuan Basin,spreading in the northern section of the Longmenshan Fault Fold Belt,is characterized by dramatic fluctuations in the surface landforms,development of abdominal faults,and low-quality seismic data,resulting in difficulties in clarifying relevant structures.The key target formation,the Mid-Permian Qixia Fm,is deeply buried with thin reservoirs and high heterogeneity,which brings great challenges to seismic prediction.Under such circumstances,researches have been conducted jointly in terms of seismic data acquisition,processing and interpretation,and finally some relevant seismic survey technologies were developed suitable for surface/underground complex structures.Through surface structural surveys,dynamic deep-well lithologic identification,single-point detector deployment and process optimization,acquisition parameters can be excited.In addition,by using an observation systemwith high-coverage,wide-azimuth and huge-displacement,quality of acquired seismic data can be enhanced dramatically.Seismic imaging technologies for complex structures have been developed to enhance the quality of images for deep formations.These technologies are dominated by microscopic logging-constrained tomography static correction,high-resolution processing with fidelity and amplitude preservation and all-around PSDM in an angular domain.By using high-resolution gravity,magnetic and electric data,details related to geological structures and faults can be identified.In combination with fine seismic data interpretation,structural details and fault features can be verified effectively.Based on forwardmodeling and fine seismic calibration of reservoirs in individualwells,suitable attributes can be identified for predictions related to the distribution of reservoirs.By using all these auxiliary technologies,a large-scale structuralelithologic composite trap with a total area of 1223 km^(2) has been discovered in the NW Sichuan Basin.The Shuangyushi-Jiangyou area as a whole distributes on structural highs.In the areas to the south of Shuangyushi,the Qixia Fm dolomite reservoirs of platform margins are continuously developed.In conclusion,these auxiliary technologies can effectively allow trap identification and thin reservoir prediction in complex structures in the study area.In addition to clarifying the exploration orientation and providing a necessarily technical supports forwell development,these technologies help to accelerate the construction of demonstration projects for the exploration and development of deep marine carbonate formations.展开更多
Formed on top of the Gulf of Cadiz, the Al Idrissi mud volcano is the shallowest and largest mud volcano in the El Arraiche mud volcano field of the northwestern Moroccan margin. The development and morphology of mud ...Formed on top of the Gulf of Cadiz, the Al Idrissi mud volcano is the shallowest and largest mud volcano in the El Arraiche mud volcano field of the northwestern Moroccan margin. The development and morphology of mud volcanoes from the El Arraiche mud volcanoes group have been studied at a large scale. However, the time interval related to their formation period still needs to be better understood. In this regard, we interpreted and analyzed the seismic facies from the 2D reflection data of the GEOMARGEN-1 campaign, which took place in 2011. The aim was to identify the seismic sequences and draw the Al Idrissi mud volcano system to determine the formation period of the Al Idriss mud volcano. And as a result, the Al Idrissi mud volcano system is made of both buried and superficial bicone and was identified along with the Upper Tortonian to Messinian-Upper Pliocene facies. As the initial mud volcano extrusive edifice, the buried bicone was formed in the Late-Messinian to Early-Pliocene period. However, the superficial bicone, as the final extrusive edifice, was included in the Late Pliocene. In this case, the timing interval between the buried and superficial bicone is equivalent to the Late-Messinian to Upper-Pliocene period. Therefore, the latter corresponds to the Al Idrissi mud volcano formation period.展开更多
基金supported by the National Natural Science Foundation of China(Grant numbers:52174012,52394250,52394255,52234002,U22B20126,51804322).
文摘Formation pore pressure is the foundation of well plan,and it is related to the safety and efficiency of drilling operations in oil and gas development.However,the traditional method for predicting formation pore pressure involves applying post-drilling measurement data from nearby wells to the target well,which may not accurately reflect the formation pore pressure of the target well.In this paper,a novel method for predicting formation pore pressure ahead of the drill bit by embedding petrophysical theory into machine learning based on seismic and logging-while-drilling(LWD)data was proposed.Gated recurrent unit(GRU)and long short-term memory(LSTM)models were developed and validated using data from three wells in the Bohai Oilfield,and the Shapley additive explanations(SHAP)were utilized to visualize and interpret the models proposed in this study,thereby providing valuable insights into the relative importance and impact of input features.The results show that among the eight models trained in this study,almost all model prediction errors converge to 0.05 g/cm^(3),with the largest root mean square error(RMSE)being 0.03072 and the smallest RMSE being 0.008964.Moreover,continuously updating the model with the increasing training data during drilling operations can further improve accuracy.Compared to other approaches,this study accurately and precisely depicts formation pore pressure,while SHAP analysis guides effective model refinement and feature engineering strategies.This work underscores the potential of integrating advanced machine learning techniques with domain-specific knowledge to enhance predictive accuracy for petroleum engineering applications.
