A Sand Body Thickness Prediction Method Based on Deep Learning From Small Sample Data and Its Application

doi:10.7657/XJPG20230214

Abstract

Abstract:

In the upper Es₄ in Y184 well block，northern Bonan subsag of Zhanhua sag， multi-stage fan delta deposits are developed，and characterized by thin sand bodies individually，great variation laterally and sandstone interbedded with shale，making it very difficult to perform quantitative prediction，which restricts the efficient development of this well block. Through deep learning and seismic attribute prediction，virtual wells were constructed to solve the problem of insufficient training samples for deep learning in the study area. Thus，a nonlinear relationship between sand body thickness and seismic attributes was clarified，and a network model for predicting sand body thickness using seismic attributes was established. This method can accurately predict sand body thickness and lateral distribution with a significantly improved accuracy，and provides a new idea for the prediction of tight sandstone reservoirs.

Key words: seismic attribute, sand body thickness prediction, lateral distribution, small sample data, deep learning, network model

CLC Number:

TE122.24

CHEN Yumao, ZHAO Hu, YANG Hongwei, WEI Guohua, LUO Pingping. A Sand Body Thickness Prediction Method Based on Deep Learning From Small Sample Data and Its Application[J]. Xinjiang Petroleum Geology, 2023, 44(2): 231-237.

Figures/Tables 11

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

Fig. 6.

Fig. 7.

Fig. 8.

Fig. 9.

Fig. 10.

Fig. 11.

