基于粒子群优化的相关向量机算法的井震联合储层参数预测与不确定性评估

doi:10.13810/j.cnki.issn.1000-7210.2023.06.015

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (4136 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract There are three types of methods for predicting porosity and saturation， which are rock physics， geostatistics， and seismic multi-attribute. The first type with clear physical meaning is widely used， but it has certain limitations. The second type can improve resolution compared with conventional methods， yet it is difficult to predict reservoir parameters in complex structural areas. The support vector machine （SVM） belongs to the third type. Its computational complexity increases with the rise of sample quantity. Meanwhile， it is difficult to evaluate the uncertainty. The relevance vector machine （RVM） in the third type lacks a clear theory for selecting kernel parameters. To improve this， particle swarm optimization （PSO） is applied to guide the selection of kernel parameters. The reservoir parameters are quantitatively predicted on the basis of obtaining the optimal kernel parameters. Then， the coefficient of variation is introduced to eliminate the influence of dimension and quantify the uncertainty of prediction results. With the help of a stepwise regression algorithm to screen seismic attributes， this paper proposes a quantitative porosity and saturation prediction method based on RVM optimized by PSO （PSO-RVM）. The results of numerical simulation and field application show that： ①PSO-RVM has good learning performance， satisfying genera-lization ability， and a certain ability of anti-noise. The RMS error of PSO-RVM prediction results is lower than that of RVM， and the prediction accuracy is higher， which indicates that PSO can effectively guide the selection of RVM kernel parameters and improve the algorithm performance. ②PSO-RVM provides a posterior probability， and it can quantify uncertainty by introducing a coefficient of variation. ③From seismic and well logs data， the porosity and gas saturation are quantitatively predicted by PSO-RVM with high prediction accuracy. Additionally， the accuracy of porosity prediction is higher， and the uncertainty is lower.

Key words： reservoir parameter seismic attribute particle swarm optimization relevance vector machine coefficient of variation uncertainty evaluation

Received: 22 February 2023

PACS:

P631

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	DAI Shiming
	LI Min
	TANG Jinliang
	ZHU Tong
	LI Jingnan
	HU Huafeng

Cite this article:

DAI Shiming,LI Min,TANG Jinliang等. Seismic and well logs integration for reservoir parameter prediction and uncertainty evaluation based on relevance vector machine optimized by particle swarm optimization[J]. OGP, 2023, 58(6): 1436-1445.

URL:

http://www.ogp-cn.com/EN/10.13810/j.cnki.issn.1000-7210.2023.06.015 OR http://www.ogp-cn.com/EN/Y2023/V58/I6/1436

