Intelligent evaluation of sandstone rock structure based on a visual large model

REN Yili, ZENG Changmin, LI Xin, LIU Xi, HU Yanxu, SU Qianxiao, WANG Xiaoming, LIN Zhiwei, ZHOU Yixiao, ZHENG Zilu, HU Huiying, YANG Yanning, HUI Fang

PDF(21164 KB)
Petroleum Exploration and Development ›› 0 DOI: 10.11698/PED.20240645

Intelligent evaluation of sandstone rock structure based on a visual large model

  • REN Yili1,2,3, ZENG Changmin4,5, LI Xin1,2,3, LIU Xi1,2, HU Yanxu6, SU Qianxiao1,2, WANG Xiaoming4,5, LIN Zhiwei7, ZHOU Yixiao7, ZHENG Zilu1,2, HU Huiying7, YANG Yanning8, HUI Fang8
Author information +
History +

Abstract

Existing sandstone rock structure evaluation methods rely on visual inspection, with low efficiency, semi-quantitative analysis of roundness, and inability to perform classified statistics in grain size analysis. This study presents an intelligent evaluation method for sandstone rock structure based on the Segment Anything Model (SAM). By developing a lightweight SAM fine-tuning method with rank-decomposition matrix adapters, a multispectral rock particle segmentation model named CoreSAM is constructed, which achieves rock particle edge extraction and type identification. Building upon this, we propose a comprehensive quantitative evaluation system for rock structure, assessing parameters including grain size, sorting, roundness, particle contact and cementation types. The experimental results demonstrate that CoreSAM outperforms existing methods in rock particle segmentation accuracy while showing excellent generalization across different image types such as CT scans and core photographs. The proposed method enables full-sample, classified grain size analysis and quantitative characterization of parameters like roundness, advancing reservoir evaluation towards more precise, quantitative, intuitive, and comprehensive development.

Key words

sandstone / rock structure / intelligent evaluation / Segment Anything Model / fine-tuning / particle edge extraction / type identification

Cite this article

Download Citations
REN Yili, ZENG Changmin, LI Xin, LIU Xi, HU Yanxu, SU Qianxiao, WANG Xiaoming, LIN Zhiwei, ZHOU Yixiao, ZHENG Zilu, HU Huiying, YANG Yanning, HUI Fang. Intelligent evaluation of sandstone rock structure based on a visual large model. Petroleum Exploration and Development. 0 https://doi.org/10.11698/PED.20240645