References 24

[1]	刘雅丽, 刘鹏, 伊伟. 渤南洼陷沙四上亚段沉积相及有利储集层分布[J]. 新疆石油地质, 2014, 35(1):39-44.
	LIU Yali, LIU Peng, YI Wei. Depositional facies and favorable reservoir distribution of Sha-4 upper member of Shahejie formation in Bonan sub-sag[J]. Xinjiang Petroleum Geology, 2014, 35(1):39-44.
[2]	付航. 渤南油田义176区块沙四油层组储层特征及分类评价研究[D]. 黑龙江大庆: 东北石油大学, 2012.
	FU Hang. Study on characteristics and classification of low porosity and low permeability reservoirs of Sha-4 oil layer group in Yi 176,Bonan oilfield[D]. Daqing,Heilongjiang: Northeast Petroleum University, 2012.
[3]	谢启, 李恒权, 李磊, 等. 春光探区强反射背景下的薄储集层预测[J]. 新疆石油地质, 2021, 42(5):617-623.
	XIE Qi, LI Hengquan, LI Lei, et al. Thin reservoir prediction under strong reflection shielding background in Chunguang area[J]. Xinjiang Petroleum Geology, 2021, 42(5):617-623.
[4]	于江龙, 陈刚, 吴俊军, 等. 玛湖凹陷风城组页岩油地质工程甜点地震预测方法及应用[J]. 新疆石油地质, 2022, 43(6):757-766.
	YU Jianglong, CHEN Gang, WU Junjun, et al. Seismic prediction method of geological and engineering shale oil sweet spots and its application in Fengcheng formation of Mahu sag[J]. Xinjiang Petroleum Geology, 2022, 43(6):757-766.
[5]	王世瑞, 王树平, 狄帮让, 等. 基于地震属性特征的河道砂体预测方法[J]. 石油地球物理勘探, 2009, 44(3):304-313.
	WANG Shirui, WANG Shuping, DI Bangrang, et al. Prediction of channel sand body based on seismic attributes[J]. Oil Geophysical Prospecting, 2009, 44(3):304-313.
[6]	迟唤昭, 刘财, 单玄龙, 等. 谱反演方法在致密薄层砂体预测中的应用研究[J]. 石油物探, 2015, 54(3):337-344. doi: 10.3969/j.issn.1000-1441.2015.03.013
	CHI Huanzhao, LIU Cai, SHAN Xuanlong, et al. Application of spectral inversion for tight thin-bed sand body prediction[J]. Geophysical Prospecting for Petroleum, 2015, 54(3):337-344. doi: 10.3969/j.issn.1000-1441.2015.03.013
[7]	蔡义丰, 熊婷, 姚卫江, 等. 地震多属性分析技术在薄层砂体预测中的应用[J]. 石油地球物理勘探, 2017, 52(2):140-145.
	CAI Yifeng, XIONG Ting, YAO Weijiang, et al. Application of seismic multi-attribute analysis technology in the prediction of thin-bed sand bodies[J]. Oil Geophysical Prospecting, 2017, 52(2):140-145.
[8]	李伟, 岳大力, 胡光义, 等. 分频段地震属性优选及砂体预测方法:秦皇岛32-6油田北区实例[J]. 石油地球物理勘探, 2017, 52(1):121-130.
	LI Wei, YUE Dali, HU Guangyi, et al. Optimization of seismic properties in sub-frequency band and prediction method of sand body:an example of the northern area of Qinhuangdao 32-6 oilfield[J]. Oil Geophysical Prospecting, 2017, 52(1):121-130.
[9]	杨军. 匹配追踪技术在薄互层砂体预测中的应用[J]. 西部探矿工程, 2018, 30(11):52-55.
	YANG Jun. Application of matching tracking technology in the prediction of thin cross-layered sand[J]. West-China Exploration Engineering, 2018, 30(11):52-55.
[10]	罗钏江, 罗耀华, 鲁建隆, 等. 基于地质统计学反演方法的洛带气田储层预测[J]. 物探化探计算技术, 2019, 41(2):200-206.
	LUO Chuanjiang, LUO Yaohua, LU Jianlong, et al. The application for the geostatistical inversion in Luodai gasfield[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2019, 41(2):200-206.
[11]	HINTON G, SALAKHUTDINOV R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507. doi: 10.1126/science.1127647 pmid: 16873662
[12]	安鹏, 曹丹平, 赵宝银, 等. 基于LSTM循环神经网络的储层物性参数预测方法研究[J]. 地球物理进展, 2019, 34(5):1 849-1 858.
	AN Peng, CAO Danping, ZHAO Baoyin, et al. Reservoir physical parameters prediction based on LSTM recurrent neural network[J]. Progress in Geophysics, 2019, 34(5):1 849-1 858.
[13]	安鹏, 刘凤轩, 李佩瑾, 等. 基于PCA-RBFN的河道砂体厚度预测方法[C]. 中国石油学会2021年物探技术研讨会论文集,石油物探编辑部, 2021:752-755.
	AN Peng, LIU Fengxuan, LI Peijin, et al. Prediction method of river sand body thickness based on PCA-RBFN[C]. 2021 Geophysical Technology Seminar of China Petroleum Society,Editorial Department of Geophysical Prospecting for Petroleum, 2021:752-755.
[14]	郭丽丽, 丁世飞. 深度学习研究进展[J]. 计算机科学, 2015, 42(5):28-33. doi: 10.11896/j.issn.1002-137X.2015.05.006
	GUO Lili, DING Shifei. Research progress on deep learning[J]. Computer Science, 2015, 42(5):28-33. doi: 10.11896/j.issn.1002-137X.2015.05.006
[15]	丁燕, 杜启振, YASIN Q, 等. 基于深度学习的裂缝预测在S区潜山碳酸盐岩储层中的应用[J]. 石油物探, 2020, 59(2):267-275. doi: 10.3969/j.issn.1000-1441.2020.02.013
	DING Yan, DU Qizhen, YASIN Q, et al. Fracture prediction based on deep learning:application to a buried hill carbonate reservoir in the S area[J]. Geophysical Prospecting for Petroleum, 2020, 59(2):267-275. doi: 10.3969/j.issn.1000-1441.2020.02.013
[16]	张国印, 王志章, 林承焰, 等. 基于小波变换和卷积神经网络的地震储层预测方法及应用[J]. 中国石油大学报(自然科学版), 2020, 44(4):83-93.
	ZHANG Guoyin, WANG Zhizhang, LIN Chengyan, et al. Seismic reservoir prediction method based on wavelet transform and convolutional neural network and its application[J]. Journal of China University of Petroleum(Edition of Natural Science), 2020, 44(4):83-93.
[17]	CHEN Xueguo. The method of sand body thickness prediction based on attribute optimization and network function approximation and its application[J]. Journal of Oil and Gas Technology, 2017, 39(2):30-35.
[18]	TIAN Xingda, HUANG Handong, CHENG Suo, et al. A carbonate reservoir prediction method based on deep learning and multiparameter joint inversion[J]. Energies, 2022, 15(7):2 506. doi: 10.3390/en15072506
[19]	TANG Jian, QIAO Junfei, CHAI Tianyou, et al. Modeling multiple components mechanical signals by means of virtual sample generation technique[J]. Acta Automatic Sinica, 2018, 44(9):1 569-1 589.
[20]	ZHENG Runan, LIU Wenbo. Research on SAR image target recognition based on virtual sample[J]. Machinery & Electronics, 2017, 35(6):12-17.
[21]	DAN Lingling, SHI Changlin, ZHANG Jian, et al. Application of Xgboost algorithm based on machine learning in reservoir prediction of offshore oilfield[J]. Springer Series in Geomechanics and Geoengineering, 2021, 33(2):3 157-3 167.
[22]	SANG Kaiheng, YIN Xingyao, ZHANG Fanchang. Machine learning seismic reservoir prediction method based on virtual sample generation[J]. Petroleum Science, 2021, 18(6):1 662-1 674. doi: 10.1016/j.petsci.2021.09.034
[23]	温凯, 韩旭, 李灿, 等. 基于神经网络的天然气流量计检定工艺智能控制系统[J]. 天然气工业, 2021, 41(7):124-133.
	WEN Kai, HAN Xu, LI Can, et al. Neural network based intelligent control system of natural gas flowmeter verification process[J]. Natural Gas Industry, 2021, 41(7):124-133.
[24]	BASHEER I A, HAJMEER M. Artificial neural networks: fundamentals,computing,design and application[J]. Journal of Microbiological Methods, 2000, 43(1):3-31. doi: 10.1016/S0167-7012(00)00201-3