基于地震属性的致密碳酸盐岩储层裂缝分布的人工智能预测方法
鲍明阳 , 董少群 , 曾联波 , 何娟 , 孙福亭 , 韩高松
地球科学 ›› 2023, Vol. 48 ›› Issue (07) : 2462 -2474.
基于地震属性的致密碳酸盐岩储层裂缝分布的人工智能预测方法
Artificial Intelligence Prediction Method for Tight Carbonate Reservoir Fracture Distribution Based on Seismic Attributes
,
裂缝是致密碳酸盐岩储层的重要渗流通道,影响油藏开发效果.由于裂缝的地球物理响应弱且复杂,使得裂缝预测困难.在深度挖掘地震属性中裂缝特征信息的基础上,建立了基于人工智能的裂缝分布预测方法.该方法通过支持向量机算法优选裂缝敏感属性,利用梯度提升决策树(GBDT)算法深度挖掘单井裂缝发育情况与地震属性之间的非线性关系,梯度提升决策树算法对于异常值有较强的鲁棒性,可以较好地解决裂缝地震响应弱且复杂的问题.该方法在中东扎格罗斯盆地某油田古近系渐新统‒新近系中新统Asmari组主力产油层位的致密碳酸盐岩储层中进行了实例应用,优选出方差、曲率、倾角偏差、倾角、方位角5种裂缝敏感地震属性,利用梯度提升决策树集成不同地震属性中的裂缝特征,建立裂缝分布预测模型,对研究区碳酸盐岩储层裂缝分布进行了预测.与常用裂缝预测方法的对比实验表明,本方法的裂缝预测结果与单井裂缝解释更为符合.预测结果表明,研究区北部裂缝更为发育,构造高部位附近裂缝更为发育,与生产动态认识相符合.
裂缝预测 / 地震属性 / 致密碳酸盐岩储层 / 人工智能 / 扎格罗斯盆地
fracture prediction / seismic attributes / tight carbonate reservoir / artificial intelligence / Zagros Basin
| [1] |
Chang, D.K., Yong, X.S., Wang, Y.H., et al., 2021. Seismic Fault Interpretation Based on Deep Convolutional Neural Networks. Oil Geophysical Prospecting, 56(1): 1-8 (in Chinese with English abstract). |
| [2] |
Chen, S. Y., Wang, Y. J., Guo, J. Y., et al., 2021. Multi-Scale Evaluation of Fractured Carbonate Reservoir and Its Implication to Sweet-Spot Optimization: A Case Study of Tazhong Oilfield, Central Tarim Basin, China. Energy Reports, 7: 2976-2988. https://doi.org/10.1016/j.egyr.2021.05.017 |
| [3] |
Dong, S.Q., Lyu, W.Y., Xia, D.L., et al., 2020. An Approach to 3D Geological Modeling of Multi-Scaled Fractures in Tight Sandstone Reservoirs. Oil & Gas Geology, 41(3):627-637 (in Chinese with English abstract). |
| [4] |
Dong, S.Q., Zeng, L.B., Che, X.H., et al., 2023. Application of Artificial Intelligence in Fracture Identification Using Well Logs in Tight Reservoirs. Earth Science, 48(7):1-12 (in Chinese with English abstract). |
| [5] |
Dong, S. Q., Zeng, L. B., Liu, J. J., et al., 2020a. Fracture Identification in Tight Reservoirs by Multiple Kernel Fisher Discriminant Analysis Using Conventional Logs. Interpretation, 8(4): SP215-SP225. https://doi.org/10.1190/int-2020-0048.1 |
| [6] |
Dong, S. Q., Zeng, L. B., Lyu, W. Y., et al., 2020b. Fracture Identification by Semi-Supervised Learning Using Conventional Logs in Tight Sandstones of Ordos Basin, China. Journal of Natural Gas Science and Engineering, 76: 103131. https://doi.org/10.1016/j.jngse.2019.103131 |
| [7] |
Dong, S. Q., Zeng, L. B., Lyu, W. Y., et al., 2020c. Fracture Identification and Evaluation Using Conventional Logs in Tight Sandstones: A Case Study in the Ordos Basin, China. Energy Geoscience, 1(3-4): 115-123. https://doi.org/10.1016/j.engeos.2020.06.003 |
| [8] |
Dong, S.Q., Zeng, L.B., Xu, C.S., et al., 2018. Some Progress in Reservoir Fracture Stochastic Modeling Research. Oil Geophysical Prospecting, 53(3): 625-641 (in Chinese with English abstract). |