References

[1] 刘合, 任义丽, 李欣, 等. 油气行业人工智能大模型应用研究现状及展望[J]. 石油勘探与开发, 2024, 51(4): 910-923.
LIU He, REN Yili, LI Xin, et al.Research status and application of artificial intelligence large models in the oil and gas industry[J]. Petroleum Exploration and Development, 2024, 51(4): 910-923.
[2] 匡立春, 刘合, 任义丽, 等. 人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发, 2021, 48(1): 1-11.
KUANG Lichun, LIU He, REN Yili, et al.Application and development trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development, 2021, 48(1): 1-11.
[3] 刘合, 任义丽, 李欣, 等. 岩心智能识别技术内涵与展望[J]. 石油学报, 2024, 45(8): 1296-1308.
LIU He, REN Yili, LI Xin, et al.Connotation and prospect of intelligent recognition technology for cores[J]. Acta Petrolei Sinica, 2024, 45(8): 1296-1308.
[4] 刘茜, 任义丽, 汪文洁, 等.基于语义分割的页岩孔隙结构智能表征方法[J/OL]. 北京航空航天大学学报, 2024: 1-15(2024-04-10)[2025-02-10]. https://doi.org/10.13700/j.bh.1001-5965.2024.0018.
LIU Qian, REN Yili, WANG Wenjie, et al.Intelligent representation method of shale pore structure based on semantic segmentation[J/OL]. Journal of Beijing University of Aeronautics and Astronautics, 2024: 1-15(2024-04-10)[2024-09-25]. https://doi.org/10.13700/j.bh.1001-5965.2024.0018.
[5] ALTUHAFI F, O’SULLIVAN C, CAVARRETTA I. Analysis of an image-based method to quantify the size and shape of sand particles[J]. Journal of Geotechnical and Geoenvironmental Engineering, 2013, 139(8): 1290-1307.
[6] SEELOS K, SIROCKO F.RADIUS-rapid particle analysis of digital images by ultra-high-resolution scanning of thin sections[J]. Sedimentology, 2005, 52(3): 669-681.
[7] ZHAO F D, YANG Y, KANG J W, et al.CE-SGAN: Classification enhancement semi-supervised generative adversarial network for lithology identification[J]. Geoenergy Science and Engineering, 2023, 223: 211562.
[8] LIU F, WANG X, LIU Z B, et al.Identification of tight sandstone reservoir lithofacies based on CNN image recognition technology: A case study of Fuyu reservoir of Sanzhao Sag in Songliao Basin[J]. Geoenergy Science and Engineering, 2023, 222: 211459.
[9] 呼和, 岳翔, 白海强, 等. 基于超像素的图像智能算法在矿物颗粒分割中的应用[J]. 中国海上油气, 2021, 33(2): 89-95.
HU He, YUE Xiang, BAI Haiqiang, et al.Application of intelligent image algorithm based on super-pixel in mineral particle segmentation[J]. China Offshore Oil and Gas, 2021, 33(2): 89-95.
[10] 周恒, 张春雷, 张欣, 等. 基于相干特征的岩石薄片序列图像边缘提取及颗粒分割[J]. 吉林大学学报(地球科学版), 2021, 51(6): 1897-1907.
ZHOU Heng, ZHANG Chunlei, ZHANG Xin, et al.Edge extraction and particle segmentation based on coherent features of rock slice sequence images[J]. Journal of Jilin University (Earth Science Edition), 2021, 51(6): 1897-1907.
[11] 司晨冉, 王仁超, 邸阔, 等. 一种基于Mask R-CNN和分水岭算法的岩石颗粒图像分割方法[J]. 水电能源科学, 2020, 38(11): 129-132.
SI Chenran, WANG Renchao, DI Kuo, et al.A rock particle image segmentation method based on Mask R-CNN and Watershed algorithm[J]. Water Resources and Power, 2020, 38(11): 129-132.
[12] LIU H, REN Y L, LI X, et al.Rock thin-section analysis and identification based on artificial intelligent technique[J]. Petroleum Science, 2022, 19(4): 1605-1621.
[13] 王伟, 李擎, 张德政, 等. 基于深度学习的矿石图像处理研究综述[J]. 工程科学学报, 2023, 45(4): 621-631.
WANG Wei, LI Qing, ZHANG Dezheng, et al.A survey of ore image processing based on deep learning[J]. Chinese Journal of Engineering, 2023, 45(4): 621-631.
[14] REN Y L, LI X, BI J Z, et al.Multi-channel attention transformer for rock thin-section image segmentation[J/OL]. Journal of Engineering Research, 2024: 1-11.(2024-04-11)[2024-10-25]. https://doi.org/10.1016/j.jer.2024.04.009.
[15] 方梦阳, 何建宁, 王万虎, 等. 一种基于MATLAB的碎屑岩粒度分析方法[J]. 岩石矿物学杂志, 2020, 39(4): 504-510.
FANG Mengyang, HE Jianning, WANG Wanhu, et al.A particle size analysis method for clastic rock based on MATLAB[J]. Acta Petrologica et Mineralogica, 2020, 39(4): 504-510.
[16] 袁瑞, 朱锐, 瞿建华, 等. 一种基于岩石薄片图像的粒度分析新方法[J]. 岩性油气藏, 2015, 27(5): 104-107.
YUAN Rui, ZHU Rui, QU Jianhua, et al.A new method of determining grain size based on rock section image[J]. Lithologic Reservoirs, 2015, 27(5): 104-107.
[17] 陶金雨, 张昌民, 朱锐. 砾石磨圆度测量方法综述[C]//中国地质学会沉积地质专业委员会, 中国矿物岩石地球化学学会沉积学专业委员会. 2015年全国沉积学大会沉积学与非常规资源论文摘要集. 武汉: 长江大学地球科学学院, 2015: 522-523.
TAO Jinyu, ZHANG Changmin, ZHU Rui.A review of gravel grinding roundness measurement methods[C]//Sedimentary Geology Professional Committee of the Geological Society of China, Sedimentology Professional Committee of the Chinese Society of Mineral, Rock and Geochemistry. Abstract collection of papers on sedimentology and unconventional resources at the 2015 National Conference on Sedimentology. Wuhan: College of Earth Sciences, Changjiang University, 2015: 522-523.
