基于深度神经网络的地震强反射剥离方法

doi:10.6038/cjg2021O0165

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (11743 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In reservoir prediction, it is often encountered that the weak reflection signal is submerged in the strong reflection, which is disadvantageous to accurately identify and describe reservoir structure. In this study, we propose a method to remove the strong seismic reflection using the deep neural networks to help detect weak reflection signals of reservoirs. In the framework of the convolution model, the proposed method first decomposes the strong reflection prediction problem into two optimization sub-problems: seismic wavelet prediction and strong reflection prediction, which are solved by AIDNN and U-Net, respectively. The mapping relationship between seismic data and strong reflection can be established directly through training, which avoids the artificial empirical parameter adjustment, and is fast in the calculation and suitable for massive seismic data processing. Tests on synthetic and real data show that the proposed method can predict and remove strong seismic reflection with good amplitude preservation and fidelity. Base on this approach we predict the distribution of sand bodies in reservoirs and achieve good results.

Key words： Deep learning Strong seismic reflection Reservoir prediction

Received: 05 May 2020

PACS:

P631

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	TIAN YaJun
	GAO JingHuai
	WANG DaXing
	CHEN DaoYu

URL:

http://www.geophy.cn//EN/10.6038/cjg2021O0165 OR http://www.geophy.cn//EN/Y2021/V64/I8/2780

