研究论文

基于深度学习的页岩黄铁矿扫描电镜图像分割及环境指示意义:以四川盆地泸州Ι区为例

  • 邓乃尔 ,
  • 徐浩 ,
  • 周文 ,
  • 唐小川 ,
  • 陈雨露 ,
  • 刘永旸 ,
  • 刘绍军 ,
  • 张益 ,
  • 蒋柯 ,
  • 刘瑞崟 ,
  • 宋威国
展开
  • 1.成都理工大学 能源学院(页岩气现代产业学院),四川 成都 610059
    2.成都理工大学 油气藏地质及 开发工程全国重点实验室,四川 成都 610059
    3.成都理工大学 计算机与网络安全学院(示范性软件学院),四川 成都 610059
    4.中国石油西南油气田公司 页岩气研究院,四川 成都 610051
    5.四川大学 电子信息学院,四川 成都 610065
    6.贵州省地质调查院,贵州 贵阳 550081
邓乃尔,硕士研究生,主要从事非常规储层精细评价研究. E-mail:2516101958@qq.com
徐浩,副教授,主要从事非常规油气储层地质评价及地质力学研究. E-mail:xuhao19@cdut.edu.cn

收稿日期: 2024-01-24

  修回日期: 2024-04-29

  网络出版日期: 2024-05-14

基金资助

国家自然科学基金项目(42202189);四川省自然科学基金项目(24NSFSC4997)

Deep Learning SEM Image Segmentation of Shale Pyrite and Environmental Indications: A Study of Luzhou Block, Sichuan Basin

  • Naier DENG ,
  • Hao XU ,
  • Wen ZHOU ,
  • Xiaochuan TANG ,
  • Yulu CHEN ,
  • Yongyang LIU ,
  • Shaojun LIU ,
  • Yi ZHANG ,
  • Ke JIANG ,
  • Ruiyin LIU ,
  • Weiguo SONG
Expand
  • 1.College of Energy (College of Modern Shale Gas Industry), Chengdu University of Technology, Chengdu 610059, China
    2.State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu 610059, China
    3.College of Computer Science and Cyber Security(Demonstrative Software College), Chengdu University of Technology, Chengdu 610059, China
    4.Research Institute of Shale Gas, PetroChina Southwest Oil & Gasfield Company, Chengdu 610051, China
    5.College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China
    6.Guizhou Geological Survery, Guiyang 550081, China
DENG Naier, Master student, research area includes unconventional reservoir fine evaluation. E-mail: 2516101958@qq.com
XU Hao, Associate professor, research areas include geological evaluation of unconventional oil and gas reservoirs and geomechanics research. E-mail: xuhao19@cdut.edu.cn

Received date: 2024-01-24

  Revised date: 2024-04-29

  Online published: 2024-05-14

Supported by

the National Natural Science Foundation of China(42202189);The Natural Science Foundation of Sichuan Province(24NSFSC4997)

摘要

黄铁矿作为页岩体系中最具代表性的重矿物之一,对其进行微观特征识别对于页岩沉积环境研究具有重要意义。以四川盆地泸州Ι区五峰组—龙一1亚段为例,通过岩心矿物实验、扫描电镜观测、网络模型优化和特征参数统计,构建了适用于黄铁矿扫描电镜图像分割的网络模型,实现了基于草莓状黄铁矿参数对研究区沉积环境的判断。结果表明:优化后的UNet-Im模型对草莓状黄铁矿扫描电镜图像的分割精度可达0.863,证明了改进措施的优越性;对比黄铁矿含量,龙一11~3小层黄铁矿含量最高,为2.95%,随后降低至龙一14小层的2.03%以及五峰组的0.83%;基于草莓状黄铁矿特征参数,推断出黄铁矿沉积环境为深水硫化环境、深水强还原环境、深水强—弱还原环境以及深水还原—次氧化环境。实现了黄铁矿扫描电镜图像的精准化分割,对于提升行业勘探开发智能化具有借鉴意义。

本文引用格式

邓乃尔 , 徐浩 , 周文 , 唐小川 , 陈雨露 , 刘永旸 , 刘绍军 , 张益 , 蒋柯 , 刘瑞崟 , 宋威国 . 基于深度学习的页岩黄铁矿扫描电镜图像分割及环境指示意义:以四川盆地泸州Ι区为例[J]. 地球科学进展, 2024 , 39(5) : 476 -488 . DOI: 10.11867/j.issn.1001-8166.2024.036

