塔里木盆地顺北油田超深断溶体深度学习地质建模方法
Deep learning-based geological modeling of ultra-deep fault-karst reservoirs in Shunbei oilfield, Tarim Basin
- 2023年44卷第1期 页码:203-212
收稿:2022-05-31,
修回:2022-11-11,
纸质出版:2023-02-01
DOI: 10.11743/ogg20230117
移动端阅览
收稿:2022-05-31,
修回:2022-11-11,
纸质出版:2023-02-01
移动端阅览
断控缝洞型储层是分布在中国塔里木盆地奥陶系的一种特殊类型储层,具有埋藏深、成因复杂、非均质性强等特点,受限于井资料稀疏和地震品质低等因素,断控缝洞型储层的准确表征与精细建模面临重要挑战。综合钻测井、岩心、野外露头及三维地震信息,在断控缝洞型储层构型模式指导下,构建了断溶体深度学习训练样本;在深度学习网络综合分析基础上,提出了适用于深层断溶体的深度学习建模方法。研究结果表明:深层少井资料条件下,基于多源数据综合建立的“原位等尺度”训练样本是断溶体深度学习建模的基础;优选的地质体目标图像转换网络可以较好地实现从地震数据到断溶体储层的直接预测。在训练网络搭建基础上,建立了塔里木盆地顺北油田5号断裂带南段的断溶体储层三维模型,该模型多维度符合断控岩溶地质模式及分布规律,与基于钻井资料的储层预测符合率较高。提升断溶体深度学习地质建模的精度和条件化程度是未来的努力攻关方向之一。
Fault-karst reservoir is of a special type distributed in the Ordovician strata in the Tarim Basin, China. It’s characterized by deep burial, complex genesis and strong heterogeneity. Due to sparse well data and low seismic quality and other adverse conditions, its accurate characterization and fine modeling are faced with great challenges. In the study, an integration of drilling, core, outcrop and 3D seismic data is applied to build a deep learning-based training dataset for the fault-karst reservoir with the guidance of architecture mode of fault-controlled fractured-vuggy reservoir. Based on the comprehensive analysis of deep learning network, we propose a deep learning-based modeling method suitable for fault-karst reservoirs. The results show that the “in-situ, equal-scale” training dataset established based on multi-source data is the basis for deep learning-based modeling of fault-karst reservoirs. The selected pix 2 pix (P2P) neural network could realize the 3D model prediction of fault-karst reservoirs by seismic data. A 3D fault-karst reservoir model is then established for the south segment of the No. 5 fault zone in Shunbei area following the built of training network. The model is conformed to the geological mode and distribution pattern of the reservoir type on all fronts, and also highly consistent with the reservoir prediction based on drilling data. One of the key research directions therefore lies in improving the accuracy and conditional degree of deep learning-based geological modeling of fault-karst reservoirs.
云露 , 朱秀香 . 一种新型圈闭: 断控缝洞型圈闭 [J]. 石油与天然气地质 , 2022 , 43 ( 1 ): 34 - 42 .
YUN Lu , ZHU Xiuxiang . A new trap type: Fault-controlled fracture-vuggy trap [J]. Oil & Gas Geology , 2022 , 43 ( 1 ): 34 - 42 .
漆立新 , 云露 , 曹自成 , 等 . 顺北油气田地质储量评估与油气勘探方向 [J]. 新疆石油地质 , 2021 , 42 ( 2 ): 127 - 135 .
QI Lixin , YUN Lu , CAO Zicheng , et al . Geological reserves assessment and petroleum exploration targets in Shunbei Oil & Gas Field [J]. Xinjiang Petroleum Geology , 2021 , 42 ( 2 ): 127 - 135 .
焦方正 . 塔里木盆地顺北特深碳酸盐岩断溶体油气藏发现意义与前景 [J]. 石油与天然气地质 , 2018 , 39 ( 2 ): 207 - 216 .
JIAO Fangzheng . Significance and prospect of ultra-deep carbonate fault-karst reservoirs in Shunbei area, Tarim Basin [J]. Oil & Gas Geology , 2018 , 39 ( 2 ): 207 - 216 .
况安鹏 , 曹东升 , 曾联波 , 等 . 顺北地区超深层碳酸盐岩断溶体钻录井识别 [J]. 石油地质与工程 , 2021 , 35 ( 3 ): 35 - 40 .
