A Logging-Based Permeability Prediction Method Based on Dual-Driven Model for Low-Permeability Gas Reservoirs: A Case Study of Dongfang Gas Field in Yinggehai Basin

doi:10.7657/XJPG20250513

Abstract

Abstract:

Offshore low-permeability reservoirs are characterized by fine lithology, poor physical property, and strong heterogeneity, making permeability prediction highly challenging. To address this issue, a regression committee learning machine (RCLM) driven by both data and physics was developed for predicting permeability based on logging data for low-permeability reservoirs. On this basis, sweet spot evaluation and dynamic permeability prediction were conducted. The results show that compared with a simple learning machine, the RCLM not only guarantees the prediction accuracy but also achieves higher prediction stability; in comparison with conventional porosity-permeability models, the RCLM obtains superior accuracy (up to 94% within half an order of magnitude). The comprehensive logging-based sweet spot index established using logging curves and petrophysical parameters can be used to effectively identify sweet spots in reservoirs. The newly drilled wells have verified the applicability of the dynamic-static permeability transformation model, which can be used to predict well test-derived permeability during regionally progressive exploration and development. The proposed method has been successfully applied in reservoir evaluation in the Dongfang gas field of the Yinggehai Basin, demonstrating its practical value. This method may provide robust support for efficiently designing exploration and development plan for offshore gas fields.

Key words: Yinggehai Basin, Dongfang gas field, low-permeability reservoir, logging-based permeability, dynamic permeability, sweet spot evaluation, regression committee learning machine

CLC Number:

TE122.23

WU Bohan, LI Fang, TANG Di, WU Yixiong, LUO Yuhu, XIAO Dazhi, ZHANG Shunchao. A Logging-Based Permeability Prediction Method Based on Dual-Driven Model for Low-Permeability Gas Reservoirs: A Case Study of Dongfang Gas Field in Yinggehai Basin[J]. Xinjiang Petroleum Geology, 2025, 46(5): 622-629.

Figures/Tables 12

Fig. 1.

Fig. 2.

Table 1.

Fig. 3.

Fig. 4.

Fig. 5.

Table 2.

Fig. 6.

Fig. 7.

Fig. 8.

Table 3.

Fig. 9.