| [9] |
Du, X.Y., Dong, S.Q., Zeng, L.B., et al., 2021. Study of Automatic Extraction Porosity Using Cast Thin Sections for Carbonates. Geological Review, 67(6): 1910-1921 (in Chinese with English abstract). |
| [10] |
Fei, S. P., Hassan, M. A., He, Z. H., et al., 2021. Assessment of Ensemble Learning to Predict Wheat Grain Yield Based on UAV-Multispectral Reflectance. Remote Sensing, 13(12): 2338. https://doi.org/10.3390/rs13122338 |
| [11] |
Gu, Y.F., Zhang, D.Y., Bao, Z.D., et al., 2021. Permeability Prediction Using Gradient Boosting Decision Tree (GBDT): A Case Study of Tight Sandstone Reservoirs of Member of Chang 4+5 in Western Jiyuan Oilfield. Progress in Geophysics, 36(2):585-594 (in Chinese with English abstract). |
| [12] |
Gu, Y. F., Zhang, D. Y., Lin, Y. B., et al., 2021. Data-Driven Lithology Prediction for Tight Sandstone Reservoirs Based on New Ensemble Learning of Conventional Logs: A Demonstration of a Yanchang Member, Ordos Basin. Journal of Petroleum Science and Engineering, 207: 109292. https://doi.org/10.1016/j.petrol.2021.109292 |
| [13] |
Hao, H.Z., Gu, Q., Hu, X.M., 2021. Research Advances and Prospective in Mineral Intelligent Identification Based on Machine Learning. Earth Science, 46(9):3091-3106 (in Chinese with English abstract). |
| [14] |
He, J., Wu, G., Nie, W.L., et al., 2020. Fracture Classification Method Based on Proximal Support Vector Machine. Lithologic Reservoirs, 32(2): 115-121 (in Chinese with English abstract). |
| [15] |
Hu, Q.H., Li, Z.Y., 2016. Non-Sparse Multiple Kernel Learning Method Based on Boosting Framework. Application Research of Computers, 33(11): 3219-3222 (in Chinese with English abstract). |
| [16] |
Huang, F.X., Xia, Z.Y., Gui, H.B., et al., 2016. The Application of BP Neural Network to DMT Hill Metamorphic Fracture Prediction. Chinese Journal of Engineering Geophysics, 13(4): 483-490 (in Chinese with English abstract). |
| [17] |
Huang, J.C., Ma, Y.H., Qi, K.Y., et al., 2018. An Ensemble-Based Intrusion Detection Algorithm. Journal of Shanghai Jiao Tong University, 52(10): 1382-1387 (in Chinese with English abstract). |
| [18] |
Jia, C.Z., 2017. Breakthrough and Significance of Unconventional Oil and Gas to Classical Petroleum Geological Theory. Petroleum Exploration and Development, 44(1): 1-11 (in Chinese with English abstract). |
| [19] |
Jia, C.Z., Zheng, M., Zhang, Y.F., 2012. Unconventional Hydrocarbon Resources in China and the Prospect of Exploration and Development. Petroleum Exploration and Development, 39(2):129-136 (in Chinese with English abstract). |
| [20] |
Khalili, A., Vaziri-Moghaddam, H., Arian, M., et al., 2021. Carbonate Platform Evolution of the Asmari Formation in the East of Dezful Embayment, Zagros Basin, SW Iran. Journal of African Earth Sciences, 181: 104229. https://doi.org/10.1016/j.jafrearsci.2021.104229 |
