A deep kernel method for fracture identification in ultra-deep tight sandstones using well logs

doi:10.13745/j.esf.sf.2024.6.22

Abstract

Abstract:

Fractures are the main seepage channels for oil and gas migration in ultra-deep tight reservoirs, and are crucial for ultra-deep oil and gas exploration and development. Ultra-deep tight reservoirs have highly complex petrophysical characteristics under high-temperature, high-pressure environments, resulting in ambiguous and multi-solution well log responses pertaining to fractures. To solve this problem, we proposes a deep kernel method (DKM) for fracture identification in ultra-deep tight sandstones. This method employs kernel principal component analysis to extract non-linear log features associated with fractures. It utilizes a deep learning cascade structure to extensively explore the log response characteristics across various scales for accurate fracture identification. Furthermore, it employs gradient-free optimization algorithms to automatically determine the optimal model structure and parameters. We conducted a case study in the ultra-deep tight sandstone reservoirs of the Lower Cretaceous Bashijiqike Formation in the Keshen gas field, Tarim Basin, and the proposed method was applied and verified. Through sensitivity analysis of logging responses to fractures, six specific logging curves were chosen for fracture identification. The first three variables, DEN, RD, and RM, correspond to direct measurements from well logging, whereas the latter three, RSD, nT1, and nT2, are reconstructed curves specifically developed to enhance the detection of fracture-related information. This distinction effectively clarifies the differences in logging parameters between fractured and non-fractured zones. A comparative analysis between the fracture identification results and the core fracture descriptions demonstrated the accuracy of the deep kernel method in identifying fractures within ultra-deep tight sandstone formations. This method achieved an accuracy improvement of over 5% compared to the conventional multi-kernel support vector machine method, thus exhibiting robust applicability for single-well fracture identification.

Key words: fracture identification, well log, deep learning, kernel method, ultra-deep tight sandstone reservoirs

CLC Number:

DONG Shaoqun, ZENG Lianbo, JI Chunqiu, ZHANG Yanbing, HAO Jingru, XU Xiaotong, HAN Gaosong, XU Hui, LI Haiming, LI Xinqi. A deep kernel method for fracture identification in ultra-deep tight sandstones using well logs[J]. Earth Science Frontiers, 2024, 31(5): 166-176.

Figures/Tables 7

Fig.1 Structural location (a, adapted from [12]), trap distribution map (b, adapted from [33]), and stratigraphy (c, modified from [38]) of Keshen gas field

