陆相页岩储层薄片超分辨率增强方法

doi:10.11743/ogg20210517

摘要/Abstract

摘要：

近年来页岩油气的勘探与开发在全世界领域都取得了很大进展。然而在储层的矿物组分以及孔喉分布等微观物性研究中，经常受困于页岩储层微观尺度的限制，使得传统岩石薄片研究难以满足页岩储层精细化分析的需要。为了能够从原始页岩薄片图像中挖掘出更多储层微观特征，解决传统薄片精细图像在分辨率方面存在的限制与不足的问题，通过引入超分辨率增强技术来提高薄片图像对页岩储层微观特性的描述能力。针对页岩储层特点开发了一套基于生成对抗网络的超分辨率模型，建立了对应的薄片图像损失函数。最后以鄂尔多斯盆地延长组陆相页岩气储层的实际资料作为测试对象，进一步定性、定量地验证并确认了该方法的可用性、准确性以及可靠性。

关键词: 微观物性, 超分辨率技术, 数据增强技术, 岩石薄片, 页岩储层, 鄂尔多斯盆地

Abstract:

Despite a great progress made in the exploration and development of shale gas and oil in recent years, the study on the pores, organic matter and mineral composition of shale reservoirs at a microscopic scale is still a challenge with thin section analysis for conventional reservoirs. In order to solve this problem, this study introduces a super-resolution technology to improve thin section image quality for revealing micro-characteristics of shale reservoirs. A set of super-resolution models are established based on generative adversarial networks and corresponding content loss functions are also set up for thin-section images. Application of the technology to the processing of actual data from lacustrine shale gas reservoirs in the Yanchang Formation in Ordos Basin has yielded positive results, demonstrating quantitatively and qualitatively its applicability, accuracy and reliability for unconventional reservoir assessment.

Key words: microscopic physical property, super-resolution, data enhancement, thin section, shale reservoir, Ordos Basin

中图分类号:

TE135

郭超,赵谦平,刘刚,等. 陆相页岩储层薄片超分辨率增强方法[J]. 石油与天然气地质, 2021, 42(5): 1202-1209. doi: 10.11743/ogg20210517 Chao Guo,Qianping Zhao,Gang Liu,et al. Super-resolution imaging of thin sections for lacustrine shale reservoirs[J]. Oil & Gas Geology, 2021, 42(5): 1202-1209. doi: 10.11743/ogg20210517