Abstract

Pyrite, a significant heavy mineral in shale, aids in the comprehension of shale depositional environments. Referencing the Wufeng-Long1 subsection Formation of the Luzhou Block in Sichuan Basin, a network model for pyrite SEM image segmentation was established via core mineral experiments, SEM observations, network model refinement, and feature parameter analysis. The model assesses the sedimentary environment of the study block using pyrite framboid parameters. Our findings indicated that enhancement of the UNet-Im model for pyrite framboid SEM images resulted in a segmentation precision of 0.863, demonstrating the effectiveness of the enhancement measures. Pyrite content varied from 2.95% in the Long11~3 minor layer to 0.83% in the Wufeng Formation, with the Long14 minor layer at 2.03%. Pyrite depositional environments are deduced as deep-water sulfide environments, strong reducing environments, strong-weak reduction environments, and reductive-suboxidative environments based on pyrite framboid characteristics. This study accurately segmented pyrite SEM images to enhance the exploration and development of intelligence in this industry.

参考文献

1 CHANG Huajin, CHU Xuelei. Pyrite framboids and palaeo-ocean redox condition reconstruction[J]. Advances in Earth Science, 2011, 26(5): 475-481.
1 常华进, 储雪蕾. 草莓状黄铁矿与古海洋环境恢复[J]. 地球科学进展, 2011, 26(5): 475-481.
2 CAO Taotao, DENG Mo, SONG Zhiguang, et al. Study on the effect of pyrite on the accumulation of shale oil and gas[J]. Natural Gas Geoscience, 2018, 29(3): 404-414.
2 曹涛涛, 邓模, 宋之光, 等. 黄铁矿对页岩油气富集成藏影响研究[J]. 天然气地球科学, 2018, 29(3): 404-414.
3 QIN Xiaoyan, WANG Zhenliang, YU Hongyan, et al. A new shale brittleness evaluation method based on rock physics and mineral compositions[J]. Natural Gas Geoscience, 2016, 27(10): 1 924-1 932, 1 941.
3 秦晓艳, 王震亮, 于红岩, 等. 基于岩石物理与矿物组成的页岩脆性评价新方法[J]. 天然气地球科学, 2016, 27(10): 1 924-1 932, 1 941.
4 ZHOU Shangwen, XUE Huaqing, GUO Wei. A mineral analysis method for shale based on SEM and X-ray EDS[J]. China Petroleum Exploration, 2017, 22(6): 27-33.
4 周尚文, 薛华庆, 郭伟. 基于扫描电镜和X射线能谱的页岩矿物分析方法[J]. 中国石油勘探, 2017, 22(6): 27-33.
5 LIU Xuefeng, ZHANG Xiaowei, ZENG Xin, et al. Pore structure characterization of shales using SEM and machine learning-based segmentation method[J]. Journal of China University of Petroleum (Edition of Natural Science), 2022, 46(1): 23-33.
5 刘学锋, 张晓伟, 曾鑫, 等. 采用机器学习分割算法和扫描电镜分析页岩微观孔隙结构[J]. 中国石油大学学报(自然科学版), 2022, 46(1): 23-33.
6 LIU Jiangyan, LI Shixiang, LI Zhen, et al. Characteristics and geological significance of pyrite in Chang 73 sub-member in the Ordos Basin[J]. Natural Gas Geoscience, 2021, 32(12): 1 830-1 838.
6 刘江艳, 李士祥, 李桢, 等. 鄂尔多斯盆地长73亚段泥页岩黄铁矿发育特征及其地质意义[J]. 天然气地球科学, 2021, 32(12): 1 830-1 838.
7 SONG Hui, SHAO Deyong, LUO Huan, et al. SEM image characteristics and paleoenvironmental significance of framboidal pyrite from the Lower Cambrian Shuijingtuo Formation in Yichang area, western Hubei Province, Southern China: a case study of well EYY1[J]. Earth Science Frontiers, 2023, 30(3): 195-207.
7 宋辉, 邵德勇, 罗欢, 等. 鄂西宜昌地区下寒武统水井沱组草莓状黄铁矿SEM图像特征及古环境指示意义:以鄂阳页1井为例[J]. 地学前缘, 2023, 30(3): 195-207.
8 LUO H, ZHANG T W, YAN J P, et al. Rare Earth elements and Yttrium (REY) distribution pattern of lower Cambrian organic-rich shale in Yichang area, Western Hubei Province, South China, and source of carbonate minerals[J]. Applied Geochemistry, 2022, 136. DOI:10.1016/j.apgeochem.2021.105173 .