| [21] |
Kor, K., Altun, G., 2020. Is Support Vector Regression Method Suitable for Predicting Rate of Penetration? Journal of Petroleum Science and Engineering, 194: 107542. https://doi.org/10.1016/j.petrol.2020.107542 |
| [22] |
Li, F.F., Guo, R., Liu, L.F., et al., 2021. Genesis of Reservoirs of Lagoon in the Mishrif Formation, M Oilfield, Iraq. Earth Science, 46(1):228-241 (in Chinese with English abstract). |
| [23] |
Li, Y.F., Cheng, J.Y., Wang, C., 2012. Seismic Attribute Optimization Based on Support Vector Machine and Coalbed Methane Prediction. Coal Geology & Exploration, 40(6): 75-78 (in Chinese with English abstract). |
| [24] |
Liao, Z.H., Chen, W.L., Li, W., et al., 2020. Fault- Fracture Systems of the Xujiahe Tight Sandstone in the Northeast Sichuan Basin, Part Ⅰ: Distribution of Fault Damage Zones. Petroleum Science Bulletin, 5(4):441-448 (in Chinese with English abstract). |
| [25] |
Liu, D. D., Zhang, C., Pan, Z. K., et al., 2020. Natural Fractures in Carbonate-Rich Tight Oil Reservoirs from the Permian Lucaogou Formation, Southern Junggar Basin, NW China: Insights from Fluid Inclusion Microthermometry and Isotopic Geochemistry. Marine and Petroleum Geology, 119: 104500. https://doi.org/10.1016/j.marpetgeo.2020.104500 |
| [26] |
Liu, G.P., Dong, S.Q., Li, H.N., et al., 2020. Characteristics of Natural Fractures and Their Influencing Factors in the Paleo-Buried-Hill Reservoirs of the Western Sag in the Liaohe Basin, China. Oil & Gas Geology, 41(3): 525-533 (in Chinese with English abstract). |
| [27] |
Liu, J. J., Liu, J. C., 2021. An Intelligent Approach for Reservoir Quality Evaluation in Tight Sandstone Reservoir Using Gradient Boosting Decision Tree Algorithm-A Case Study of the Yanchang Formation, Mid-Eastern Ordos Basin, China. Marine and Petroleum Geology, 126: 104939. https://doi.org/10.1016/j.marpetgeo.2021.104939 |
| [28] |
Liu, J.Z., Han, L., Shi, L., et al., 2021. Seismic Prediction of Tight Sandstone Reservoir Fractures in XC Area, Western Sichuan Basin. Oil & Gas Geology, 42(3):747-754 (in Chinese with English abstract). |
| [29] |
Liu, X.B., Wen, Z.X., He, Z.J., et al., 2019. Zagros Basin in Middle East: Along-Strike Variations of Structure and Petroleum Accumulation Characteristics. Acta Petrologica Sinica, 35(4):1269-1278 (in Chinese with English abstract). |
| [30] |
Lu, Y. J., Zhang, Z., Shangguan, D.H., et al., 2021. Novel Machine Learning Method Integrating Ensemble Learning and Deep Learning for Mapping Debris-Covered Glaciers. Remote Sensing, 13(13):2595. https://doi.org/10.3390/rs13132595 |
| [31] |