图/表 10

图1

图2

图3

图4

表1

图5

图6

图7

表2

图8

参考文献 19

1	王卫星, 谭嘉玉. 基于分数阶微分和形态学多级合成的岩石节理裂隙图像分割[J]. 计算机应用, 2010, 30 (4): 929- 931.
	Wang Weixing , Tan Jiayu . Rock joint image segmentation based on fractional differential and multi-grade combination in mathematical morphology[J]. Journal of Computer Applications, 2010, 30 (4): 929- 931.
2	Yang X , Zhang G , Lu J , et al. A kernel fuzzy c-means clustering-based fuzzy support vector machine algorithm for classification problems with outliers or noises[J]. IEEE Transactions on Fuzzy Systems, 2011, 19 (1): 105- 115. doi: 10.1109/TFUZZ.2010.2087382
3	Zhang Y , Fu L Y , Zhang L , et al. Finite difference modeling of ultrasonic propagation (coda waves) in digital porous cores with un-split convolutional PML and rotated staggered grid[J]. Journal of Applied Geophysics, 2014, 104 (5): 75- 89.
4	陈本廷, 周骛, 蔡小舒, 等. 基于K-均值聚类的岩芯偏振显微图像粒径分析[J]. 上海理工大学学报, 2016, 38 (4): 341- 345, 351.
	Chen Benting , Zhou Wu , Cai Xiaoshu , et al. New method for the segmentation of polarizing microscope image of rock core based on K-means cluster algorithm[J]. University of Shanghai for Science and Technology, 2016, 38 (4): 341- 345, 351.
5	叶润青, 牛瑞卿, 张良培. 基于多尺度分割的岩石图像矿物特征提取及分析[J]. 吉林大学学报(地球科学版), 2011, 41 (4): 1253- 1261.
	Ye Runqing , Niu Ruiqing , Zhang Liangpei . Mineral features extraction and analysis based om multiresolution segmentation of petrographic images[J]. Journal of Jilin University(Earth Science Edition), 2011, 41 (4): 1253- 1261.
6	姚军, 赵秀才, 衣艳静, 等. 储层岩石微观结构性质的分析方法[J]. 中国石油大学学报(自然科学版), 2007, 31 (1): 80- 86.
	Yao Jun , Zhao Xiucai , Yi Yanjing , et al. Analysis methods for reservoir rock's microstructure[J]. Journal of China University of Petroleum, 2007, 31 (1): 80- 86.
7	Li Z , Teng Q , He X , et al. Sparse representation-based volumetric super-resolution algorithm for 3D CT images of reservoir rocks[J]. Journal of Applied Geophysics, 2017, 144, 69- 77. doi: 10.1016/j.jappgeo.2017.04.013
8	Wang Y D, Armstrong, Mostaghimi P. Super resolution convolutional Neural Network Models for enhancing resolution of rock Micro-CT Images[EB/OL]. 2019. arXiv: 1904.07470[cs. CV]. https://arxiv.org/abs/1904.07470.
9	Ye Liu , C Guo , J Cao , et al. A new resolution enhancement method for sandstone thin-section images using perceptual GAN[J]. Journal of Petroleum Science and Engineering, 2020, 195 (2): 107921.
10	Chao Dong , Chen Change Loy , Kaiming He , et al. Image super-resolution using deep convolutional networks[J]. IEEE Trans Pattern Anal Mach Intell, 2016, 38 (2): 295- 307. doi: 10.1109/TPAMI.2015.2439281
11	Chao D, Chen C L, Tang X, et al. Accelerating the super-resolution convolutional neural network[C]//European Conference on Computer Vision, Springer, Amsterdam, 2016.
12	Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, 2016, 1646-1654.
13	Yu J, Fan Y, Yang J, et al. Wide activation for efficient and accurate image super-resolution[EB/OL]. 2018 arXiv: 1808.08718v1[cs. CV]. https://arxiv.org/abs/1808.08718v1.
14	Christian Ledig, Theis L, Husz'ar F, et al. Photo-realistic single image super resolution using a generative adversarial network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2017.
15	Guo Y, Chen J, Wang J, et al. Closed-loop Matters: Dual regression networks for single image super-resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020.
16	Zhou Yuemei, Wu Gaochang, Fu Ying, et al. Cross-MPI: Cross-scale stereo for image super-resolution using multiplane images[EB/OL]. 2011. arXiv: 2011.14631[cs. CV]. https://arxiv.org/abs/2011.14631
17	Jolicoeur Martineau A. The relativistic discriminator: a key element missing from standard GAN[EB/OL]. 2018 arXiv: 1807.00734[cs. LG]. https://arxiv.org/abs/1807.00734.
18	Zhang L , Zhang L , Mou X , et al. FSIM: A feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20 (8): 2378- 2386.
19	Xue W , Zhang L , Mou X , et al. Gradient magnitude similarity deviation: A highly efficient perceptual image quality index[J]. IEEE Transactions on Image Processing, 2014, 23 (2): 684- 695.

Batch size	训练时间/min	FSIM均值	FSIM方差	GMSD均值	GMSD方差
5	496	0.723 8	0.002 234	0.194 2	0.001 365
10	429	0.725 7	0.002 296	0.192 8	0.001 408
20	436	0.726 3	0.002 377	0.192 9	0.001 396
30	436	0.723 8	0.002 261	0.194 6	0.001 353

模拟	数值	PNSR	SSIM	IMMSE	FSIM	GMSD	NIQE
Bicubic	期望值	19.912 1	0.879 040	694.784 100	0.880 87	0.240 49	6.926 00
Bicubic	方差	1.384 1	0.028 143	197.633 300	0.174 93	0.172 10	0.261 74
SR	期望值	31.905 0	0.982 990	55.632 820	0.999 10	0.044 996	5.434 90
SR	方差	2.875 9	0.011 865	5.632 482	0.006 12	0.021 924	0.666 08

