A log-based lithofacies identification method based on random forest and sedimentary microfacies characteristics:A case study of tight sandstones in the second member of the Xujiahe Formation in the Xinchang area
HE Xiao-Long(), ZHANG Bing(), YANG Kai, HE Yi-Fan, LI Zhuo
Key Laboratory of Earth Exploration and Information Techniques,Ministry of Education,Chengdu University of Technology,Chengdu 610059,China
Tight sandstones serve as significant oil and gas reservoirs.Their lithofacies identification can assist in further understanding the developmental characteristics of reservoirs.Combining core observations with log data processing,this study analyzed the lithofacies and sedimentary microfacies characteristics of tight sandstones in the Xinchang area and the internal relationships between lithofacies and sedimentary microfacies.Moreover,it constructed a random forest classification model with geological implications through data mining of sedimentary microfacies characteristics.The results show that:(1)Tight sandstones in the Xinchang area can be classified into seven typical lithofacies,including mudstone,siltstone with ripple lamination,massive fine sandstone,fine sandstone with parallel bedding,massive medium- to coarse-grained sandstone,and medium- to coarse-grained sandstone with parallel/cross bedding;(2)The sedimentary microfacies in the Xinchang area consist primarily of subaqueous distributary channel,subaqueous distributary bay,river-mouth bar,and prodeltaic mud,which are closely associated with the sedimentation of lithofacies;(3)In the classification model,the relative centroid(RM),root mean square deviation(GS),average median(AM),and average slope(M) of the gamma ray(GR) curve can be used as the characteristic parameters of sedimentary microfacies to increase the number of characteristics in the dataset;(4)Considering the characteristics of sedimentary microfacies,especially the energy and turbulence of water bodies,can significantly enhance the performance of the random forest classification model.Overall,the results of this study provide a novel approach for lithofacies identification using machine learning methods and a significant reference for oil and gas exploration in tight sandstones.
Xiao-Long HE,Bing ZHANG,Kai YANG, et al. A log-based lithofacies identification method based on random forest and sedimentary microfacies characteristics:A case study of tight sandstones in the second member of the Xujiahe Formation in the Xinchang area[J]. Geophysical and Geochemical Exploration,
2024, 48(5): 1337-1347.
Gu S, Wang W J, Gao Q, et al. Management mechanism of large-scale benefit development of tight sandstone gas[J]. Natural Gas Industry, 2023, 43(5):100-107.
Ren R C, Zeng J C, Liang B. Study on sandstone architecture and patterns of F19 block in Gangxi Oilfield[J]. Mud Logging Engineering, 2022, 33(2):122-128.
[3]
Miall A D. Lithofacies types and vertical profile models in braided river deposits:a summary[G]//Miall A D. Fluvial Sedimentology.AAPG Memoir 5,1977:597-604.
[4]
Blair T C, McPherson J G. Alluvial fans and their natural distinction from rivers based on morphology,hydraulic processes,sedimentary processes,and facies assemblages[J]. Journal of Sedimentary Research, 1994, 64(3a):450-489.
[5]
Sulpizio R, Dellino P, Doronzo D M, et al. Pyroclastic density currents:State of the art and perspectives[J]. Journal of Volcanology and Geothermal Research, 2014,283:36-65.
Deng Y, Chen X, Qin J H, et al. Paleogeomorphology and favorable reservior distribution of the first member of Permian Lucaogou Formation in Jimsar Sag[J]. Lithologic Reservoirs, 2024, 36(1):136-144.
Lai J, Li H B, Zhang M, et al. Advances in well logging geology in the era of unconventional hydrocarbon resources[J]. Journal of Palaeogeography:Chinese Edition, 2023, 25(5):1118-1138.
Che S Q. Shale lithofacies identification and classification by using logging data:A case of Wufeng-Longmaxi Formation in Fuling gas field,Sichuan Basin[J]. Lithologic Reservoirs, 2018, 30(1):121-132.
Liu J L, Liu Z Q, Xiao K H, et al. Characterization of favorable lithofacies in tight sandstone reservoirs and its significance for gas exploration and exploitation:A case study of the 2nd Member of Triassic Xujiahe Formation in the Xinchang Area,Sichuan Basin[J]. Petroleum Exploration and Development, 2020, 47(6):1111-1121.
