Characterization of thin sand reservoirs based on a multi-layer perceptron deep neural network
DU Xin1,2, FAN Ting'en1,2, DONG Jianhua1,2, NIE Yan1,2, FAN Hongjun1,2, GUO Boyang3
1. State Key Laboratory of Offshore Oil Exploitation, Beijing 100020, China; 2. CNOOC Research Institute Ltd., Beijing 100020, China; 3. School of Energy Resources, China University of Geosciences(Beijing), Beijing 100083, China
Abstract:haracterization of thin reservoirs is significantly important in seismic exploration.Compared with the method based on seismic inversion,reservoir prediction based on seismic multiple-attribute regression (MAR) can enhance resolution and alleviate the over modeling issue,but the poor ability of generalizing the trained model in MAR frequently causes the instability of the estimated result between wells.A multi-layer perceptron (MLP)-based MAR method is proposed for characterizing thin sandstone-shale reservoirs.This method takes seismic data (background information),90°-phase data (the framework of reservoir structure) and discontinuious reservor boundary (which is a self-deve-loped seismic attribute measuring the discontinuity of reservoir) as inputs,and the gamma-ray (GA) logs of wells as expected outputs,uses the MLP deep neural network to train the model for estimating the GA data,and finally characterizes thin re-servoirs based on the close lithologic relationship between sandstone and shale.Applications to field data from an offshore oilfield A show that the correlated coefficient between the estimated and the true GA of wells has reached 0.855 in a training set with 10 wells,and 0.864 in a prediction set with 2 wells.They are significantly better than the results from the traditional MAR method.Based on the GA data,we interpreted 6 top surfaces for finely describing the reservoir in a target area, and extracted the reservoir-sensitive seismic attribute (Sum of Negative Amplitude,SNA) along the horizon to assess the association between the SNA and the sum thickness (ST) of the reservoir drilled in 156 wells.The SNA based on GA data shows relatively high association with the ST.The correlation coefficient between the SNA based on GA estimation and the ST is about 38% higher than that between the SNA based on the 90°-phase data and the ST,which further confirmed the feasibility of the proposed MLP-based MAR method.
杜昕, 范廷恩, 董建华, 聂妍, 范洪军, 郭泊洋. 基于多层感知机网络的薄储层预测[J]. 石油地球物理勘探, 2020, 55(6): 1178-1187.
DU Xin, FAN Ting'en, DONG Jianhua, NIE Yan, FAN Hongjun, GUO Boyang. Characterization of thin sand reservoirs based on a multi-layer perceptron deep neural network. Oil Geophysical Prospecting, 2020, 55(6): 1178-1187.
王延光,李皓,李国发,等.一种用于薄层和薄互层砂体厚度估算的复合地震属性[J].石油地球物理勘探,2020,55(1):153-160.WANG Yanguang,LI Hao,LI Guofa,et al.A composite seismic attribute used to estimate the sand thickness for thin bed and thin interbed[J].Oil Geophysical Prospecting,2020,55(1):153-160.
[2]
徐丽英,徐鸣洁,陈振岩.利用谱分解技术进行薄储层预测[J].石油地球物理勘探,2006,41(3):299-302.XU Liying,XU Mingjie,CHEN Zhenyan.Using spectrum decomposition technique for prediction of thin reservoir[J].Oil Geophysical Prospecting,2006,41(3):299-302.
[3]
孙学栋,赵建儒,白军,等.谱分解技术在营尔凹陷长沙岭地区薄储层预测中的应用[J].石油地球物理勘探,2011,46(增刊1):72-75.SUN Xuedong,ZHAO Jianru,BAI Jun,et al.Spectrum decomposition application in thin-reservoir prediction in Changshaling belt,Yinger Depression[J].Oil Geophysical Prospecting,2011,46(S1):72-75.
[4]
Du X,Li G,Zhang M,et al.Multichannel band-controlled deconvolution based on a data-driven structural regularization[J].Geophysics,2018,83(5):R401-R411.
[5]
王香文,刘红,滕彬彬,等.地质统计学反演技术在薄储层预测中的应用[J].石油与天然气地质,2012,33(5):730-735.WANG Xiangwen,LIU Hong,TENG Binbin,et al.Application of geostatistical in inversion to thin reservoir prediction[J].Oil & Gas Geology,2012,33(5):730-735.
[6]
张义,尹艳树,秦志勇.地质统计学反演在薄砂体储层预测中的应用[J].断块油气田,2015,22(5):565-569.ZHANG Yi,YIN Yanshu,QIN Zhiyong.Application of geostatistical inversion in thin sandstone reservoir prediction[J].Fault-Block Oil & Gas Field,2015,22(5):565-569.
[7]
沈洪涛,郭乃川,秦童,等.地质统计学反演技术在超薄储层预测中的应用[J].地球物理学进展,2017,32(1):248-253.SHEN Hongtao,GUO Naichuan,QIN Tong,et al.Application of geostatistical inversion for super thin reservoir prediction[J].Progress in Geophysics,2017,32(1):248-253.