[1]	印兴耀,崔维,宗兆云,等.基于弹性阻抗的储层物性参数预测方法[J].地球物理学报,2014,57(12): 4132-4140.YIN Xinyao,CUI Wei,ZONG Zhaoyun,et al.Petrophysical property inversion of reservoirs based on elastic impedance[J].Chinese Journal of Geophysics,2014,57(12): 4132-4140.
[2]	张广智,陈娇娇,陈怀震,等.基于岩石物理模版的碳酸盐岩含气储层定量解释[J].吉林大学学报(地球科学版),2015,45(2): 630-638.ZHANG Guangzhi,CHEN Jiaojiao,CHEN Huaizhen,et al.Quantitative interpretation of carbonate gas re- servoir based on rock physics template[J].Journal of Jilin University(Earth Science Edition),2015,45(2): 630-638.
[3]	未晛,杨志芳,晏信飞,等.改进型随机斑块饱和模型及其在致密气层检测中的应用[J].石油地球物理勘探,2018,53(6): 1227-1234.WEI Xian,YANG Zhifang,YAN Xinfei,et al.Modified continuous random patchy-saturation model in tight gas detection[J].Oil Geophysical Prospecting,2018,53(6): 1227-1234.
[4]	牛聪,张益明,王迪,等.LA地区盒8段优质储层的特征与分布预测[J].石油地球物理勘探,2017,52(3): 591-598.NIU Cong,ZHANG Yiming,WANG Di,et al.Prediction of high-quality reservoir characteristics and distribution in the area LA[J].Oil Geophysical Prospecting,2017,52(3): 591-598.
[5]	孙月成.基于Bayesian-MCMC算法的地质统计学反演及其在油藏模拟中的应用[J].地球物理学进展,2018,33(2): 724-729.SUN Yuecheng.Geostatistical inversion based on Bayesian-MCMC algorithm and its applications in re- servoir simulation[J].Progress in Geophysics,2018,33(2): 724-729.
[6]	ZHANG J,LI H,ZHANG G,et al.Rock physics inversion based on an optimized MCMC method[J].Applied Geophysics,2021,18(3): 288-298.
[7]	刘兴业,陈小宏,李景叶,等.基于核贝叶斯判别法的储层物性参数预测[J].石油学报,2016,37(7): 878-886.LIU Xingye,CHEN Xiaohong,LI Jingye,et al.Reservoir physical property prediction based on kernel-Bayes discriminant method[J].Acta Petrolei Sinica,2016,37(7): 878-886.
[8]	潘新朋,张广智,印兴耀.岩石物理驱动的储层裂缝参数与物性参数概率地震反演方法[J].地球物理学报,2018,61(2): 683-696.PAN Xinpeng,ZHANG Guangzhi,YIN Xinyao.Probabilistic seismic inversion for reservoir fracture and petrophysical parameters driven by rock-physics models[J].Chinese Journal of Geophysics,2018,61(2): 683-696.
[9]	韩宏伟,刘浩杰,桑文镜,等.基于半监督学习的井震联合储层横向孔隙度预测方法[J].地球物理学报,2022,65(10): 4073-4086.HAN Hongwei,LIU Haojie,SANG Wenjing,et al.Seismic and well logs integration for reservir lateral porosity prediction based on semi-supervised learning[J].Chinese Journal of Geophysics,2022,65(10): 4073-4086.
[10]	宋超,郭智奇,鹿琪,等.基于支持向量机法识别砂岩中流体类型[J].地球物理学进展,2015,30(2): 616-620.SONG Chao,GUO Zhiqi,LU Qi,et al.Fluid type identification of sandstone based on support vector machine[J].Progress in Geophysics,2015,30(2): 616-620.
[11]	赵学松,高强山,唐传章,等.基于支持向量回归机与井导向的三角洲岩性油气藏储层参数预测[J].石油地球物理勘探,2016,51（5): 976-982.ZHAO Xuesong,GAO Qiangshan,TANG Chuanzhang,et al.Delta stratigraphic reservoir parameter estimation based on support vector regression machine and well logging data[J].Oil Geophysical Prospecting,2016,51(5): 976-982.
[12]	王维强.基于KICA属性优化的支持向量机储层参数预测[J].物探与化探,2021,45(4): 990-997.WANG Weiqiang.The research of reservoir parameters forecasting based on KICA and SVM[J].Geophysical and Geochemical Exploration,2021,45(4): 990-997.
[13]	TIPPING M E.Sparse Bayesian learning and the re-levance vector machine[J].Journal of Machine Lear-ning Research,2001,1(3): 211-244.
[14]	JI Y,LIN Z.A novel approach for seismic time-frequency analysis[C].SEG Technical Program Expanded Abstracts,2019,38: 3939-3943.
[15]	PILIKOS G.The relevance vector machine for seismic Bayesian compressive sensing[J].Geophysics,2020,85(4): WA279-WA292.
[16]	DAI S,LI S J,ZHU T,et al.An attribute-guided method for reservoir parameter prediction using relevance vector machine[C].Extended Abstracts of 82nd EAGE Conference & Exhibition,2021,doi: https:∥doi.org/10.3997/2214-4609.202112538.
[17]	EBERHART R,KENNEDY J.A new optimizer using particle swarm theory[C].MHS'95.Proceedings of the Sixth International Symposium on Micro Machine and Human Science,1995,39-43.
[18]	陈俊霖,王朋,郜元元,等.多元逐步回归法在致密砂岩储层矿物与孔隙度关系分析中的应用——以鄂尔多斯盆地姬塬地区长8储层为例[J].天然气地球科学,2021,32(9): 1372-1383.CHEN Junlin,WANG Peng,GAO Yuanyaun,et al.Application of multiple stepwise regression method in the analysis of the relationship between porosity and tight sandstone: Case study of Chang 8 reservoir in Jiyuan area,Ordos Basin[J].Natural Gas Geoscience,2021,32(9): 1372-1383.