References 27

[1]	郑炀, 徐锦绣, 刘欢, 等. 基于随钻核磁测井的渗透率评价方法及其应用:以渤海锦州油田古近系沙河街组为例[J]. 中国海上油气, 2019, 31(2):69-75.
	ZHENG Yang, XU Jinxiu, LIU Huan, et al. A permeability evaluation method based on NMR logging while drilling and its application:Taking Paleogene Shahejie formation in Jinzhou oilfield of Bohai Sea as an example[J]. China Offshore Oil and Gas, 2019, 31(2):69-75.
[2]	吴勃翰. 致密砂岩储层孔隙结构评价方法及应用研究[D]. 北京: 中国石油大学(北京), 2022.
	WU Bohan. Study on the evaluation and application of pore structure in tight sandstone reservoir[D]. Beijing: China University of Petroleum(Beijing), 2022.
[3]	SHEN Bo, WU Dong, WANG Zhonghao. A new method for permeability estimation from conventional well logs in glutenite reservoirs[J]. Journal of Geophysics and Engineering, 2017, 14(5):1268-1274.
[4]	李雄炎, 秦瑞宝, 曹景记, 等. 白云岩储层特征与渗透率评价方法:以伊拉克美索不达米亚盆地古近系为例[J]. 中国海上油气, 2024, 36(3):81-94.
	LI Xiongyan, QIN Ruibao, CAO Jingji, et al. Dolomite reservoir characteristics and permeability evaluation methods:An example from the Paleogene,Mesopotamian Basin,Iraq[J]. China Offshore Oil and Gas, 2024, 36(3):81-94.
[5]	刘土亮, 胡向阳, 袁伟, 等. 取心井渗透率数值模拟及精细评价方法研究[J]. 录井工程, 2023, 34(4):55-60. doi: 10.3969/j.issn.1672-9803.2023.04.009
	LIU Tuliang, HU Xiangyang, YUAN Wei, et al. Research on numerical simulation and fine evaluation methods for permeability of cored wells[J]. Mud Logging Engineering, 2023, 34(4):55-60. doi: 10.3969/j.issn.1672-9803.2023.04.009
[6]	汤翟, 吴勃翰, 吴一雄, 等. 海上低渗气藏储层分类及测井渗透率精细评价:以莺琼盆地DF13-A气田为例[J/OL]. 中国海上油气:1-12. [2025-03-10]. ttps://link.cnki.net/urlid/11.5339.TE.20250307.1443.002 .
	TANG DI, WU Bohan, WU Yixiong, et al. Reservoir classification and fine logging permeability evaluation of offshore low-permeability gas reservoirs:A case study of the DF13-A gas field,Yingqiong Basin[J/OL]. China Offshore Oil and Gas:1-12. [2025-03-10]. ttps://link.cnki.net/urlid/11.5339.TE.20250307.1443.002 .
[7]	TIMUR A. Pulsed nuclear magnetic resonance studies of porosity,movable fluid,and permeability of sandstones[J]. Journal of Petroleum Technology, 1969, 21(6):775-786.
[8]	COATES G, DUMANOIR J L. A new approach to improved log-derived permeability[R]. SPWLA 14th Annual Logging Symposium, 1973.
[9]	郭同政, 申富豪, 饶博, 等. 各向异性孔隙地层随钻声波测井理论模拟及应用[J]. 科学技术与工程, 2023, 23(28):11962-11971.
	GUO Tongzheng, SHEN Fuhao, RAO Bo, et al. Theoretical simulation and application of acoustic logging while drilling in anisotropic porous formation[J]. Science Technology and Engineering, 2023, 23(28):11962-11971.
[10]	李宁, 徐彬森, 武宏亮, 等. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 2021, 42(4):508-522. doi: 10.7623/syxb202104008
	LI Ning, XU Binsen, WU Hongliang, et al. Application status and prospects of artificial intelligence in well logging and formation evaluation[J]. Acta Petrolei Sinica, 2021, 42(4):508-522. doi: 10.7623/syxb202104008
[11]	JAMSHIDIAN M, HADIAN M, ZADEH M M, et al. Prediction of free flowing porosity and permeability based on conventional well logging data using artificial neural networks optimized by imperialist competitive algorithm:A case study in the South Pars gas field[J]. Journal of Natural Gas Science and Engineering, 2015, 24:89-98.
[12]	ZHU Lingqi, ZHANG Chong, WEI Yang, et al. Permeability prediction of the tight sandstone reservoirs using hybrid intelligent algorithm and nuclear magnetic resonance logging data[J]. Arabian Journal for Science and Engineering, 2017, 42(4):1643-1654.
[13]	赵军, 张涛, 何胜林, 等. 基于参数优选的储层渗透率深度置信网络模型预测初探[J]. 油气藏评价与开发, 2021, 11(4):577-585.
	ZHAO Jun, ZHANG Tao, HE Shenglin, et al. Prediction of reservoir permeability by deep belief network based on optimized parameters[J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4):577-585.
[14]	SEN S, ABIOUI M, GANGULI S S, et al. Petrophysical heterogeneity of the Early Cretaceous Alamein dolomite reservoir from North Razzak oil field,Egypt integrating well logs,core measurements,and machine learning approach[J]. Fuel, 2021, 306(15):21698.
[15]	李宁, 王克文, 武宏亮, 等. 渗透率测井评价:现状及发展方向[J]. 石油科学通报, 2023, 8(4):432-444.
	LI Ning, WANG Kewen, WU Hongliang, et al. Permeability logging evaluation:Current status and development directions[J]. Petroleum Science Bulletin, 2023, 8(4):432-444.
[16]	CHEN Changhsu, LIN Zsayshing. A committee machine with empirical formulas for permeability prediction[J]. Computers & Geosciences, 2006, 32(4):485-496.
[17]	BAI Yang, TAN Maojin, SHI Yujiang, et al. Regression committee machine and petrophysical model jointly driven parameters prediction from wireline logs in tight sandstone reservoirs[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-9.
[18]	WU Bohan, XIE Ranhong, LIU Mi, et al. Novel method for predicting mercury injection capillary pressure curves of tight sandstone reservoirs using NMR T₂ distributions[J]. Energy & Fuels, 2021, 35(19):15607-15617.
[19]	吴克强, 裴健翔, 胡林, 等. 莺歌海盆地大—中型气田成藏模式及勘探方向[J]. 石油学报, 2023, 44(12):2200-2216. doi: 10.7623/syxb202312012
	WU Keqiang, PEI Jianxiang, HU Lin, et al. Accumulation model and exploration direction of medium-large gas fields in Yinggehai Basin[J]. Acta Petrolei Sinica, 2023, 44(12):2200-2216. doi: 10.7623/syxb202312012
[20]	李华, 杨朝强, 周伟, 等. 莺歌海盆地东方1-1气田中新统黄流组浅海多级海底扇形成机理及储层分布[J]. 石油与天然气地质, 2023, 44(2):429-440.
	LI Hua, YANG Zhaoqiang, ZHOU Wei, et al. Genetic mechanism and reservoir distribution of shallow-marine multi-stepped submarine fans in the Miocene Huangliu formation of Dongfang 1-1 gas field,Yinggehai Basin[J]. Oil & Gas Geology, 2023, 44(2):429-440.
[21]	关耀, 叶青, 张冲, 等. 高压低渗透碎屑岩储层孔隙结构特征及分类评价:以莺歌海盆地东方A-1区黄流组一段为例[J]. 东北石油大学学报, 2024, 48(5):75-89.
	GUAN Yao, YE Qing, ZHANG Chong, et al. Pore structure characteristics and classification evaluation of high-pressure and low-permeability clastic reservoirs:A case study of the Huangliu formation in the eastern A-1 area of Yinggehai Basin[J]. Journal of Northeast Petroleum University, 2024, 48(5):75-89.
[22]	GAO Lun, XIE Ranhong, GUO Jiangfeng, et al. Method for predicting mercury injection capillary pressure curve of tight sandstone using NMR data[R]. London,UK:81th EAGE Conference & Exhibition, 2019.
[23]	WU Bohan, XIE Ranhong, XU Chenyu, et al. A new method for predicting capillary pressure curves based on NMR echo data:Sandstone as an example[J]. Journal of Petroleum Science and Engineering, 2021, 202:108581.
[24]	唐军, 何泽, 申威, 等. 对标产能的碳酸盐岩储集层测井分类评价:以塔里木盆地托甫台地区一间房组为例[J]. 新疆石油地质, 2023, 44(1):112-118.
	TANG Jun, HE Ze, SHEN Wei, et al. Productivity-based classified logging evaluation of carbonate reservoirs:A case study on Yijianfang formation in Tuofutai area,Tarim Basin[J]. Xinjiang Petroleum Geology, 2023, 44(1):112-118.
[25]	WU Bohan, XIE Ranhong, XIAO Lizhi, et al. Integrated classification method of tight sandstone reservoir based on principal component analysis-simulated annealing genetic algorithm-fuzzy cluster means[J]. Petroleum Science, 2023, 20(5):2747-2758.
[26]	覃建华, 李映艳, 杜戈峰, 等. 基于核磁共振测井的页岩油产能分析及甜点评价[J]. 新疆石油地质, 2024, 45(3):317-326.
	QIN Jianhua, LI Yingyan, DU Gefeng, et al. NMR logging-based productivity analysis and sweet spot evaluation for shale oil[J]. Xinjiang Petroleum Geology, 2024, 45(3):317-326.
[27]	张琳琳, 王孔杰, 赖枫鹏, 等. 鄂尔多斯盆地西缘奥陶系乌拉力克组海相页岩气储层甜点分类评价[J]. 石油实验地质, 2024, 46(1):191-201.
	ZHANG Linlin, WANG Kongjie, LAI Fengpeng, et al. Classification and evaluation of sweet spots of marine shale gas reservoir in Ordovician Wulalike formation on the westen margin of Ordos Basin[J]. Petroleum Geology & Experiment, 2024, 46(1):191-201.