[18] 陶金雨, 张昌民, 郭旭光, 等. 磨圆度定量表征在扇三角洲沉积微相判别中的应用: 以玛湖凹陷百口泉组砾岩为例[J]. 沉积学报, 2020, 38(5): 956-965.
TAO Jinyu, ZHANG Changmin, GUO Xuguang, et al.Application of quantitative roundness characterization to identify sedimentary microfacies in fan delta deposits: A case study of conglomerates in the Baikouquan Formation, Mahu Sag[J]. Acta Sedimentologica Sinica, 2020, 38(5): 956-965.
[19] 双棋. 砾石磨圆度定量方法探究[J]. 资源信息与工程, 2019, 34(1): 103-105.
SHUANG Qi.Exploration on the quantitative method of gravel grinding roundness[J]. Resource Information and Engineering, 2019, 34(1): 103-105.
[20] 陈建湟, 张中俭, 徐文杰, 等. 基于数字图像处理的矿物颗粒形态定量分析[J]. 工程地质学报, 2021, 29(1): 59-68.
CHEN Jianhuang, ZHANG Zhongjian, XU Wenjie, et al.Quantitative method of shape parameters of mineral particles based on image processing[J]. Journal of Engineering Geology, 2021, 29(1): 59-68.
[21] 操应长, 葸克来, 王艳忠, 等. 冀中坳陷廊固凹陷河西务构造带古近系沙河街组四段储集层孔隙度演化定量研究[J]. 古地理学报, 2013, 15(5): 593-604.
CAO Yingchang, XI Kelai, WANG Yanzhong, et al.Quantitative research on porosity evolution of reservoirs in the Member 4 of Paleogene Shahejie Formation in Hexiwu structural zone of Langgu sag, Jizhong Depression[J]. Journal of Palaeogeography(Chinese Edition), 2013, 15(5): 593-604.
[22] 久博, 黄文辉, 王雅婷, 等. 鄂尔多斯盆地南部煤系致密砂岩胶结作用对储层物性的影响[J]. 煤炭学报, 2018, 43(9): 2543-2552.
JIU Bo, HUANG Wenhui, WANG Yating, et al.Effect of coal-measure tight sandstone cementation on reservoir physical property in the South of Ordos Basin[J]. Journal of China Coal Society, 2018, 43(9): 2543-2552.
[23] 韩学辉, 聂俊光, 郭俊鑫, 等. 泥质砂岩中接触胶结泥质定量估算及对砂岩弹性的影响[J]. 地球物理学报, 2020, 63(4): 1654-1662.
HAN Xuehui, NIE Junguang, GUO Junxin, et al.Quantitative estimation of contact cemented clay in clayey sandstone and its effect on elastic properties of sandstone[J]. Chinese Journal of Geophysics, 2020, 63(4): 1654-1662.
[24] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[R]. Las Vegas, NV:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[25] RONNEBERGER O, FISCHER P, BROX T.U-Net: Convolutional networks for biomedical image segmentation[C]//NAVAB N, HORNEGGER J, WELLS W M, et al. Medical Image Computing and Computer-Assisted Intervention: MICCAI 2015. Cham: Springer International Publishing, 2015: 234-241.
[26] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[R]. Montreal, QC:2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
[27] CAO H, WANG Y Y, CHEN J, et al.Swin-Unet: Unet-like pure transformer for medical image segmentation[C]//KARLINSKY L, MICHAELI T, NISHINO K. Computer Vision: ECCV 2022 Workshops. Cham: Springer, 2023: 205-218.
[28] CHENG B W, MISRA I, SCHWING A G, et al. Masked-attention mask transformer for universal image segmentation[R]. New Orleans, LA:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[29] KIRILLOV A, MINTUN E, RAVI N, et al. Segment anything[R]. Paris:2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
[30] PENG Z L, XU Z Q, ZENG Z L, et al.Sam-parser: Fine-tuning SAM efficiently by parameter space reconstruction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(5): 4515-4523.
[31] CHEN T R, ZHU L Y, DING C T, et al. SAM-adapter: Adapting segment anything in underperformed scenes[R]. Paris:2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2023.
[32] ALLABADI G, LUCIC A, WANG Y X, et al. Learning to detect novel species with SAM in the wild[J/OL]. International Journal of Computer Vision, 2024: 1-12(2024-11-13)[2025-02-25]. https://doi.org/10.1007/s11263-024-02234-0.
[33] 国家能源局. 岩石薄片鉴定: SY/T 5368—2016[S]. 北京: 石油工业出版社, 2017.
National Energy Administration.Identification for thin section of rocks: SY/T 5368—2016[S]. Beijing: Petroleum Industry Press, 2017.
[34] WANG Y Q, XU Z L, WANG X L, et al. End-to-end video instance segmentation with transformers[R]. Nashville, TN:2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[35] YANG L J, FAN Y C, XU N. Video instance segmentation[R]. Seoul:2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
[36] WU J F, JIANG Y, BAI S, et al.SeqFormer: Sequential transformer for video instance segmentation[C]//AVIDAN S, BROSTOW G, CISSÉ M, et al. Computer Vision-ECCV 2022. Cham: Springer Nature Switzerland, 2022: 553-569.
PDF(21164 KB)

6

Accesses

0

Citation

Detail

Sections
Recommended

/