Porosity inversion by Caianiello neural networks with Levenberg-Marquardt optimization

doi:10.1190/INT-2016-0119.1

CORC > 地质与地球物理研究所 > 中国科学院地质与地球物理研究所 > 中国科学院油气资源研究重点实验室

	Porosity inversion by Caianiello neural networks with Levenberg-Marquardt optimization
	Boateng, Cyril D.1,2; Fu, Li-Yun 1; Yu, Wu 1; Guan Xizhu 1,3
刊名	INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION
	2017-08-01
卷号	5 期号:3 页码:SL33-SL42
ISSN号	2324-8858
DOI	10.1190/INT-2016-0119.1
文献子类	Article
英文摘要	Caianiello neural networks (CNNs) incorporated with the Robinson seismic convolutional model are modified by the Levenberg-Marquardt algorithm to improve convergence. CNNs are extended to the multiattribute domain for reservoir property inversion, with time-varying signal processing by a frequency-domain block implementation using fast Fourier transforms. Optimal inversion can be achieved by applying the Levenberg-Marquardt optimization to multiattribute domain CNNs for convergency improvement due to its ability to swing between the steepest- descent and Gauss-Newton algorithms. The methodology is applied to porosity estimation in an oilfield with six wells in the Bohai Basin of China. Cross-validation results indicate significant correlation between actual porosity logs and predicted porosity logs. Compared with a traditional method, our technique is robust.
WOS关键词	SEISMIC DATA ; MULTIATTRIBUTE TRANSFORMS ; ACOUSTIC-IMPEDANCE ; OIL-FIELD ; PREDICTION ; PARAMETERS ; ALGORITHM ; VELOCITY ; CHINA ; BASIN
WOS研究方向	Geochemistry & Geophysics
语种	英语
出版者	SOC EXPLORATION GEOPHYSICISTS
WOS记录号	WOS:000409910400006
资助机构	Chinese Academy of Sciences ; World Academy of Sciences through the CAS-TWAS President's Fellowship program ; Chinese Academy of Sciences ; World Academy of Sciences through the CAS-TWAS President's Fellowship program ; Chinese Academy of Sciences ; World Academy of Sciences through the CAS-TWAS President's Fellowship program ; Chinese Academy of Sciences ; World Academy of Sciences through the CAS-TWAS President's Fellowship program
内容类型	期刊论文
源URL	[http://ir.iggcas.ac.cn/handle/132A11/61929]
专题	地质与地球物理研究所_中国科学院油气资源研究重点实验室
通讯作者	Boateng, Cyril D.
作者单位	1.Inst Geol & Geophys, Key Lab Petr Resource Res, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.CNOOC, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Boateng, Cyril D.,Fu, Li-Yun,Yu, Wu,et al. Porosity inversion by Caianiello neural networks with Levenberg-Marquardt optimization[J]. INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION,2017,5(3):SL33-SL42.
APA	Boateng, Cyril D.,Fu, Li-Yun,Yu, Wu,&Guan Xizhu.(2017).Porosity inversion by Caianiello neural networks with Levenberg-Marquardt optimization.INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION,5(3),SL33-SL42.
MLA	Boateng, Cyril D.,et al."Porosity inversion by Caianiello neural networks with Levenberg-Marquardt optimization".INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION 5.3(2017):SL33-SL42.