Adler J, Öktem O. 2017. Solving ill-posed inverse problems using iterative deep neural networks. Inverse Problem, 33(2):1-24.
Cai W J, Zhang H, Wang Y, et al. 2019. Application of seismic wavelet decomposition and reconstruction technology in reservoir prediction of Fuyu reservoir in Chagan area. Progress in Geophysics (in Chinese), 34(4):1381-1390, doi:10.6038/pg2019CC0152.
Chen D Y, Gao J H, Hou Y P, et al. 2019. High resolution inversion of seismic wavelet and reflectivity using iterative deep neural networks.//89th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 2538-2542.
Chen R J, Tong S Y, Liu H S, et al. 2014. Reservoir prediction technology based on wavelet decomposition and reconstruction. Marine Geology Frontiers (in Chinese), 30(1):55-61.
Das V, Pollack A, Wollner U, et al. 2019. Convolutional neural network for seismic impedance inversion. Geophysics, 84(6):R869-R880.
Di H B, Alregib G. 2020. A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels. Geophysical Prospecting, 68(2):521-535.
Du Y S, Fan T T, Zhang J H, et al. 2016. Seismic description technology of deep reservoirs above coal seams:a case study of Xishanyao formation in Yongjin Oilfield. Progress in Geophysics (in Chinese), 31(4):1562-1568, doi:10.6038/pg20160420.
Duan Y T, Zheng X D, Hu L L, et al. 2019. Fault detection based on 3D semi-dense convolutional neural network. Progress in Geophysics (in Chinese), 34(6):2256-2261, doi:10.6038/pg2019CC0367.
Fu C, Lin N T, Zhang D, et al. 2018. Prediction of reservoirs using multi-component seismic data and the deep learning method. Chinese Journal of Geophysics (in Chinese), 61(1):293-303, doi:10.6038/cjg2018L0193.
Gao J H, Liu N H, Lv Q, et al. 2018. Characterization of thin interbedded reservoir using synchrosqueezing transform. Geophysical Prospecting for Petroleum (in Chinese), 57(4):512-521.
Gao J H, Wan T, Chen W C, et al. 2006. Three parameter wavelet and its applications to seismic data processing. Chinese Journal of Geophysics (in Chinese), 49(6):1802-1812.
Guo J, Wang Y H. 2004. Recovery of a target reflection underneath coal seams. Journal of Geophysics and Engineering, 1(1):46-50.
He F, Weng B, Han G, et al. 2019. A seismic constraint-based technology for elimination of strong coal seam reflection via well-control and matching pursuit. China Offshore Oil and Gas (in Chinese), 31(1):61-66.
Hu L L, Zheng X D, Duan Y T, et al. 2019. First-arrival picking with a U-net convolutional network. Geophysics, 84(6):U45-U57.
Kim Y, Nakata N. 2018. Geophysical inversion versus machine learning in inverse problems. The Leading Edge, 37(12):894-901.
Li H S, Yang W Y, Tian J, et al. 2014. Coal seam strong reflection separation with matchingpursuit. Oil Geophysical Prospecting (in Chinese), 49(5):866-870.
Li W W, Gong R B, Zhou X G, et al. 2021. UNet++:a deep-neural-network-based seismic arrival time picking method. Progress in Geophysics (in Chinese), 36(1):187-194, doi:10.6038/pg2021EE0152.
Lin N T, Zhang D, Zhang K, et al. 2018. Predicting distribution of hydrocarbon reservoirs with seismic data based on learning of the small-sample convolution neural network. Chinese Journal of Geophysics (in Chinese), 61(10):4110-4125, doi:10.6038/cjg2018J0775.
Liu N H, Gao J H, Zhang Z S, et al. 2017. High-resolution characterization of geologic structures using the synchrosqueezing transform. Interpretation, 5(1):T75-T85.
Liu N H, Gao J H, Zhang B, et al. 2019. Self-adaptive generalized S-transform and its application in seismic time-frequency analysis. IEEE Transactions on Geoscience and Remote Sensing, 57(10):7849-7859.
Liu N H, He T, Tian Y J, et al. 2020. Common-azimuth seismic data fault analysis using residual UNet. Interpretation, 8(3):SM25-SM37.
Lou Y H, Zhang B, Lin T F, et al. 2020. Seismic horizon picking by integrating reflector dip and instantaneous phase attributes. Geophysics, 85(2):O37-O45.
Lu W K, Li F Y. 2013. Seismic spectral decomposition using deconvolutive short-time Fourier transform spectrogram. Geophysics, 78(2):V43-V51.
Qin X F, Li W. 2014. Research of Identification and trimming of Coal-Bed interference in daniudi gas field. Journal of Jilin University (Earth Science Edition) (in Chinese), 44(3):1048-1054.
Qu X F, Wen D S, Zhang L, et al. 2017. Accumulation process of ultra-low permeability reservoirs in Yanchang Formation ordos basin:a case from Gufengzhuang-Mahuangshan area. Acta Sedimentologica Sinica (in Chinese), 35(2):383-392.
Robinson E A. 1985. Seismic time-invariant convolutional model. Geophysics, 50(12):2742-2751.
Ronneberger O, Fischer P, Brox T. 2015. U-Net:convolutional networks for biomedical image segmentation.//Navab N, Hornegger J, Wells W, et al eds. International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 234-241.
She G, Zhou X Y, Wang J B. 2013. Prediction of sand reservoir with multi-wavelet seismic trace decomposition and reconstruction. Journal of Southwest Petroleum University (Science & Technology Edition)(in Chinese), 35(1):19-27.