学习器	决定系数	均方根误差
RCLM	0.81~0.83 （0.82，0.005）	0.300~0.320 （0.310，0.004）
EMABP神经网络	0.73~0.83 （0.78，0.028）	0.310~0.370 （0.340，0.019）
RBF神经网络	0.79~0.82 （0.80，0.007）	0.310~0.320 （0.317，0.006）
ELM	0.72~0.78 （0.74，0.014）	0.340~0.380 （0.360，0.008）

孔隙度/ %	渗透率/ mD	含水饱和度/%	深电阻率与泥岩电阻率之比	解释结论	测井甜点综合指数
20	4.00	50	2.4	气层	53.67
15	1.00	50	2.4	气层	30.98
13	0.20	50	2.4	气层	14.88
15	1.00	75	1.2	气水同层	7.38
15	1.00	95	1.0	水层	1.30
10	0.05	95	1.1	干层	0.39

井区	动静态渗透率转换模型
DF1-1井区、DF11-2井区、 DF13-1井区、HK29-1井区	K_d=0.156 9（K_sC_p）^{1.661 2}
DF29-1井区	K_d=6.663 8（K_sC_p）^{0.565 2}
DF13-2井区	K_d=0.058 4（K_sC_p）^{0.565 2}
LD10-1井区	K_d=0.010 3（K_sC_p）^{2.442 6}