Lü, G.H., Yu, C.Q., Dong, N., 2006. The Application of Post-Stack Seismic Attribute Analysis in the Oil-Gas Exploration and Development. Progress in Geophysics, 21(1): 161-166 (in Chinese with English abstract). |
| [32] |
Lü, W.Y., Zeng, L.B., Zhou, S.B., et al., 2020. Microfracture Characteristics and Its Controlling Factors in the Tight Oil Sandstones in the Southwest Ordos Basin: Case Study of the Eighth Member of the Yanchang Formation in Honghe Oilfield. Natural Gas Geoscience, 31(1): 37-46 (in Chinese with English abstract). |
| [33] |
Qu, Z.P., Wang, F.F., Zhang, Y.Y., et al., 2021. Thickness Prediction of Seismic Multi-Attributes Sand Based on Association Rules and Random Forests. Bulletin of Geological Science and Technology, 40(3): 211-218 (in Chinese with English abstract). |
| [34] |
Shang, X. F., Long, S. X., Duan, T. Z., 2021. Fracture System in Shale Gas Reservoir: Prospect of Characterization and Modeling Techniques. Journal of Natural Gas Geoscience, 6(3): 157-172. https://doi.org/10.1016/j.jnggs.2021.06.001 |
| [35] |
Sun, B., Wang, J.D., Chen, H.Y., et al., 2014. Diversity Measures in Ensemble Learning. Control and Decision, 29(3): 385-395 (in Chinese with English abstract). |
| [36] |
Sun, F.T., Wang, L., Wang, H.Q., et al., 2021. Application of Dipole Acoustic Logging Data in the Evaluation of Reservoir Fractures. Journal of Chongqing University of Science and Technology (Natural Sciences Edition), 23(1): 26-30 (in Chinese with English abstract). |
| [37] |
Sun, S., Zhao, S.X., Hou, J.G., et al., 2019. Hierarchical Modeling of Multi-Scale Fractures in Tight Sandstones: A Case Study of the Eighth Member of the Yanchang Formation in Wellblock 92 of the Honghe Oilfield. Petroleum Science Bulletin, 4(1):11-26 (in Chinese with English abstract). |
| [38] |
Sun, Z.X., Jiang, B.S., Xiao, K., et al., 2020. Prediction of Fracture Aperture in Bedrock Buried Hill Oil Reservoir Based on Novel Ensemble Learning Algorithm. Petroleum Geology and Recovery Efficiency, 27(3): 32-38 (in Chinese with English abstract). |
| [39] |
Sun, Z.Y., Peng, S.P., Zou, G.G., 2017. Automatic Identification of Small Faults Based on SVM and Seismic Data. Journal of China Coal Society, 42(11): 2945-2952 (in Chinese with English abstract). |
| [40] |
Tootkaboni, M. G., Ebadati, N., Naderi, A., 2021.3D Simulation of a Giant Oilfield in Calcareous Formations and Scrutiny Study of the Interaction of the Calculated Parameters (Asmari Formation in Maroon Oilfield, Iran). Arabian Journal of Geosciences, 14(9): 799. https://doi.org/10.1007/s12517-021-07141-z |
| [41] |
Wang, H.Q., Yang, W.Y., Xie, C.H., et al., 2014. Azimuthal Anisotropy Analysis of Different Seismic Attributes and Fracture Prediction. Oil Geophysical Prospecting, 49(5): 925-931 (in Chinese with English abstract). |
| [42] |
