Identification and comparison of organic matter-hosted pores in shale by SEM image analysis—a deep learning-based approach

doi:10.13745/j.esf.sf.2022.5.45

Abstract

Abstract:

The introduction of deep learning models can greatly improve the efficiency of geological image analysis and thus increase the level of quantitative research. As an example, the Ar-ion polishing scanning electron microscope (SEM) images of shale samples from the Lower Cambrian Niutitang Formation in western Hubei, Upper Yangtze were analyzed using three deep learning models, Mask-RCNN, FCN and U-Net, to identify the minerals, organic matter and pores (basic tasks) after image pretreatment (binarization, etc.) We compared the running time and identification accuracy between the three models, and discussed the model applicability and model differences in geological image recognition and processing. In addition, we compared the best performance model, U-Net model, with the general image processing softwares (JmicroVision, Adobe Photoshop, etc.) in pore recognition. The FCN model performed well in the basic tasks, but could not distinguish the mineral components and fractures with similar colors; whereas the Mask-RCNN model could identify the main minerals with strong segmentation but not low-resolution pores and fractures. In comparison, the U-Net model greatly improved the efficiency of shale geological image recognition with an 300-fold increase in image recognition speed over the general image processing softwares. Applying the U-Net model, the pore structural types of the Niutitang shale of the study area can be divided into circular intra-granular mineral pores, random irregular inter-granular mineral pores, angular organic matter-hosted pores and dense organic matter-hosted micropores. The pore structural parameters obtained based on SEM image analysis of large enough sample size may be used for reservoir classification and evaluation. The example provided in this study may help improving the efficiency of geological image research as well as promoting artificial intelligence application in oil and gas research.

Key words: shale, pyrite, fracture, organic matter-hosed pore, U-Net, deep leaning, scanning electron microscope image

CLC Number:

P572
P234.4

CHEN Zongming, TANG Xuan, LIANG Guodong, GUAN Ziheng. Identification and comparison of organic matter-hosted pores in shale by SEM image analysis—a deep learning-based approach[J]. Earth Science Frontiers, 2023, 30(3): 208-220.