9 CHEN Zongming, TANG Xuan, LIANG Guodong, et al. 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.
9 陈宗铭, 唐玄, 梁国栋, 等. 基于深度学习的页岩扫描电镜图像有机质孔隙识别与比较[J]. 地学前缘, 2023, 30(3): 208-220.
10 RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]// International conference on medical image computing and computer-assisted intervention. Cham: Springer, 2015: 234-241.
11 HUANG Peng, ZHENG Qi, LIANG Chao. Overview of image segmentation methods[J]. Journal of Wuhan University (Natural Science Edition), 2020, 66(6): 519-531.
11 黄鹏, 郑淇, 梁超. 图像分割方法综述[J]. 武汉大学学报(理学版), 2020, 66(6): 519-531.
12 QIAO Fengjuan, GUO Hongli, LI Wei, et al. Research on deep learning classification based on SVM: a review[J]. Journal of Qilu University of Technology, 2018, 32(5): 39-44.
12 乔风娟, 郭红利, 李伟, 等. 基于SVM的深度学习分类研究综述[J]. 齐鲁工业大学学报, 2018, 32(5): 39-44.
13 LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521: 436-444.
14 LI Yimin, TAN Zhenyu, YANG Chen, et al. Extraction of algal blooms in Dianchi Lake based on multi-source satellites using machine learning algorithms[J]. Advances in Earth Science, 2022, 37(11): 1 141-1 156.
14 李一民, 谭振宇, 杨辰, 等. 基于多源卫星的滇池藻华提取机器学习算法研究[J]. 地球科学进展, 2022, 37(11): 1 141-1 156.
15 LI Xiaoxin, LIANG Ronghua. A review for face recognition with occlusion: from subspace regression to deep learning[J]. Chinese Journal of Computers, 2018, 41(1): 177-207.
15 李小薪, 梁荣华. 有遮挡人脸识别综述: 从子空间回归到深度学习[J]. 计算机学报, 2018, 41(1): 177-207.
16 ZHOU Yongzhang, WANG Jun, ZUO Renguang, et al. Machine learning, deep learning and Python language in field of geology[J]. Acta Petrologica Sinica, 2018, 34(11): 3 173-3 178.
16 周永章, 王俊, 左仁广, 等. 地质领域机器学习、深度学习及实现语言[J]. 岩石学报, 2018, 34(11): 3 173-3 178.
17 ALIGHOLI S, KHAJAVI R, RAZMARA M. Automated mineral identification algorithm using optical properties of crystals[J]. Computers & Geosciences, 2015, 85: 175-183.
18 CHEN Yan, LI Zhicheng, CHENG Chao, et al. FLU-net: a deep fully convolutional neural network for shale reservoir micro-pore characterization[J]. Marine Geology Frontiers, 2021, 37(8): 34-43.
18 陈雁, 李祉呈, 程超, 等. FLU-net:用于表征页岩储层微观孔隙的深度全卷积网络[J]. 海洋地质前沿, 2021, 37(8): 34-43.
19 LIU Shaojun, LIU Yong, ZHAO Shengxian, et al. Distribution characteristics and pattern of deep shale present geostress field in northern Luzhou[J]. Advances in Earth Science, 2023, 38(12): 1 271-1 284.
19 刘绍军, 刘勇, 赵圣贤, 等. 泸州北区深层页岩现今地应力场分布特征及扰动规律[J]. 地球科学进展, 2023, 38(12): 1 271-1 284.
20 YANG Hongzhi, ZHAO Shengxian, LIU Yong, et al. Main controlling factors of enrichment and high-yield of deep shale gas in the Luzhou Block, southern Sichuan Basin[J]. Natural Gas Industry, 2019, 39(11): 55-63.
20 杨洪志, 赵圣贤, 刘勇, 等. 泸州区块深层页岩气富集高产主控因素[J]. 天然气工业, 2019, 39(11): 55-63.
21 WANG Yuman, DONG Dazhong, LI Xinjing, et al. Stratigraphic sequence and sedimentary characteristics of Lower Silurian Longmaxi Formation in the Sichuan Basin and its peripheral areas[J]. Natural Gas Industry, 2015, 35(3): 12-21.
21 王玉满, 董大忠, 李新景, 等. 四川盆地及其周缘下志留统龙马溪组层序与沉积特征[J]. 天然气工业, 2015, 35(3): 12-21.
22 SHEN Cheng, XIE Jun, ZHAO Jinzhou, et al. Evolution difference of fracability of marine shale gas reservoir in Luzhou and West Chongqing Block, Sichuan Basin[J]. Journal of China University of Mining & Technology, 2020, 49(4): 742-754.
22 沈骋, 谢军, 赵金洲, 等. 泸州—渝西区块海相页岩可压性演化差异[J]. 中国矿业大学学报, 2020, 49(4): 742-754.
