This study proposed a fracture prediction method based on unsupervised clustering of fracture sensitivity attributes to accurately characterize the distribution of fractures with different attitudes in tight sandstones of the Upper Triassic Xujiahe formation in the Yuanba area, northeastern Sichuan. First, the sensitivity of fractures was extracted and selected based on the optimized post-stack seismic data. Then, the convolutional neural network, a deep learning algorithm, was used to learn global massive fault and fracture databases of various types, obtaining the intensities, dip angles, and azimuths of fractures. In combination with high-precision-guided curvature attributes, an unsupervised clustering algorithm based on the Bayesian probability model was used to predict the intensities of fractures with different dip angles through dimensionality reduction using principal component analysis (PCA). The prediction results are highly consistent with both the fracture interpretation results from imaging logs and the geological results. The results of this study show that the third member of the Xujiahe Formation has more developed fractures than the second member. Fractures in the third member include both the fault-induced fractures distributed near the faults in the southeast flank of the Jiulongshan anticline and the fold-induced fractures in the areas with large formation flexures. By contrast, only fault-induced fractures near the faults occur in the second member.
Zou C N, Yang Z, Zhu R K, et al. Progress in China’s unconventional oil & gas exploration and development and theoretical technologies[J]. Acta Geologica Sinica, 2015, 89(6):979 -1007.
Lyu X Y, Jiang Y L, Liu J D, et al. Lower limits of porosity and permeability of tight sandstone gas reservoirs in the middle-lower 3Es in Duzhai area,Dongpu depression[J]. Geological Science and Technology Information, 2017, 36(3):182-188.
Yuan J, Cao Y, Li J, et al. Diversities and disparities of fracture systems in the Paleogene in DN gas field,Kuqa Depression,Tarim Basin[J]. Oil & Gas Geology, 2017, 38(5):840-850.
Xie Q H, Jiang L W, Zhao C D, et al. Application study of improving the precision of the ant-tracking-based fracture prediction technique[J]. Geophysical and Geochemical Exploration, 2021, 45(5):1295-1302.
Dai R X, Ran Q, Guan X, et al. A comprehensive seismic method for multi- scale fracture prediction:A case study on Lower Cambrian Longwangmiao Formation gas reservoir,Central Sichuan Basin[J]. Natural Gas Exploration and Development, 2017, 40(2):38-44.
Xie R, Yan J G, Chen Q. Prestack inversion of anisotropic coefficients and its application in fracture prediction[J]. Geophysical and Geochemical Exploration, 2022, 46(4):968-976.
Liu J Z, Han L, Shi L, et al. Seismic prediction of tight sandstone reservoir fractures in XC area,western Sichuan Basin[J]. Oil & Gas Geology, 2021, 42(3):747-754.
Zeng L B, Lyu W Y, Xu X, et al. Development characteristics,formation mechanism and hydrocarbon significance of bedding fractures in typical tight sandstone and shale[J]. Acta Petrolei Sinica, 2022, 43(2):180-191.
Zhang L, He F, Chen X Z, et al. Quantitative characterization of fault identification using likelihood attribute based on dip-steering filter control[J]. Lithologic Reservoirs, 2020, 32(2):108-114.
Xie S L, Ning S H, Zeng D L, et al. Recognition of minor faults by dip structure oriented filtering[J]. China’s Manganese Industry, 2017, 35(2):79-81.
[13]
Hoecker C, Fehmers G. Fast structural interpretation with structure-oriented filtering[J]. The Leading Edge, 2002: 21(2):238-243.
doi: 10.1190/1.1463775
Bai X F, Huo J J, Zhu M, et al. Reservoir prediction technique on restrain of dip steering cube[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2014, 36(1):107-112.
Si L, Wang Y H, Tong H M, et al. 3D visualization well-seismic match fault interpretation based on seismic attribute[J]. Reservoir Evaluation and Development, 2013, 3(3):1-4.
Liu D. Research and application of lower-class faults description technology:A case study in the north area of Bamianhe oilfield[J]. Petrochemical Industry Technology, 2020, 27(4):122-123.
[18]
穆龙新, 赵国良, 田中元, 等. 储层裂缝预测研究[M]. 北京: 石油工业出版社, 2009.
[18]
Mu L X, Zhao G L, Tian Z Y, et al. Research on reservoir fracture prediction[M]. Beijing: Petroleum Industry Press, 2009.
Zhen Z Y, Zheng J F, Sun J L, et al. Fault ientification method based on the maximum likelihood attribute and its application[J]. Progress in Geophysics, 2020, 35(1):374-378.
[20]
Hale D. Methods to compute fault images,extract fault surfaces,and estimate fault throws from 3D seismic images[J]. Geophysics, 2013: 78(2):33-43.
Zhou Y H, Gao J H. Application of local structural entropy measure on the detection of discontimuity of seismic data[J]. Coal Geology & Exploration, 2007, 35(1):71-73.
He F Q, Liang C C, Lu C, et al. Identification and description of fault-fracture bodies in tight and low permeability reservoirs in transitional zone at the south margin of Ordoc Basin[J]. Oil & Gas Geology, 2020, 41(4):710-718.
Li W, Chen G, Wang D X, et al. Identification of micro fault opening in sweet-spot member of Lucaogou Formation in Jimusar Sag of Junggar Basin by maximum positive and negative curvature[J]. OGP, 2022, 57(1):184-193.