[1]	刘池洋, 王建强, 张东东, 赵红格, 赵俊峰, 黄雷, 王文青, 秦阳. 鄂尔多斯盆地油气资源丰富的成因与赋存-成藏特点[J]. 石油与天然气地质, 2021, 42(5): 1011-1029.
[2]	任战利, 祁凯, 李进步, 霍小菊, 崔军平, 杨鹏, 王琨, 陈占军, 杨桂林. 鄂尔多斯盆地热动力演化史及其对油气成藏与富集的控制作用[J]. 石油与天然气地质, 2021, 42(5): 1030-1042.
[3]	李相博, 王宏波, 黄军平, 张才利, 张艳, 王雅婷, 张雷, 王菁, 刘化清. 鄂尔多斯盆地怀远运动不整合面特征及油气勘探意义[J]. 石油与天然气地质, 2021, 42(5): 1043-1055.
[4]	何发岐, 齐荣, 王付斌, 邓杰, 成立, 胡天乐. 鄂尔多斯盆地南部三叠系延长组沟谷体系构造成因[J]. 石油与天然气地质, 2021, 42(5): 1056-1062.
[5]	周新平, 何青, 刘江艳, 李士祥, 杨田. 鄂尔多斯盆地三叠系延长组7段深水碎屑流沉积特征及成因[J]. 石油与天然气地质, 2021, 42(5): 1063-1077.
[6]	范柏江, 晋月, 师良, 李亚婷, 陈玮常. 鄂尔多斯盆地中部三叠系延长组7段湖相页岩油勘探潜力[J]. 石油与天然气地质, 2021, 42(5): 1078-1088.
[7]	张亚雄. 鄂尔多斯盆地中部地区三叠系延长组7段暗色泥岩烃源岩特征[J]. 石油与天然气地质, 2021, 42(5): 1089-1097.
[8]	陈朝兵, 赵振宇, 付玲, 高建荣, 宋微, 陈新晶. 鄂尔多斯盆地华庆地区延长组6段深水致密砂岩填隙物特征及对储层发育的影响[J]. 石油与天然气地质, 2021, 42(5): 1098-1111.
[9]	时保宏, 秦馨雨, 张才利, 刘文, 刘刚, 史婵媛, 张雷, 勇子树. 鄂尔多斯盆地姬塬地区延长组6段油藏差异成藏因素[J]. 石油与天然气地质, 2021, 42(5): 1112-1123.
[10]	刘玲, 王琳霖, 吴疆, 陈霞, 杨佳奇. 鄂尔多斯盆地南部彬长区块上石盒子组7段储层识别与预测[J]. 石油与天然气地质, 2021, 42(5): 1124-1135.
[11]	李进步, 王继平, 王龙, 付斌, 夏辉, 李志潇. 古地貌恢复及其对三角洲前缘沉积砂体的控制作用——以鄂尔多斯盆地庆阳气田二叠系山西组1³亚段为例[J]. 石油与天然气地质, 2021, 42(5): 1136-1145, 1158.
[12]	刘畅, 张道旻, 李超, 路媛媛, 于姗姗, 郭明强. 鄂尔多斯盆地临兴区块上古生界致密砂岩气藏成藏条件及主控因素[J]. 石油与天然气地质, 2021, 42(5): 1146-1158.
[13]	张军涛, 金晓辉, 谷宁, 卞昌蓉, 杨佳奇, 何治亮. 鄂尔多斯盆地北部地区马家沟组岩溶储层的差异性和发育模式[J]. 石油与天然气地质, 2021, 42(5): 1159-1168, 1242.
[14]	张东东, 刘文汇, 王晓锋, 罗厚勇, 王庆涛, 李忆宁, 李风娇. 深层油气藏成因类型及其特征[J]. 石油与天然气地质, 2021, 42(5): 1169-1180.
[15]	焦方正. 鄂尔多斯盆地页岩油缝网波及研究及其在体积开发中的应用[J]. 石油与天然气地质, 2021, 42(5): 1181-1188.