Figures/Tables 13

References 32

[1]	HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. DOI PMID
[2]	LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. DOI
[3]	付超, 林年添, 张栋, 等. 多波地震深度学习的油气储层分布预测案例[J]. 地球物理学报, 2018, 61(1): 293-303.
[4]	陈钢花, 梁莎莎, 王军, 等. 机器学习AdaBoost.M2算法在砂砾岩流体识别中的应用[J]. 石油地球物理勘探, 2019, 54(6): 1357-1362, 1177.
[5]	张勇, 马晓东, 李彦婧, 等. 深度学习在南川页岩气含气量预测中的应用[J]. 物探与化探, 2021, 45(3): 569-575.
[6]	LIU Y Y, MA X H, ZHANG X W, et al. A deep-learning-based prediction method of the estimated ultimate recovery (EUR) of shale gas wells[J]. Petroleum Science, 2021, 18(5): 1450-1464. DOI URL
[7]	杨午阳, 杨佳润, 陈双全, 等. 基于U-Net深度学习网络的地震数据断层检测[J]. 石油地球物理勘探, 2021, 56(4): 688-697, 669.
[8]	张野, 李明超, 韩帅. 基于岩石图像深度学习的岩性自动识别与分类方法[J]. 岩石学报, 2018, 34(2): 333-342.
[9]	刘银星. 基于深度学习的地质图像盐层分割方法研究[D]. 北京: 北京工业大学, 2019.
[10]	徐述腾, 周永章. 基于深度学习的镜下矿石矿物的智能识别实验研究[J]. 岩石学报, 2018, 34(11): 3244-3252.
[11]	白林, 姚钰, 李双涛, 等. 基于深度学习特征提取的岩石图像矿物成分分析[J]. 中国矿业, 2018, 27(7): 178-182.
[12]	马陇飞, 萧汉敏, 陶敬伟, 等. 基于深度学习岩性分类的研究与应用[J]. 科学技术与工程, 2022, 22(7): 2609-2617.
[13]	李周. 岩石铸体薄图像的孔隙提取及颗粒分割研究[D]. 成都: 四川大学, 2018.
[14]	蔡宇恒, 滕奇志, 涂秉宇. 基于深度学习的岩石铸体薄片图像孔隙自动提取[J]. 科学技术与工程, 2020, 20(28): 11685-11692.
[15]	王依诚, 姜汉桥, 于馥玮, 等. 基于机器学习的数字岩心孔渗预测方法研究[J]. 石油科学通报, 2019, 4(4): 354-363.
[16]	YU Q Y, XIONG Z W, DU C, et al. Identification of rock pore structures and permeabilities using electron microscopy experiments and deep learning interpretations[J]. Fuel, 2020, 268: 117416. DOI URL
[17]	武瑾, 梁峰, 吝文, 等. 渝东北地区龙马溪组页岩储层微观孔隙结构特征[J]. 成都理工大学学报(自然科学版), 2016, 43(3): 308-319.
[18]	孙寅森, 郭少斌. 基于图像分析技术的页岩微观孔隙特征定性及定量表征[J]. 地球科学进展, 2016, 31(7): 751-763. DOI
[19]	CHEN Z H, LIU X J, YANG J J, et al. Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin[J]. Computers and Geosciences, 2020, 138: 104450. DOI URL
[20]	葛轶洲, 许翔, 杨锁荣, 等. 序列数据的数据增强方法综述[J]. 计算机科学与探索, 2021, 15(7): 1207-1219. DOI
[21]	薛东杰, 唐麒淳, 王傲, 等. 煤岩微观相态FCN智能识别与分形重构[J]. 岩石力学与工程学报, 2020, 39(6): 1203-1221.
[22]	王庆, 曾齐红, 张友焱, 等. 基于多尺度区域卷积神经网络的露头孔洞自动提取[J]. 现代地质, 2021, 35(4): 1147-1154.
[23]	张新明, 祝晓斌, 蔡强, 等. 图像语义分割深度学习模型综述[J]. 高技术通讯, 2017, 27(增刊1): 808-815.
[24]	梁艳美, 王冬梅. Photoshop软件教学研究[J]. 电脑知识与技术, 2021, 17(2): 48-49.
[25]	LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651. DOI PMID
[26]	陈岩, 奚砚涛, 万家华, 等. 面向小样本遥感解译的空间置弃FCN模型[J]. 航天返回与遥感, 2021, 42(3): 107-116.
[27]	HE K M, GEORGIA G, PIOTR D, et al. Mask R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2961-2969.
[28]	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]// 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2015: 234-241.
[29]	王香增. 鄂尔多斯盆地延长探区低渗致密油气成藏理论进展及勘探实践[J]. 地学前缘, 2023, 30(1): 143-155. DOI
[30]	赵文智, 朱如凯, 刘伟, 等. 我国陆相中高熟页岩油富集条件与分布特征[J]. 地学前缘, 2023, 30(1): 116-127. DOI
[31]	黄伟标, 李学, 宋晶, 等. 滨海软土微观孔隙测定方法[J]. 科学技术与工程, 2019, 19(28): 290-296.
[32]	赵秀才. 数字岩心及孔隙网络模型重构方法研究[D]. 青岛: 中国石油大学, 2009.