Shi Y Z, Wu X M, Fomel S. 2019. Saltseg:Automatic 3D salt segmentation using a deep convolutional neural network. Interpretation, 7(3):SE113-SE122.
Tian Y J, Gao J H, Liu N H, et al. 2020. Construction of optimal basic wavelet via AIDNN and its application in seismic data analysis. IEEE Geoscience and Remote Sensing Letters, 1-5.
Wang B J, Zhang Y C, Wang D X, et al. 2012. Predicting and detecting of the thin sand bodies by general transform in coal-bearing strata. Progress in Geophysics (in Chinese), 27(3):1219-1226, doi:10.6038/j.issn.1004-2903.2012.03.049.
Wang D X, Wang Y G, Zhao Y H, et al. 2016a. A strong seismic reflection amplitude suppressing method applied in the Ordos Basin.//86th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 389-391.
Wang L L, Zhao Q, Gao J H, et al. 2016b. Seismic sparse-spike deconvolution via Toeplitz-sparse matrix factorization. Geophysics, 81(3):V169-V182.
Wang Y H. 2010. Multichannel matching pursuit for seismic trace decomposition. Geophysics, 75(4):V61-V66.
Wu B Y, Meng D L, Wang L L, et al. 2020. Seismic impedance inversion using fully convolutional residual network and transfer learning. IEEE Geoscience and Remote Sensing Letters, 17(12):2140-2144.
Wu H, Zhang B, Li F Y, et al. 2019a. Semiautomatic first-arrival picking of microseismic events by using the pixel-wise convolutional image segmentation method. Geophysics, 84(3):V143-V155.
Wu H, Zhang B, Lin T F, et al. 2019b. Semiautomated seismic horizon interpretation using the encoder-decoder convolutional neural network. Geophysics, 84(6):B403-B417.
Wu X M, Liang L M, Shi Y Z, et al. 2019c. FaultSeg3D:Using synthetic data sets to train an end-to-end convolutional neural network for 3d seismic fault segmentation. Geophysics, 84(3):IM35-IM45.
Xi X, Huang J Q. 2018. Deep learning inversion imaging method for scattered wavefield. Progress in Geophysics (in Chinese), 33(6):2483-2489, doi:10.6038/pg2018BB0531.
Xi X, Huang J Q. 2020. Location and imaging of scatterers in seismic migration profiles based on convolution neural network. Chinese Journal of Geophysics (in Chinese), 63(2):687-714, doi:10.6038/cjg2020M0490.
Xu L, Wu X H, Zhang M Z, et al. 2019. Strong reflection identification and separation based on the local-frequency-constrained dynamic matching pursuit. Oil Geophysical Prospecting (in Chinese), 54(3):587-593.
Yu Z Y, Chu R S, Sheng M H. 2018. Pick onset time of P and S phase by deep neural network. Chinese Journal of Geophysics (in Chinese), 61(12):4873-4886, doi:10.6038/cjg2018L0725.
Zhang W, Shi Y. 2019. Imaging conditions for elastic reverse time migration. Geophysics, 84(2):S95-S111.
Zhao M, Chen S, Yuen D. 2019. Waveform classification and seismic recognition by convolution neural network. Chinese Journal of Geophysics (in Chinese), 62(1):374-382, doi:10.6038/cjg2019M0151.
Zhao S, Li Z D, Xu H M, et al. 2007. Using multiple wavelet decomposition technique to detect the sandstone reservoir with coal layer. Natural Gas Industry (in Chinese), 27(9):44-47.
Zhu T Y, Harris J M. 2014. Modeling acoustic wave propagation in heterogeneous attenuating media using decoupled fractional Laplacians. Geophysics, 79(3):T105-T116.
附中文参考文献
蔡文杰, 张宏, 汪勇等. 2019. 地震子波分解与重构技术在查干泡地区扶余油层储层预测中的应用研究. 地球物理学进展, 34(4): 1381-1390, doi:10.6038/pg2019CC0152.
陈人杰, 童思友, 刘怀山等. 2014. 基于子波分解与重构的储层预测技术. 海洋地质前沿, 30(1):55-61.
杜玉山, 范腾腾, 张军华等. 2016. 深层煤上储层地震描述技术——以永进油田西山窑组为例. 地球物理学进展, 31(4):1562-1568, doi:10.6038/pg20160420.
段艳廷, 郑晓东, 胡莲莲等. 2019. 基于3D半密度卷积神经网络的断裂检测. 地球物理学进展, 34(6):2256-2261, doi:10.6038/pg2019CC0367.
付超, 林年添, 张栋等. 2018. 多波地震深度学习的油气储层分布预测案例. 地球物理学报, 61(1):293-303, doi:10.6038/cjg2018L0193.
高静怀, 刘乃豪, 吕奇等. 2018. 薄互层型油气储层同步挤压变换域分析方法. 石油物探, 57(4):512-521.
高静怀, 万涛, 陈文超等. 2006. 三参数小波及其在地震资料分析中的应用. 地球物理学报, 49(6):1802-1812.
何峰, 翁斌, 韩刚等. 2019. 一种基于地震约束的井控匹配追踪煤层强反射消除技术. 中国海上油气, 31(1):61-66.
李海山, 杨午阳, 田军等. 2014. 匹配追踪煤层强反射分离方法. 石油地球物理勘探, 49(5):866-870.
李薇薇, 龚仁彬, 周相广等. 2021. 基于深度学习UNet++网络的初至波拾取方法. 地球物理学进展, 36(1):187-194, doi:10.6038/pg2021EE0152.
林年添, 张栋, 张凯等. 2018. 地震油气储层的小样本卷积神经网络学习与预测. 地球物理学报, 61(10):4110-4125, doi:10.6038/cjg2018J0775.
秦雪霏, 李巍. 2014. 大牛地气田煤系地层去煤影响储层预测技术. 吉林大学学报(地球科学版), 44(3):1048-1054.
屈雪峰, 温德顺, 张龙等. 2017. 鄂尔多斯盆地延长组超低渗透油藏形成过程分析——以古峰庄-麻黄山地区为例. 沉积学报, 35(2):383-392.
佘刚, 周小鹰, 王箭波. 2013. 多子波分解与重构法砂岩储层预测. 西南石油大学学报(自然科学版), 35(1):19-27.
王宝江, 张永常, 王大兴等. 2012. 广义S变换用于含煤地层薄砂体预测研究. 地球物理学进展, 27(3):1219-1226, doi:10.6038/j.issn.1004-2903.2012.03.049.
奚先, 黄江清. 2018. 散射波场的深度学习反演成像法. 地球物理学进展, 33(6):2483-2489, doi:10.6038/pg2018BB0531.
奚先, 黄江清. 2020. 基于卷积神经网络的地震偏移剖面中散射体的定位和成像. 地球物理学报, 63(2):687-714, doi:10.6038/cjg2020M0490.
许璐, 吴笑荷, 张明振等. 2019. 基于局部频率约束的动态匹配追踪强反射识别与分离方法. 石油地球物理勘探, 54(3):587-593.
于子叶, 储日升, 盛敏汉. 2018. 深度神经网络拾取地震P和S波到时. 地球物理学报, 61(12):4873-4886, doi:10.6038/cjg2018L0725.
赵明, 陈石, Yuen D. 2019. 基于深度学习卷积神经网络的地震波形自动分类与识别. 地球物理学报, 62(1):374-382, doi:10.6038/cjg2019M0151.
赵爽, 李仲东, 许红梅等. 2007. 多子波分解技术检测含煤砂岩储层. 天然气工业, 27(9):44-47.