Wang, X.Y., Zeng, L.B., Wei, H.H., et al., 2018. Research Progress of the Fractured-Vuggy Reservoir Zones in Carbonate Reservoir. Advances in Earth Science, 33(8):818-832 (in Chinese with English abstract). |
| [43] |
Xiao, Y., Liu, G.P., Han, C.Y., et al., 2018. Development Characteristics and Main Controlling Factors of Natural Fractures in Deep Carbonate Reservoirs in the Jizhong Depression. Natural Gas Industry, 38(11): 33-42 (in Chinese with English abstract). |
| [44] |
Xie, Y. X., Zhu, C. Y., Zhou, W., et al., 2018. Evaluation of Machine Learning Methods for Formation Lithology Identification: A Comparison of Tuning Processes and Model Performances. Journal of Petroleum Science and Engineering, 160: 182-193. https://doi.org/10.1016/j.petrol.2017.10.028 |
| [45] |
Yu, A., Guo, J.L., Qing, Y., et al., 2021.Deep Convolutional Neural Network for Automatic Fault Recognition from 3D Seismic Datasets. Computers & Geosciences, 153:104776. https://doi.org/10.1016/j.cageo.2021.104776 |
| [46] |
Zeng, L.B., 2008. Formation and Distribution of Fractures in Low Permeability Sandstone Reservoirs. Science Press, Beijing, 1-27 (in Chinese). |
| [47] |
Zeng, L.B., Ke, S.Z., Liu,Y., 2010.Fracture Research Method for Low Permeability Oil and Gas Reservoir. Petroleum Industry Press, Beijing, 1-14 (in Chinese). |
| [48] |
Zeng, L.B., Lyu, P., Qu, X.F., et al., 2020. Multi-Scale Fractures in Tight Sandstone Reservoirs with Low Permeability and Geological Conditions of Their Development. Oil & Gas Geology, 41(3): 449-454 (in Chinese with English abstract). |
| [49] |
Zhang, W. H., Yu, J. Q., Zhao, A. J., et al., 2021. Predictive Model of Cooling Load for Ice Storage Air-Conditioning System by Using GBDT. Energy Reports, 7: 1588-1597. https://doi.org/10.1016/j.egyr.2021.03.017 |
| [50] |
Zhao, X.Y., Hu, X.Y., Zeng, L.B., et al., 2017. Evaluation on the Effectiveness of Natural Fractures in Reef-Flat Facies Reservoirs of Changxing Fm in Yuanba Area, Sichuan Basin. Natural Gas Industry, 37(2): 52-61 (in Chinese with English abstract). |
| [51] |
Zhu, Z.Y., Bai, X.Z., Xu, L., et al., 2021. Medium Term Prediction of Power Consumption of a Crude Oil Pipeline Based on a Bootstrap Method and Support Vector Machine Theory. Petroleum Science Bulletin, 6(1):127-137 (in Chinese with English abstract). |
| [52] |
Zou, C.N., Zhai, G.M., Zhang, G.Y., et al., 2015. Formation, Distribution, Potential and Prediction of Global Conventional and Unconventional Hydrocarbon Resources. Petroleum Exploration and Development, 42(1): 13-25 (in Chinese with English abstract). |
| [53] |
常德宽, 雍学善, 王一惠, 等, 2021. 基于深度卷积神经网络的地震数据断层识别方法. 石油地球物理勘探, 56(1): 1-8. |
| [54] |
董少群, 吕文雅, 夏东领, 等, 2020. 致密砂岩储层多尺度裂缝三维地质建模方法. 石油与天然气地质, 41(3):627-637. |
| [55] |
董少群,曾联波,车小花,等,2023.人工智能在致密储层裂缝测井识别中的应用.地球科学, 48(7):1-12. |