基金This work was supported by the National Natural Science Foundation of China (No. 90401025)Key Project of MOE (No. 105036)
文摘A non-return-to-zero （NRZ） to pseudo-return-to-zero （PRZ） converter consisting of a semiconductor optical amplifier （SOA） and an arrayed waveguide grating （AWG） is proposed, by which the enhancement of clock frequency component and clock-to-data suppression ratio of the XRZ data are evidently achieved. All- optical clock recovery from XRZ data at 10 Gb/s is successfully demonstrated with the proposed XRZ-to- PRZ converter and a mode-locked SOA fiber laser. Furthermore, XRZ-to-RZ format conversion of 10 Gb/s is realized bv using the recovered clock as the control light of terahertz optical asymmetric demultiplexer （TOAD）, which further proves that the proposed clock recovery scheme is applicable.
基金Supported by the CNPC Science and Technology Projects(2022-N/G-47808,2023-N/G-67014)RIPED International Cooperation Project(19HTY5000008).
文摘To solve the problems in restoring sedimentary facies and predicting reservoirs in loose gas-bearing sediment,based on seismic sedimentologic analysis of the first 9-component S-wave 3D seismic dataset of China,a fourth-order isochronous stratigraphic framework was set up and then sedimentary facies and reservoirs in the Pleistocene Qigequan Formation in Taidong area of Qaidam Basin were studied by seismic geomorphology and seismic lithology.The study method and thought are as following.Firstly,techniques of phase rotation,frequency decomposition and fusion,and stratal slicing were applied to the 9-component S-wave seismic data to restore sedimentary facies of major marker beds based on sedimentary models reflected by satellite images.Then,techniques of seismic attribute extraction,principal component analysis,and random fitting were applied to calculate the reservoir thickness and physical parameters of a key sandbody,and the results are satisfactory and confirmed by blind testing wells.Study results reveal that the dominant sedimentary facies in the Qigequan Formation within the study area are delta front and shallow lake.The RGB fused slices indicate that there are two cycles with three sets of underwater distributary channel systems in one period.Among them,sandstones in the distributary channels of middle-low Qigequan Formation are thick and broad with superior physical properties,which are favorable reservoirs.The reservoir permeability is also affected by diagenesis.Distributary channel sandstone reservoirs extend further to the west of Sebei-1 gas field,which provides a basis to expand exploration to the western peripheral area.
基金funded by the Basic Science Centre Project of the National Natural Science Foundation of China(Grant No.72088101)supported by the Higher Education Commission,Pakistan(Grant No.20-14925/NRPU/R&D/HEC/2021-2021)+1 种基金the Researchers Supporting Project Number(Grant No.RSP2025R351)King Saud University,Riyadh,Saudi Arabia,for funding this research article.
文摘Pore pressure is a decisive measure to assess the reservoir’s geomechanical properties,ensures safe and efficient drilling operations,and optimizes reservoir characterization and production.The conventional approaches sometimes fail to comprehend complex and persistent relationships between pore pressure and formation properties in the heterogeneous reservoirs.This study presents a novel machine learning optimized pore pressure prediction method with a limited dataset,particularly in complex formations.The method addresses the conventional approach's limitations by leveraging its capability to learn complex data relationships.It integrates the best Gradient Boosting Regressor(GBR)algorithm to model pore pressure at wells and later utilizes ContinuousWavelet Transformation(CWT)of the seismic dataset for spatial analysis,and finally employs Deep Neural Network for robust and precise pore pressure modeling for the whole volume.In the second stage,for the spatial variations of pore pressure in the thin Khadro Formation sand reservoir across the entire subsurface area,a three-dimensional pore pressure prediction is conducted using CWT.The relationship between the CWT and geomechanical properties is then established through supervised machine learning models on well locations to predict the uncertainties in pore pressure.Among all intelligent regression techniques developed using petrophysical and elastic properties for pore pressure prediction,the GBR has provided exceptional results that have been validated by evaluation metrics based on the R^(2) score i.e.,0.91 between the calibrated and predicted pore pressure.Via the deep neural network,the relationship between CWT resultant traces and predicted pore pressure is established to analyze the spatial variation.
基金The work was jointly supported by the State Science and Technology Commission of China (Grant No. 95-special-04) the Geological Bureau of Survey and CAGS (Grant Nos. DKD2001007 and DKD2001010).