Fig.2 The deep kernel method (DKM) for fracture identification using logs

Fig.3 DEN-RM cross plot

Fig.4 RD-nT2 cross plot

Fig.5 RSD-nT1 cross plot

Fig.6 Fracture identification model for ultra-deep tight sandstone reservoirs

Fig.7 Post-inspection well profile of the Bashjiqike Formation in the study area

References 41

[1]	王志民, 王翠丽, 徐珂, 等. 超深层致密砂岩构造裂缝发育特征及控制因素: 以塔里木盆地库车坳陷博孜-大北地区下白垩统储集层为例[J]. 天然气地球科学, 2023, 34(9): 1535-1551. DOI
[2]	袁龙, 信毅, 吴思仪, 等. 深层白垩系致密砂岩裂缝定性识别、参数建模与控制因素分析: 以塔里木盆地库车坳陷克深地区白垩系巴什基奇克组储层为例[J]. 东北石油大学学报, 2021, 45(1): 20-31, 72.
[3]	曾联波, 吕鹏, 屈雪峰, 等. 致密低渗透储层多尺度裂缝及其形成地质条件[J]. 石油与天然气地质, 2020, 41(3): 449-454.
[4]	丁文龙, 王兴华, 胡秋嘉, 等. 致密砂岩储层裂缝研究进展[J]. 地球科学进展, 2015, 30(7): 737-750. DOI
[5]	LI H, FAN C W, JIANG Z X, et al. Natural fractures in low-permeability sandstone reservoirs in the LD-a HPHT gas field, Yinggehai Basin: implications for hydrocarbon exploration and development[J]. Frontiers in Earth Science, 2022, 10: 934097.
[6]	丁文龙, 尹帅, 王兴华, 等. 致密砂岩气储层裂缝评价方法与表征[J]. 地学前缘, 2015, 22(4): 173-187. DOI
[7]	HUANG S L, LIU J Y, SUN J D, et al. Water invasion mode of carbonate gas reservoirs controlled by edge water: three invasion modes[J]. Frontiers in Energy Research, 2022, 10: 860527.
[8]	汪明锐, 张冲, 聂昕, 等. 基于测井曲线重构的致密砂岩储层裂缝识别[J]. 西安石油大学学报(自然科学版), 2022, 37(5): 10-20.
[9]	DONG S Q, ZENG L B, LYU W Y, et al. Fracture identification by semi-supervised learning using conventional logs in tight sandstones of Ordos Basin, China[J]. Journal of Natural Gas Science and Engineering, 2020, 76: 103131.
[10]	DONG S Q, ZENG L B, LYU W Y, et al. Fracture identification and evaluation using conventional logs in tight sandstones: a case study in the Ordos Basin, China[J]. Energy Geoscience, 2020, 1(3/4): 115-123.
[11]	LYU W Y, ZENG L B, LIAO Z H, et al. Fault damage zone characterization in tight-oil sandstones of the Upper Triassic Yanchang Formation in the southwest Ordos Basin, China: integrating cores, image logs, and conventional logs[J]. Interpretation, 2017, 5(4): SP27-SP39.
[12]	王珂, 张荣虎, 王俊鹏, 等. 超深层致密砂岩储层构造裂缝分布特征及其成因: 以塔里木盆地库车前陆冲断带克深气田为例[J]. 石油与天然气地质, 2021, 42(2): 338-353.
[13]	常宝华, 唐永亮, 朱松柏, 等. 超深层裂缝性致密砂岩气藏试井特征及认识: 以塔里木盆地克深气田为例[J]. 大庆石油地质与开发, 2021, 40(3): 167-174.
[14]	ZENG L B, GONG L, GUAN C, et al. Natural fractures and their contribution to tight gas conglomerate reservoirs: a case study in the northwestern Sichuan Basin, China[J]. Journal of Petroleum Science and Engineering, 2022, 210: 110028.
[15]	BHATTACHARYA S, MISHRA S. Applications of machine learning for facies and fracture prediction using Bayesian Network Theory and Random Forest: case studies from the Appalachian Basin, USA[J]. Journal of Petroleum Science and Engineering, 2018, 170: 1005-1017.
[16]	DONG S Q, ZENG L B, LIU J J, et al. Fracture identification in tight reservoirs by multiple kernel Fisher discriminant analysis using conventional logs[J]. Interpretation, 2020, 8(4): SP215-SP225.