| [56] |
董少群, 曾联波, Xu, C.S., 等, 2018. 储层裂缝随机建模方法研究进展. 石油地球物理勘探, 53(3): 625-641. |
| [57] |
杜相仪, 董少群, 曾联波, 等, 2021. 碳酸盐岩铸体薄片面孔自动提取研究. 地质论评, 67(6): 1910-1921. |
| [58] |
谷宇峰, 张道勇, 鲍志东, 等, 2021. 利用梯度提升决策树(GBDT)预测渗透率——以姬塬油田西部长4+5段致密砂岩储层为例. 地球物理学进展, 36(2):585-594. |
| [59] |
郝慧珍, 顾庆, 胡修棉, 2021. 基于机器学习的矿物智能识别方法研究进展与展望. 地球科学, 46(9):3091-3106. |
| [60] |
何健, 武刚, 聂文亮, 等, 2020. 基于近似支持向量机的裂缝分类方法. 岩性油气藏, 32(2): 115-121. |
| [61] |
胡庆辉, 李志远, 2016. 基于Boosting框架的非稀疏多核学习方法. 计算机应用研究, 33(11): 3219-3222. |
| [62] |
黄凤祥, 夏振宇, 桂红兵, 等, 2016. 基于BP神经网络裂缝预测方法在DMT凹陷潜山变质岩中的应用研究. 工程地球物理学报, 13(4): 483-490. |
| [63] |
黄金超, 马颖华, 齐开悦, 等, 2018. 一种基于集成学习的入侵检测算法. 上海交通大学学报, 52(10): 1382-1387. |
| [64] |
贾承造, 2017. 论非常规油气对经典石油天然气地质学理论的突破及意义. 石油勘探与开发, 44(1): 1-11. |
| [65] |
贾承造, 郑民, 张永峰, 2012. 中国非常规油气资源与勘探开发前景. 石油勘探与开发, 39(2):129-136. |
| [66] |
李峰峰, 郭睿, 刘立峰, 等, 2021. 伊拉克M油田白垩系Mishrif组潟湖环境碳酸盐岩储集层成因机理. 地球科学, 46(1):228-241. |
| [67] |
李艳芳, 程建远, 王成, 2012. 基于支持向量机的地震属性优选及煤层气预测. 煤田地质与勘探, 40(6): 75-78. |
| [68] |
廖宗湖, 陈伟伦, 李薇, 等, 2020. 川东北须家河组致密砂岩断缝系统Ⅰ: 断层破碎带的平面分布特征. 石油科学通报, 5(4):441-448. |
| [69] |
刘国平, 董少群, 李洪楠, 等, 2020. 辽河盆地西部凹陷古潜山天然裂缝特征及其影响因素. 石油与天然气地质, 41(3): 525-533. |
| [70] |
刘俊州, 韩磊, 时磊, 等, 2021. 致密砂岩储层多尺度裂缝地震预测技术——以川西XC地区为例. 石油与天然气地质, 42(3): 747-754. |
| [71] |
刘小兵, 温志新, 贺正军, 等, 2019. 中东扎格罗斯盆地: 沿走向变化的构造及油气特征. 岩石学报, 35(4): 1269-1278. |
| [72] |
吕公河, 于常青, 董宁, 2006. 叠后地震属性分析在油气田勘探开发中的应用. 地球物理学进展, 21(1): 161-166. |
| [73] |
吕文雅, 曾联波, 周思宾, 等, 2020. 鄂尔多斯盆地西南部致密砂岩储层微观裂缝特征及控制因素——以红河油田长8储层为例. 天然气地球科学, 31(1): 37-46. |
| [74] |
曲志鹏, 王芳芳, 张云银, 等, 2021. 基于关联规则与随机森林的地震多属性砂体厚度预测. 地质科技通报, 40(3): 211-218. |
| [75] |
孙博, 王建东, 陈海燕, 等, 2014. 集成学习中的多样性度量. 控制与决策, 29(3): 385-395. |
| [76] |
孙福亭, 王龙, 汪洪强, 等, 2021. 偶极声波测井资料在储层裂缝评价中的应用. 重庆科技学院学报(自然科学版), 23(1): 26-30. |
| [77] |
孙爽, 赵淑霞, 侯加根, 等, 2019. 致密砂岩储层多尺度裂缝分级建模方法——以红河油田92井区长8储层为例. 石油科学通报, 4(1): 11-26. |
| [78] |
孙振宇, 彭苏萍, 邹冠贵, 2017. 基于SVM算法的地震小断层自动识别. 煤炭学报, 42(11): 2945-2952. |
| [79] |
孙致学, 姜宝胜, 肖康, 等, 2020. 基于新型集成学习算法的基岩潜山油藏储层裂缝开度预测算法. 油气地质与采收率, 27(3): 32-38. |
| [80] |
王洪求, 杨午阳, 谢春辉, 等, 2014. 不同地震属性的方位各向异性分析及裂缝预测. 石油地球物理勘探, 49(5): 925-931. |
| [81] |
王小垚, 曾联波, 魏荷花, 等, 2018. 碳酸盐岩储层缝洞储集体研究进展. 地球科学进展, 33(8):818-832. |
| [82] |
肖阳, 刘国平, 韩春元, 等, 2018. 冀中坳陷深层碳酸盐岩储层天然裂缝发育特征与主控因素. 天然气工业, 38(11): 33-42. |
| [83] |
曾联波,2008.低渗透砂岩储层裂缝的形成与分布.北京:科学出版社,1-27. |
| [84] |
曾联波,柯式镇,刘洋,2010.低渗透油气储层裂缝研究方法.北京:石油工业出版社,1-14. |
| [85] |
曾联波, 吕鹏, 屈雪峰, 等, 2020. 致密低渗透储层多尺度裂缝及其形成地质条件. 石油与天然气地质, 41(3): 449-454. |
| [86] |
赵向原, 胡向阳, 曾联波, 等, 2017. 四川盆地元坝地区长兴组礁滩相储层天然裂缝有效性评价. 天然气工业, 37(2): 52-61. |
| [87] |
朱振宇, 白小众, 徐磊, 等, 2021. 基于自取法和支持向量机原理的原油管道运行电耗中期预测方法研究. 石油科学通报, 6(1):127-137. |
| [88] |
邹才能, 翟光明, 张光亚, 等, 2015. 全球常规‒非常规油气形成分布、资源潜力及趋势预测. 石油勘探与开发, 42(1): 13-25. |
国家自然科学基金青年项目(42002134)
中国博士后科学基金第14批特别资助项目(2021T140735)
/
| 〈 |
|
〉 |