文摘The Canglangpu Stage of Lower Cambrian Series is widely distributed along both sides of the Tanlu (Tancheng-Lujiang) Fault Zone in the Jiao-Liao-Xu-Huai regions. In the Liaodong Peninsula, the Canglangpu Stage consists of three formations, i.e. Gejiatun, Dalinzi and Jianchang formations in ascending order (lying on the eastern side of the Tanlu Fault Zone). The Dalinzi Formation, developing in a littoral Sabkha environment, is full of catastrophic event records of violent seism, such as liquefied muddy-sandy veins, hydroplastic folds, hydroplastic micro-faults (three forming an organic whole), liquefied crinkled deformations, liquefied breccia and sandy dikes. Based on such records, the seismic liquified sequence of argillaceous rocks in Sabkha is built up. In northern Jiangsu and Anhui provinces, however, there hardly observe seismic records in the Canglangpu Stage, which consists of Jinshanzhai and lower Gouhou and upper Gouhou formations (lying on the western side of the Tanlu Fault Zone). Even if the Gouhou Formation, developing in a lagoon-dry environment, is in the same climate zone as the Dalinzi Formation, and 4 depositional sequences have been identified in the Canglangpu Stage in Northern Jiangsu and Anhui provinces, however, in the same stage in the Liaodong Peninsula, there exist only 3 ones. Therefore, it is not supported by the above mentioned evidence (such as catastrophic events, sequences stratigraphy and lithologic correlation of formations) that the Canglangpu Stage in the Liaodong Peninsula came from northern Jiangsu and Anhui provinces through a long-distance, about hundreds kilometers, left-hand displacement of the Tanlu Fault in the Mesozoic era.
基金Project supported by the National Major Science and Technology Project“Development of Large Oil/Gas Fields and Coalbed Methane”(No.2016ZX05004-005&2016ZX05007-004)the CNPC Major Science and Technology Project“Research and application of key technologies for maintaining gas productivity of 30 billion cubic meters in Southwest Oil and Gas Fields”(No.2016E-06,2016E-0602,2016E-0603&2016E-0604).
文摘The northern Sichuan Basin,spreading in the northern section of the Longmenshan Fault Fold Belt,is characterized by dramatic fluctuations in the surface landforms,development of abdominal faults,and low-quality seismic data,resulting in difficulties in clarifying relevant structures.The key target formation,the Mid-Permian Qixia Fm,is deeply buried with thin reservoirs and high heterogeneity,which brings great challenges to seismic prediction.Under such circumstances,researches have been conducted jointly in terms of seismic data acquisition,processing and interpretation,and finally some relevant seismic survey technologies were developed suitable for surface/underground complex structures.Through surface structural surveys,dynamic deep-well lithologic identification,single-point detector deployment and process optimization,acquisition parameters can be excited.In addition,by using an observation systemwith high-coverage,wide-azimuth and huge-displacement,quality of acquired seismic data can be enhanced dramatically.Seismic imaging technologies for complex structures have been developed to enhance the quality of images for deep formations.These technologies are dominated by microscopic logging-constrained tomography static correction,high-resolution processing with fidelity and amplitude preservation and all-around PSDM in an angular domain.By using high-resolution gravity,magnetic and electric data,details related to geological structures and faults can be identified.In combination with fine seismic data interpretation,structural details and fault features can be verified effectively.Based on forwardmodeling and fine seismic calibration of reservoirs in individualwells,suitable attributes can be identified for predictions related to the distribution of reservoirs.By using all these auxiliary technologies,a large-scale structuralelithologic composite trap with a total area of 1223 km^(2) has been discovered in the NW Sichuan Basin.The Shuangyushi-Jiangyou area as a whole distributes on structural highs.In the areas to the south of Shuangyushi,the Qixia Fm dolomite reservoirs of platform margins are continuously developed.In conclusion,these auxiliary technologies can effectively allow trap identification and thin reservoir prediction in complex structures in the study area.In addition to clarifying the exploration orientation and providing a necessarily technical supports forwell development,these technologies help to accelerate the construction of demonstration projects for the exploration and development of deep marine carbonate formations.
文摘Formed on top of the Gulf of Cadiz, the Al Idrissi mud volcano is the shallowest and largest mud volcano in the El Arraiche mud volcano field of the northwestern Moroccan margin. The development and morphology of mud volcanoes from the El Arraiche mud volcanoes group have been studied at a large scale. However, the time interval related to their formation period still needs to be better understood. In this regard, we interpreted and analyzed the seismic facies from the 2D reflection data of the GEOMARGEN-1 campaign, which took place in 2011. The aim was to identify the seismic sequences and draw the Al Idrissi mud volcano system to determine the formation period of the Al Idriss mud volcano. And as a result, the Al Idrissi mud volcano system is made of both buried and superficial bicone and was identified along with the Upper Tortonian to Messinian-Upper Pliocene facies. As the initial mud volcano extrusive edifice, the buried bicone was formed in the Late-Messinian to Early-Pliocene period. However, the superficial bicone, as the final extrusive edifice, was included in the Late Pliocene. In this case, the timing interval between the buried and superficial bicone is equivalent to the Late-Messinian to Upper-Pliocene period. Therefore, the latter corresponds to the Al Idrissi mud volcano formation period.