KUANG Anpeng , CAO Dongsheng , ZENG Lianbo , et al . Drilling and logging identification of the ultra-deep carbonate fault-karst reservoirs in Shunbei area of Tarim Basin [J]. Petroleum Geology and Engineering , 2021 , 35 ( 3 ): 35 - 40 .
云露 . 顺北地区奥陶系超深断溶体油气成藏条件 [J]. 新疆石油地质 , 2021 , 42 ( 2 ): 136 - 142 .
YUN Lu . Hydrocarbon accumulation of ultra-deep Ordovician fault-karst reservoirs in Shunbei area [J]. Xinjiang Petroleum Geology , 2021 , 42 ( 2 ): 136 - 142 .
吕海涛 , 韩俊 , 张继标 , 等 . 塔里木盆地顺北地区超深碳酸盐岩断溶体发育特征与形成机制 [J]. 石油实验地质 , 2021 , 43 ( 1 ): 14 - 22 .
LYU Haitao , HAN Jun , ZHANG Jibiao , et al . Development characteristics and formation mechanism of ultra-deep carbonate fault-dissolution body in Shunbei area, Tarim Basin [J]. Petroleum Geology and Experiment , 2021 , 43 ( 1 ): 14 - 22 .
邓尚 , 李慧莉 , 张仲培 , 等 . 塔里木盆地顺北及邻区主干走滑断裂带差异活动特征及其与油气富集的关系 [J]. 石油与天然气地质 , 2018 , 39 ( 5 ): 878 - 888 .
DENG Shang , LI Huili , ZHANG Zhongpei , et al . Characteristics of differential activities in major strike-slip fault zones and their control on hydrocarbon enrichment in Shunbei area and its surroundings, Tarim Basin [J]. Oil & Gas Geology , 2018 , 39 ( 5 ): 878 - 888 .
邓尚 , 李慧莉 , 韩俊 , 等 . 塔里木盆地顺北5号走滑断裂中段活动特征及其地质意义 [J]. 石油与天然气地质 , 2019 , 40 ( 5 ): 990 - 998, 1073 .
DENG Shang , LI Huili , HAN Jun , et al . Characteristics of the central segment of Shunbei 5 strike-slip fault zone in Tarim Basin and its geological significance [J]. Oil & Gas Geology , 2019 , 40 ( 5 ): 990 - 998, 1073 .
韩俊 , 况安鹏 , 能源 , 等 . 顺北5号走滑断裂带纵向分层结构及其油气地质意义 [J]. 新疆石油地质 , 2021 , 42 ( 2 ): 152 - 160 .
HAN Jun , KUANG Anpeng , NENG Yuan , et al . Vertical layered structure of Shunbei No.5 strike-slip fault zone and its significance on hydrocarbon accumulation [J]. Xinjiang Petroleum Geology , 2021 , 42 ( 2 ): 152 - 160 .
赵锐 , 赵腾 , 李慧莉 , 等 . 塔里木盆地顺北油气田断控缝洞型储层特征与主控因素 [J]. 特种油气藏 , 2019 , 26 ( 5 ): 8 - 13 .
ZHAO Rui , ZHAO Teng , LI Huili , et al . Fault-controlled fracture-cavity reservoir characterization and main-controlling factors in the Shunbei hydrocarbon field of Tarim Basin [J]. Special Oil & Gas Reservoirs , 2019 , 26 ( 5 ): 8 - 13 .
郑函庆 , 丁心鲁 , 刘学清 , 等 . 塔里木盆地碳酸盐岩缝洞型储层试井资料特征及KT1井储层缝洞组合关系认识 [J]. 石油地质与工程 , 2021 , 35 ( 4 ): 26 - 29, 37 .
ZHENG Hanqing , DING Xinlu , LIU Xueqing , et al . Well test data characteristics of fracture-cave reservoir in carbonate rocks of Tarim Basin and understanding of fracture-cave association of KT1 Well [J]. Petroleum Geology and Engineering , 2021 , 35 ( 4 ): 26 - 29, 37 .
刘宝增 . 塔里木盆地顺北地区油气差异聚集主控因素分析——以顺北1号、顺北5号走滑断裂带为例 [J]. 中国石油勘探 , 2020 , 25 ( 3 ): 83 - 95 .