[17]	程超, 何亮, 张本健, 等. 中坝气田须二段气藏裂缝分级评价方法[J]. 大庆石油地质与开发, 2020, 39(2): 56-64.
[18]	TIAN M, OMRE H, XU H M. Inversion of well logs into lithology classes accounting for spatial dependencies by using hidden Markov models and recurrent neural networks[J]. Journal of Petroleum Science and Engineering, 2021, 196: 107598.
[19]	NOURI-TALEGHANI M, MAHMOUDIFAR M, SHOKROLLAHI A, et al. Fracture density determination using a novel hybrid computational scheme: a case study on an Iranian Marun oil field reservoir[J]. Journal of Geophysics and Engineering, 2015, 12(2): 188-198.
[20]	郑军, 刘鸿博, 周文, 等. 阿曼五区块Daleel油田储层裂缝识别方法研究[J]. 测井技术, 2010, 34(3): 251-256.
[21]	武中原, 张欣, 张春雷, 等. 基于LSTM循环神经网络的岩性识别方法[J]. 岩性油气藏, 2021, 33(3): 120-128.
[22]	孙予舒, 黄芸, 梁婷, 等. 基于XGBoost算法的复杂碳酸盐岩岩性测井识别[J]. 岩性油气藏, 2020, 32(4): 98-106.
[23]	谷宇峰, 张道勇, 鲍志东. 利用混合模型CRBM-PSO-XGBoost识别致密砂岩储层岩性[J]. 石油与天然气地质, 2021, 42(5): 1210-1222.
[24]	DONG S Q, ZENG L B, DU X Y, et al. An intelligent prediction method of fractures in tight carbonate reservoirs[J]. Petroleum Exploration and Development, 2022, 49(6): 1364-1376.
[25]	XU J L, WANG R T, ZAN L, et al. Geomechanical log responses and identification of fractures in tight sandstone, West Sichuan Xinchang Gas Field[J]. Scientific Reports, 2022, 12: 15543. DOI PMID
[26]	DONG S Q, ZHONG Z H, CUI X H, et al. A deep kernel method for lithofacies identification using conventional well logs[J]. Petroleum Science, 2023, 20(3):1411-1428.
[27]	王珂, 张荣虎, 王俊鹏, 等. 塔里木盆地库车坳陷侏罗系阿合组与白垩系巴什基奇克组储层特征对比与勘探开发启示[J]. 天然气地球科学, 2022, 33(4): 556-571. DOI
[28]	曾联波, 刘国平, 朱如凯, 等. 库车前陆盆地深层致密砂岩储层构造成岩强度的定量评价方法[J]. 石油学报, 2020, 41(12): 1601-1609.
[29]	何登发, 周新源, 杨海军, 等. 库车坳陷的地质结构及其对大油气田的控制作用[J]. 大地构造与成矿学, 2009, 33(1): 19-32.
[30]	魏强, 李贤庆, 孙可欣, 等. 塔里木盆地库车坳陷克深大气田深层天然气成藏地球化学特征[J]. 天然气地球科学, 2019, 30(6): 897-907. DOI
[31]	付晓飞, 贾茹, 王海学, 等. 断层-盖层封闭性定量评价: 以塔里木盆地库车坳陷大北—克拉苏构造带为例[J]. 石油勘探与开发, 2015, 42(3): 300-309.
[32]	王招明, 李勇, 谢会文, 等. 库车前陆盆地超深层大油气田形成的地质认识[J]. 中国石油勘探, 2016, 21(1): 37-43.
[33]	宋泽章, 吕明阳, 赵力彬, 等. 基于分形理论的致密砂岩渗透率预测模型[J]. 沉积学报, 2023, 41(6): 1847-1858.
[34]	赖锦, 王贵文, 孙思勉, 等. 致密砂岩储层裂缝测井识别评价方法研究进展[J]. 地球物理学进展, 2015, 30(4): 1712-1724.
[35]	赖锦, 王贵文, 郑新华, 等. 油基泥浆微电阻率扫描成像测井裂缝识别与评价方法[J]. 油气地质与采收率, 2015, 22(6): 47-54.
[36]	汪林波, 韩登林, 王晨晨, 等. 库车坳陷克深井区白垩系巴什基奇克组孔缝充填特征及流体来源[J]. 岩性油气藏, 2022, 34(3): 49-59.
[37]	张荣虎, 王珂, 王俊鹏, 等. 塔里木盆地库车坳陷克深构造带克深8区块裂缝性低孔砂岩储层地质模型[J]. 天然气地球科学, 2018, 29(9): 1264-1273. DOI
[38]	王珂, 张荣虎, 赵继龙, 等. 塔里木盆地库车坳陷克拉苏构造带走滑作用对构造裂缝的影响[J]. 天然气地球科学, 2023, 34(8): 1316-1327. DOI
[39]	高文杰, 李贤庆, 张光武, 等. 塔里木盆地库车坳陷克拉苏构造带深层致密砂岩气藏储层致密化与成藏关系[J]. 天然气地球科学, 2018, 29(2): 226-235. DOI
[40]	毛亚昆, 钟大康, 李勇, 等. 构造挤压背景下深层砂岩压实分异特征: 以塔里木盆地库车前陆冲断带白垩系储层为例[J]. 石油与天然气地质, 2017, 38(6): 1113-1122.
[41]	年涛, 王贵文, 肖承文, 等. 库车坳陷巴什基奇克组裂缝密度的控制因素分析[J]. 石油科学通报, 2016, 1(3): 319-329.