Yang Y, Shi W Z, Zhang X M, et al. Identification method of shale lithofacies by logging curves:A case study from Wufeng-Longmaxi Formation in Jiaoshiba Area,SW China[J]. Lithologic Reservoirs, 2021, 33(2):135-146.
[11]
Al-Mudhafar W J. Integrating well log interpretations for lithofacies classification and permeability modeling through advanced machine learning algorithms[J]. Journal of Petroleum Exploration and Production Technology, 2017, 7(4):1023-1033.
Jiang L, Zhang Z M, Wang Q W, et al. Comparative study on lithology classification of oil logging data based on different machine learning models[J]. Geophysical and Geochemical Exploration, 2024, 48(2):489-497.
Wang M, Yang J L, Wang X, et al. Identification of shale lithofacies by well logs based on random forest algorithm[J]. Earth Science, 2023, 48(1):130-142.
Gao F, Qu Z P, Wei Z, et al. A study on well-log lithofacies classification based on machine learning methods[J]. Progress in Geophysics, 2024, 39(3):1173-1192..
Li H B, Wang G W, Wang S, et al. Shale oil lithofacies identification by kohonen neural network method:The case of the Permian Lucaogou Formation in Jimusaer Sag[J]. Acta Sedimentologica Sinica, 2022, 40(3):626-640.
Pang G Y, Tang J, Wang Q, et al. Prediction of diagenetic facies with probabilistic neural network:Taking member Chang 8 of Heshui Area in Ordos Basin as an example[J]. Special Oil & Gas Reservoirs, 2013, 20(2):43-47,152-153.
[17]
张昌民, 张祥辉, Adrian J.Hartley, 等. 分支河流体系分类初探[J]. 岩性油气藏, 2023, 35(4):1-15.
[17]
Zhang C M, Zhang X H, Hartley A J, et al. On classification of distributive fluvial system[J]. Lithologic Reservoirs, 2023, 35(4):1-15.
Li P W, Hu Z Q, Liu Z Q, et al. Types of the deep tight sandstone reservoirs and their different controlling in the T3x2 member of Xujiahe formation in Xinchang area,western Sichuan Basin[J]. Natural Gas Geoscience, 2024, 35(7):1136-1149..
Wang Z K. Provenance characteristics and its relationship with the reservoir of the 2nd member of Xujiahe Formation in Xinchang,western Sichuan depression[D]. Chengdu: Chengdu University of Technology, 2021.
Zheng H R, Liu Z Q, Xu S L, et al. Progress and key research directions of tight gas exploration and development in Xujiahe Formation,Sinopec exploration areas,Sichuan Basin[J]. Oil & Gas Geology, 2021, 42(4):765-783.
Su J L, Lin L B, Yu Y, et al. Comparative study on the provenance and reservoir characteristics of the second and fourth members of the Upper Triassic Xujiahe Formation in the Xinchang Area,western Sichuan,China[J]. Acta Sedimentologica Sinica, 2023, 41(5):1451-1467.
Liu J L, Ji Y L, Yang K M, et al. Tectono-stratigraphy and sedimentary infill characteristics of Xujiahe Formation in western Sichuan foreland basin[J]. Journal of China University of Petroleum:Edition of Natural Science, 2015, 39(6):11-23.
[23]
Efron B, Tibshirani R J. An introduction to the bootstrap[M]. New York: Chapman and Hall/CRC,1994.
Pan D, Zhuge Y Y, Ye W J, et al. New method for identification of fluid with log facies in Maxi area[C]// Xi'an Shiyou University,Shaanxi Petroleum Society.Proceedings of the 2018 International Field Exploration and Development Conference(IFEDC 2018).Hebei Branch,CNPC Logging Co.,Ltd.,2018:10.
Li Z H, Huang W H. Lithofacies characteristics and sedimentary model of braided delta:A case study of He8 member in the southern Sulige,Ordos Basin[J]. Lithologic Reservoirs, 2017, 29(1):43-50.