LIU Baozeng . Analysis of main controlling factors of oil and gas differential accumulation in Shunbei area, Tarim Basin—taking Shunbei No.1 and No.5 strike slip fault zones as examples [J]. China Petroleum Exploration , 2020 , 25 ( 3 ): 83 - 95 .
何治亮 , 马永生 , 朱东亚 , 等 . 深层-超深层碳酸盐岩储层理论技术进展与攻关方向 [J]. 石油与天然气地质 , 2021 , 42 ( 3 ): 533 - 546 .
HE Zhiliang , MA Yongsheng , ZHU Dongya , et al . Theoretical and technological progress and research direction of deep and ultra-deep carbonate reservoirs [J]. Oil & Gas Geology , 2021 , 42 ( 3 ): 533 - 546 .
张文彪 , 段太忠 , 李蒙 , 等 . 塔河油田托甫台区奥陶系断溶体层级类型及表征方法 [J]. 石油勘探与开发 , 2021 , 48 ( 2 ): 314 - 325 .
ZHANG Wenbiao , DUAN Taizhong , LI Meng , et al . Architecture characterization of Ordovician fault-controlled paleokarst carbonate reservoirs in Tuoputai, Tahe Oilfield, Tarim Basin, NW China [J]. Petroleum Exploration and Development , 2021 , 48 ( 2 ): 314 - 325 .
商晓飞 , 段太忠 , 张文彪 , 等 . 断控岩溶主控的缝洞型碳酸盐岩内部溶蚀相带表征——以塔河油田10区奥陶系油藏为例 [J]. 石油学报 , 2020 , 41 ( 3 ): 329 - 341 .
SHANG Xiaofei , DUAN Taizhong , ZHANG Wenbiao , et al . Characterization of dissolution facies belt in fracture-cavity carbonate rocks mainly controlled by fault-controlling karst: A case study of Ordovician reservoirs in the Block 10 of Tahe Oilfieid [J]. Acta Petrolei Sinica , 2020 , 41 ( 3 ): 329 - 341 .
张文彪 , 张亚雄 , 段太忠 , 等 . 塔里木盆地塔河油田托甫台区奥陶系碳酸盐岩断溶体系层次建模方法 [J]. 石油与天然气地质 , 2022 , 43 ( 1 ): 207 - 218 .
ZHANG Wenbiao , ZHANG Yaxiong , DUAN Taizhong , et al . Hierarchy modeling of the Ordovician fault-karst carbonate reservoir in Tuoputai area, Tahe Oilfield, Tarim Basin, NW China [J]. Oil & Gas Geology , 2022 , 43 ( 1 ): 207 - 218 .
张文彪 , 段太忠 , 赵华伟 , 等 . 断控岩溶体系空间结构差异性与三维建模——以顺北1号断裂带为例 [J]. 科学技术与工程 , 2021 , 21 ( 28 ): 12094 - 12108 .
ZHANG Wenbiao , DUAN Taizhong , ZHAO Huawei , et al . Hierarchical characteristics and 3D modeling of fault-controlled paleokarst systems: A case study of Shunbei 1 strike-slip fault zone [J]. Science Technology and Engineering , 2021 , 21 ( 28 ): 12094 - 12108 .
DUAN Taizhong , ZHANG Wenbiao , LU Xinbian , et al . Architectural characterization of Ordovician fault-controlled paleokarst carbonate reservoirs, Tahe Oilfield, China [J]. Interpretation , 2020 , 8 ( 4 ): T953 - T965 .
DEUTSCH C V , WANG Libing . Hierarchical object-based stochastic modeling of fluvial reservoirs [J]. Mathematical Geology , 1996 , 28 ( 7 ): 857 - 880 .
刘彦锋 , 张文彪 , 段太忠 , 等 . 深度学习油气藏地质建模研究进展 [J]. 地质科技通报 , 2021 , 40 ( 4 ): 235 - 241 .
LIU Yanfeng , ZHANG Wenbiao , DUAN Taizhong , et al . Progress of deep learning in oil and gas reservoir geological modeling [J]. Bulletin of Geological Science and Technology , 2021 , 40 ( 4 ): 235 - 241 .