[8]
高君,毕建军,赵海山,等.地震波形指示反演薄储层预测技术及其应用[J].地球物理学进展,2017,32(1):142-145.GAO Jun,BI Jianjun,ZHAO Haishan,et al.Seismic waveform inversion technology and application of thinner reservoir prediction[J].Progress in Geophy-sics,2017,32(1):142-145.
[9]
蔡冬梅,赵弟江,彭靖松,等.优质烃源岩识别及其多属性反演技术定量评价——以渤海海域辽东南洼陷为例[J].石油地球物理勘探,2018,53(2):330-338.CAI Dongmei,ZHAO Dijiang,PENG Jinsong,et al.High-quality hydrocarbon source rock identification and quantitative evaluation with multi-attribute inversion:A case study of Liaodong south sub-sag,Bohai Bay Basin[J].Oil Geophysical Prospecting,2018,53(2):330-338.
[10]
张显文,曹树春,聂妍,等.地震多属性孔隙因子参数反演及其在伊拉克M油田碳酸盐岩储层预测中的应用[J].石油物探,2018,57(5):756-763.ZHANG Xianwen,CAO Shuchun,NIE Yan,et al.Seismic multi-attribute inversion for pore-sensitive factor and its application in carbonate reservoir prediction of M oilfield in Iraq[J].Geophysical Prospecting for Petroleum,2018,57(5):756-763.
[11]
张晶玉,范廷恩,王宗俊,等.多属性储层参数反演方法在M油田中的应用[J].油气藏评价与开发,2019,9(1):8-14.ZHANG Jingyu,FAN Ting'en,WANG Zongjun,et al.Application of reservoir parameters inversion method by using multi-attributes in M oilfield[J].Reservoir Evaluation and Development,2019,9(1):8-14.
[12]
Krizhevsky A,Sutskever I,and Hinton G E.Imagenet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25(2):1097-1105.
[13]
Zeiler M D and Fergus R.Visualizing and understanding convolutional networks[C].European Conference on Computer Vision,2014,818-833.
[14]
Girshick R,Donahue J,Darrell T,et al.Rich feature hie-rarchies for accurate object detection and semantic segmentation[C].Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition,2014,580-587.
[15]
Ren S,He K,Girshick R,et al.Faster R-CNN:to-wards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[16]
Ronneberger O,Fischer P,and Brox T.U-net:Con-volutional networks for biomedical image segmentation[C].International Conference on Medical Image Computing and Computer-Assisted Intervention,2012,234-241.
[17]
Badrinarayanan V,Kendall A,and Cipolla R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[18]
Yuan S,Liu J,and Wang S X.Seismic waveform classification and first-break picking using convolution neural networks[J].IEEE Geoscience & Remote Sensing Letters,2018,15(2):272-276.
[19]
韩卫雪,周亚同,池越.基于深度学习卷积神经网络的地震数据随机噪声去除[J].石油物探,2018,57(6):862-869.HAN Weixue,ZHOU Yatong,CHI Yue.Deep lear-ning convolutional neural networks for random noise attenuation in seismic data[J].Geophysical Prospecting for Petroleum,2018,57(6):862-869.
[20]
Deng L,Yuan S Y,Wang S X.Sparse Bayesian lear-ning-based seismic denoise by using physical wavelet as basis functions[J].IEEE Geoscience & Remote Sensing Letters,2017,14(11):1993-1997.
[21]
Wu X M,Shi Y Z,Fomel S,et al.Fault Net 3D:predicting fault probabilities,strikes,and dips with a single convolutional neural network[J].IEEE Transactions on Geoscience Remote Sensing,2019.57(11):9138-9155.
[22]
Shi Y Z,Wu X M,Fomel S.Saltseg:automatic 3D salt segmentation using a deep convolutional neural network[J].Interpretation,2019,7(3):SE113-SE122.
[23]
Yang F,Ma J.Deep-learning inversion:a next-gene-ration seismic velocity model building method[J].Geophysics,2019,84(4):R583-R599.
[24]
Li S C,Liu B,Ren Y X,et al.Deep learning inversion of seismic data[DB/OL].arXiv:1901.07733,2019.doi:10.1109/TGRS.201902953473.
[25]
刘力辉,陆蓉,杨文魁.基于深度学习的地震岩相反演方法[J].石油物探,2019,58(1):123-129.LIU Lihui,LU Rong,YANG Wenkui.Seismic lithofacies inversion based on deep learning[J].Geophysical Prospecting for Petroleum,2019,58(1):123-129.
[26]
Zeng H,Backus M M.Interpretive advantages of 90°-phase wavelets,Part 1:Modeling[J].Geophysics,2005,70(3):C5-C15.
[27]
Zeng H,Backus M M.Interpretive advantages of 90°-phase wavelets,Part 2:Seismic applications[J].Geophysics,2005,70(3):C17-C24.
[28]
范廷恩.点坝砂体储层内部不连续界线类型及预测方法研究[D].四川成都:西南石油大学,2016.FAN Ting'en.The Discontinuous Boundary of Thin Fluvial Reservoir and Its Prediction[D].Southwest Petroleum University,Chengdu,Sichuan,2016.