	原图	U-Net	Mask R-CNN	FCN
Ⅰ	标注: 矿物基质:0% 有机质基质:78.948% 有机孔隙:21.052% 裂缝:0%	A 矿物基质:0% 有机质基质:79.648% 有机孔隙:20.352% 裂缝:0%	B 矿物基质:0% 有机质基质:82.997% 有机孔隙:17.003% 裂缝:0%	C 矿物基质:0% 有机质基质:91.904 有机孔隙:8.096% 裂缝:0%
Ⅱ	标注: 矿物基质:0% 黄铁矿:60.024% 有机质基质:28.548% 有机孔隙:11.428% 裂缝:0%	A 矿物基质:0% 黄铁矿:59.856% 有机质基质:29.043% 有机孔隙:11.101% 裂缝:0%	B 矿物基质:0% 黄铁矿:57.525% 有机质基质:34.417 有机孔隙:8.058% 裂缝:0%	C 矿物基质:0% 黄铁矿:53.435% 有机质基质:41.63% 有机孔隙:4.935% 裂缝:0%
Ⅲ	标注: 矿物基质:56.846% 黄铁矿:0% 有机质基质:33.795% 有机孔隙:7.994% 裂缝:1.265%	A 矿物基质:57.956% 黄铁矿:0% 有机质基质:33.094% 有机孔隙:7.885% 裂缝:1.065%	B 矿物基质:58.599% 黄铁矿:0% 有机质基质:35.644% 有机孔隙:5.335% 裂缝:0.422%	C 矿物基质:59.021% 黄铁矿:0% 有机质基质:36.758% 有机孔隙:4.221% 裂缝:0%

	原图	U-Net	Mask R-CNN	FCN
Ⅰ	标注: 矿物基质:0% 有机质基质:78.948% 有机孔隙:21.052% 裂缝:0%	A 矿物基质:0% 有机质基质:79.648% 有机孔隙:20.352% 裂缝:0%	B 矿物基质:0% 有机质基质:82.997% 有机孔隙:17.003% 裂缝:0%	C 矿物基质:0% 有机质基质:91.904 有机孔隙:8.096% 裂缝:0%
Ⅱ	标注: 矿物基质:0% 黄铁矿:60.024% 有机质基质:28.548% 有机孔隙:11.428% 裂缝:0%	A 矿物基质:0% 黄铁矿:59.856% 有机质基质:29.043% 有机孔隙:11.101% 裂缝:0%	B 矿物基质:0% 黄铁矿:57.525% 有机质基质:34.417 有机孔隙:8.058% 裂缝:0%	C 矿物基质:0% 黄铁矿:53.435% 有机质基质:41.63% 有机孔隙:4.935% 裂缝:0%
Ⅲ	标注: 矿物基质:56.846% 黄铁矿:0% 有机质基质:33.795% 有机孔隙:7.994% 裂缝:1.265%	A 矿物基质:57.956% 黄铁矿:0% 有机质基质:33.094% 有机孔隙:7.885% 裂缝:1.065%	B 矿物基质:58.599% 黄铁矿:0% 有机质基质:35.644% 有机孔隙:5.335% 裂缝:0.422%	C 矿物基质:59.021% 黄铁矿:0% 有机质基质:36.758% 有机孔隙:4.221% 裂缝:0%

软件模型	JMicroVision	Photoshop	U-Net
识别孔隙图
识别时间	5 min	4 min	850 ms
识别孔隙面积占比/%	15.45	15.10	15.04

软件模型	JMicroVision	Photoshop	U-Net
识别孔隙图
识别时间	5 min	4 min	850 ms
识别孔隙面积占比/%	15.45	15.10	15.04

序号	名称	孔隙类型				孔隙度/%		渗透率/nD
序号	名称	圆度	长宽比	大小/nm²	赋存介质	计算值	实测值	计算值	实测值
a	矿物内圆状孔	0.7~1.0	0.7~0.9	<100	石英、长石、方解石、白云石	5.34	3.21	0.384	0.57
b	矿物随机不规则孔	0~0.4	0~0.1	差异大	石英、长石、方解石、白云石	7.13	5.22	0.870	211
c	有机棱角状孔	0.4~0.6	0.1~0.5	100~300	有机质	11.97	7.23	0.810	12.3
d	有机密集微孔	差异大	差异大	<100	有机质	11.20	7.57	0.430	0.95