With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural network...With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.展开更多
Mafic and ultramafic intrusions observed in the Archean formations of the Sipilou region exhibit occurrences of polymetallic sulphide. Mapping, petrographic and geochemical studies have defined magnetic facies associa...Mafic and ultramafic intrusions observed in the Archean formations of the Sipilou region exhibit occurrences of polymetallic sulphide. Mapping, petrographic and geochemical studies have defined magnetic facies associated with the various geological units. The results of this work reveal that cupronickel sulphides, olivines and pyroxenes as well as spinels are related to ultrabasic formations where strong magnetic facies prevail. Iron sulphides and magnetite are linked to quartzo-feldspathic and jotunite-enderbite formations, which are characterised by moderate magnetic facies. The latter are thought to be derived from anatexite remobilisation within Archean granulites, which have weak magnetic facies.展开更多
Regarding high drilling costs,an effort should be made to substantially reduce the drilling operation.To achieve this goal,exploration and development stages should be carried out precisely with maximum information ac...Regarding high drilling costs,an effort should be made to substantially reduce the drilling operation.To achieve this goal,exploration and development stages should be carried out precisely with maximum information acquired from the reservoir.The use of multi-attribute matching technology to predict sedimentary system has always been a very important but challenging task.To resolve the challenges,we utilized a quantitative analysis method of seismic attributes based on geological models involving high resolution 3D seismic data for sedimentary facies.We developed a workflow that includes core data,seismic attribute analysis,and well logging to highlight the benefit of understanding the facies distribution in the 3 rd Member of the Lower Jurassic Badaowan Formation,Hongshanzui area,Junggar Basin,China.1)Data preprocessing.2)Cluster analysis.3)RMS attribute based on a normal distribution constrains facies boundary.4)Mapping the sedimentary facies by using MRA(multiple regression analysis)prediction model combined with the lithofacies assemblages and logging facies assemblages.The confident level presented in this research is 0.745,which suggests that the methods and data-mining techniques are practical and efficient,and also be used to map facies in other similar geological settings.展开更多
Most inverse reservoir modeling techniques require many forward simulations, and the posterior models cannot preserve geological features of prior models. This study proposes an iterative static modeling approach that...Most inverse reservoir modeling techniques require many forward simulations, and the posterior models cannot preserve geological features of prior models. This study proposes an iterative static modeling approach that utilizes dynamic data for rejecting an unsuitable training image(TI) among a set of TI candidates and for synthesizing history-matched pseudo-soft data. The proposed method is applied to two cases of channelized reservoirs, which have uncertainty in channel geometry such as direction, amplitude, and width. Distance-based clustering is applied to the initial models in total to select the qualified models efficiently. The mean of the qualified models is employed as a history-matched facies probability map in the next iteration of static models. Also, the most plausible TI is determined among TI candidates by rejecting other TIs during the iteration. The posterior models of the proposed method outperform updated models of ensemble Kalman filter(EnKF) and ensemble smoother(ES) because they describe the true facies connectivity with bimodal distribution and predict oil and water production with a reasonable range of uncertainty. In terms of simulation time, it requires 30 times of forward simulation in history matching, while the EnKF and ES need 9000 times and 200 times, respectively.展开更多
基金funded by the Fundamental Research Project of CNPC Geophysical Key Lab(2022DQ0604-4)the Strategic Cooperation Technology Projects of China National Petroleum Corporation and China University of Petroleum-Beijing(ZLZX 202003)。
文摘With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.
文摘Mafic and ultramafic intrusions observed in the Archean formations of the Sipilou region exhibit occurrences of polymetallic sulphide. Mapping, petrographic and geochemical studies have defined magnetic facies associated with the various geological units. The results of this work reveal that cupronickel sulphides, olivines and pyroxenes as well as spinels are related to ultrabasic formations where strong magnetic facies prevail. Iron sulphides and magnetite are linked to quartzo-feldspathic and jotunite-enderbite formations, which are characterised by moderate magnetic facies. The latter are thought to be derived from anatexite remobilisation within Archean granulites, which have weak magnetic facies.
基金supported by the National Natural Science Foundation of China(41902109)Tianshan Youth Program(2020Q064)+1 种基金National Major Projects(2017ZX05001004)Tianshan Innovation Team Program(2020D14023)。
文摘Regarding high drilling costs,an effort should be made to substantially reduce the drilling operation.To achieve this goal,exploration and development stages should be carried out precisely with maximum information acquired from the reservoir.The use of multi-attribute matching technology to predict sedimentary system has always been a very important but challenging task.To resolve the challenges,we utilized a quantitative analysis method of seismic attributes based on geological models involving high resolution 3D seismic data for sedimentary facies.We developed a workflow that includes core data,seismic attribute analysis,and well logging to highlight the benefit of understanding the facies distribution in the 3 rd Member of the Lower Jurassic Badaowan Formation,Hongshanzui area,Junggar Basin,China.1)Data preprocessing.2)Cluster analysis.3)RMS attribute based on a normal distribution constrains facies boundary.4)Mapping the sedimentary facies by using MRA(multiple regression analysis)prediction model combined with the lithofacies assemblages and logging facies assemblages.The confident level presented in this research is 0.745,which suggests that the methods and data-mining techniques are practical and efficient,and also be used to map facies in other similar geological settings.
基金supported by Korea Institute of Geoscience and Mineral Resources(Project No.GP2017-024)Ministry of Trade and Industry [Project No.NP2017-021(20172510102090)]funded by National Research Foundation of Korea(NRF)Grants(Nos.NRF-2017R1C1B5017767,NRF-2017K2A9A1A01092734)
文摘Most inverse reservoir modeling techniques require many forward simulations, and the posterior models cannot preserve geological features of prior models. This study proposes an iterative static modeling approach that utilizes dynamic data for rejecting an unsuitable training image(TI) among a set of TI candidates and for synthesizing history-matched pseudo-soft data. The proposed method is applied to two cases of channelized reservoirs, which have uncertainty in channel geometry such as direction, amplitude, and width. Distance-based clustering is applied to the initial models in total to select the qualified models efficiently. The mean of the qualified models is employed as a history-matched facies probability map in the next iteration of static models. Also, the most plausible TI is determined among TI candidates by rejecting other TIs during the iteration. The posterior models of the proposed method outperform updated models of ensemble Kalman filter(EnKF) and ensemble smoother(ES) because they describe the true facies connectivity with bimodal distribution and predict oil and water production with a reasonable range of uncertainty. In terms of simulation time, it requires 30 times of forward simulation in history matching, while the EnKF and ES need 9000 times and 200 times, respectively.