23 ZHAO Shengxian, YANG Yueming, ZHANG Jian, et al. Micro-layers division and fine reservoirs contrast of Lower Silurian Longmaxi Formation shale, Sichuan Basin, SW China[J]. Natural Gas Geoscience, 2016, 27(3): 470-487.
23 赵圣贤, 杨跃明, 张鉴, 等. 四川盆地下志留统龙马溪组页岩小层划分与储层精细对比[J]. 天然气地球科学, 2016, 27(3): 470-487.
24 ZHONG Sihua, GUO Xingming, ZHENG Yineng. Improved U-Net network for lung nodule segmentation[J]. Computer Engineering and Applications, 2020, 56(17): 203-209.
24 钟思华, 郭兴明, 郑伊能. 改进U-Net网络的肺结节分割方法[J]. 计算机工程与应用, 2020, 56(17): 203-209.
25 YAO Jiaqi, XU Zhengguo, YAN Jikun, et al. WPLoss: weighted pairwise loss for class-imbalanced datasets[J]. Application Research of Computers, 2021, 38(3): 702-704, 709.
25 姚佳奇, 徐正国, 燕继坤, 等. WPLoss:面向类别不平衡数据的加权成对损失[J]. 计算机应用研究, 2021, 38(3): 702-704, 709.
26 LI X Y, SUN X F, MENG Y X, et al. Dice loss for data-imbalanced NLP tasks[C]// Proceedings of the 58th annual meeting of the association for computational linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2020.
27 LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]// 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017: 2 999-3 007.
28 CHEN Ying, LI Chisheng, ZHANG Ruiqi. Modulated signal recognition method based on improved residual neural network[J]. Modern Electronics Technique, 2021, 44(15): 54-58.
28 陈颖, 李迟生, 张睿琦. 一种改进残差神经网络的调制信号识别方法[J]. 现代电子技术, 2021, 44(15): 54-58.
29 GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]// GORDON G,DUNSON D,DUDíK M. International conference on artificial intelligence and statistics.USA: Proceedings of Machine Learning Research,2011:315-323.
30 CHEN L C, ZHU Y K, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]// European conference on computer vision. Cham: Springer, 2018: 833-851.
31 WANG J D, SUN K, CHENG T H, et al. Deep high-resolution representation learning for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10): 3 349-3 364.
32 WANG Dongsheng, ZHANG Jinchuan, LI Zhen, et al. Formation mechanism of framboidal pyrite and its theory inversion of paleo-redox conditions[J]. Geology in China, 2022, 49(1): 36-50.
32 王东升, 张金川, 李振, 等. 草莓状黄铁矿的形成机制探讨及其对古氧化—还原环境的反演[J]. 中国地质, 2022, 49(1): 36-50.
33 WILKIN R T, BARNES H L, BRANTLEY S L. The size distribution of framboidal pyrite in modern sediments: an indicator of redox conditions[J]. Geochimica et Cosmochimica Acta, 1996, 60(20): 3 897-3 912.
34 XIAO Di, DAI Chaocheng, BAI Bin, et al. Characteristics and significance of continental organic rich shale pyrite: taking Yanchang formation in Ordos Basin and Qingshankou formation in Songliao Basin as examples[J]. Science Technology and Engineering, 2023, 23(23): 9 888-9 902.
34 肖迪, 戴朝成, 白斌, 等. 陆相富有机质页岩黄铁矿特征及意义: 以鄂尔多斯盆地延长组和松辽盆地青山口组为例[J]. 科学技术与工程, 2023, 23(23): 9 888-9 902.
35 LIU Ziyi, ZHANG Jinchuan, LIU Yang, et al. The particle size characteristics of pyrite in western Hunan and Hubei areas’ Wufeng-Longmaxi Formation shale[J]. Science Technology and Engineering, 2016, 16(26): 34-41.
35 刘子驿, 张金川, 刘飏, 等. 湘鄂西地区五峰—龙马溪组泥页岩黄铁矿粒径特征[J]. 科学技术与工程, 2016, 16(26): 34-41.
36 WU Jianfa, ZHAO Shengxian, ZHANG Yingkun, et al. Material composition and pore contribution of deep shale gas reservoir and its significance for exploration and development[J]. Natural Gas Geoscience, 2022, 33(4): 642-653.
36 吴建发, 赵圣贤, 张瑛堃, 等. 深层页岩气储层物质组成与孔隙贡献及其勘探开发意义[J]. 天然气地球科学, 2022, 33(4): 642-653.
文章导航

/