田启川 , 王满丽 . 深度学习算法研究进展 [J]. 计算机工程与应用 , 2019 , 55 ( 22 ): 25 - 33 .
TIAN Qichuan , WANG Manli . Research progress on deep learning algorithms [J]. Computer Engineering and Applications , 2019 , 55 ( 22 ): 25 - 33 .
李苍柏 , 范建福 , 宋相龙 . 深度学习在地质学上的应用 [J]. 地质学刊 , 2018 , 42 ( 1 ): 115 - 121 .
LI Cangbai , FAN Jianfu , SONG Xianglong . A study on application of deep learning in geology [J]. Journal of Geology , 2018 , 42 ( 1 ): 115 - 121 .
RONNEBERGER O , FISCHER P , BROX T . U-net: Convolutional networks for biomedical image segmentation [C]//NAVAB N, HORNEGGER J, WELLS W M, eds. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015 , Munich , 2015 . Cham : Springer , 2015: 234 - 241 .
SALIMANS T , GOODFELLOW I , ZAREMBA W , et al . Improved techniques for training GANs [C]//LEE D D, VON LUXBURG U, GARNETT R, eds. Proceedings of the 30th International Conference on Neural Information Processing Systems , Barcelona , 2016 . Red Hook : Curran Associates Inc. , 2016: 2234 - 2242 .
ARJOVSKY M , CHINTALA S , BOTTOU L . Wasserstein GAN [EB/OL]. ( 2017-12-06 )[ 2022-05-30 ]. https://arxiv.org/abs/1701.07875 https://arxiv.org/abs/1701.07875 .
GOODFELLOW I J , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [C]//GHAHRAMANI Z, WELLING M, CORTES C, eds. Proceedings of the 27th International Conference on Neural Information Processing Systems , Montreal , 2014 . Cambridge : MIT Press , 2014: 2672 - 2680 .
CHAVDAROVA T , FLEURET F . SGAN: An alternative training of generative adversarial networks [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition , Salt Lake City, 2018 . Piscataway, NJ : IEEE , 2018 : 9407 - 9415 .
YEH R A , CHEN Chen , LIM T Y , et al . Semantic image inpainting with deep generative models [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , Honolulu, 2017 . Piscataway, NJ : IEEE , 2017 : 6882 - 6890 .
CHAN S , ELSHEIKH A H . Parametrization of stochastic inputs using generative adversarial networks with application in geology [J]. Frontiers in Water , 2020 , 2 : 5 .
RUFFINO C , HÉRAULT R , LALOY E , et al . Pixel-wise conditioned generative adversarial networks for image synthesis and completion [EB/OL]. ( 2020-02-04 )[ 2022-05-30 ]. https://arxiv.org/abs/2002.01281 https://arxiv.org/abs/2002.01281 .
ZHANG Tuanfeng , TILKE P , DUPONT E , et al . Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks [J]. Petroleum Science , 2019 , 16 ( 3 ): 541 - 549 .
SONG Suihong , MUKERJI T , HOU Jiagen . Geological facies modeling based on progressive growing of generative adversarial networks (GANs) [J]. Computational Geosciences , 2021 , 25 ( 3 ): 1251 - 1273 .
SONG Suihong , MUKERJI T , HOU Jiagen . GANSim: Conditional facies simulation using an improved progressive growing of generative adversarial networks (GANs) [J]. Mathematical Geosciences , 2021 , 53 ( 7 ): 1413 - 1444 .
ISOLA P , ZHU Junyan , ZHOU Tinghui , et al . Image-to-image translation with conditional adversarial networks [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , Honolulu, 2017 . Piscataway, NJ : IEEE , 2017 : 5967 - 5976 .
DENTON E , CHINTALA S , SZLAM A , et al . Deep generative image models using a Laplacian pyramid of adversarial networks [C]//CORTES C, LEE D D, SUGIYAMA M, eds. Proceedings of the 28th International Conference on Neural Information Processing Systems , Montreal , 2015 . Cambridge : MIT Press , 2015: 1486 - 1494 .
KORJANI M , POPA A , GRIJALVA E , et al . A new approach to reservoir characterization using deep learning neural networks [C]// SPE Western Regional Meeting , Anchorage, 2016 . London : SPE , 2016 : SPE-180359-MS.
相关作者
相关机构
京公网安备11010802024621
