Study on the PNN Neural Network Inversion Based on the Integration of Seismic Multi-Attribute with Frequency Division RGB - Fuyu Oil Layer in Gaotaizi Area, Songliao Basin is Taken for an Example

Abstract:

Fuyu oil layer in Changyuan of Daqing is a strategic area for Daqing oil field to increase and stabilize production at present, but its reservoir is structured mostly by riverway sand bodies. The sand bodies are thin and change with complexity, so they are difficult to identify. Through PNN probability neural network, and combined with the seismic multi-attribute and earthquake frequency division data, wave impedance inversions are implemented, and the maximum correlation coefficient is 0.517 if a single attribute is described and it is raised to 0.773 by linear weighting, and also 9 independent attributes are used for PNN network training so that a more complex nonlinear relationship is obtained. Then, the correlation coefficient continues to increase until 0.869, so that the spatial distribution characteristics of the sandstones in the study area are accurately described. This indicates that the PNN neural network inversion based on the integration of seismic multi-attribute with frequency division RGB can play an obvious effect in the areas of thin and changing sand bodies, and can meet the needs of the oil field exploration and development.

• Periodical: Applied Mechanics and Materials (Volumes 416-417)
• Pages: 2025-2032
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.416-417.2025
• Online since: September 2013
• Authors: Xin Rong Zhang, Shi Fang, Jin Ping Liu, Mao Xin Yang
• Keywords: Frequency Division, Probabilistic Neural Network, Seismic Inversion, Seismic Multi-Attribute

References

[1] Jianying WAN, Shibo WANG, Qiudeng ZHAO, et al. Reservoir characteristics of Fuyang oil layer in Q3 and Q4 Member in Daqing Placanticline and Area to Its West [J]. Petroleum Geology & Oilfield Development in Daqing, 2007 (05).

[2] Jianying WAN, Shibo WANG. Shallow Water Lake Delta Sedimentary Characteristics of Fuyang Oil Layer in Q3 and Q4 Member in Daqing Placanticline and Area to Its West [J]. Inner Mongulia Petrochemical Industry, 2011 (10).

[3] Erhua ZHANG, Yongzhong SONG, Shummin CHEN, Guoping JIN, Ying QIU. Seismic Recognition Method of Channel Sand Body of Fuyang Pay Zone in Songliao Basin [J]. Petroleum Geology & Oilfield Development in Daqing, 2004 (05).

DOI: 10.1190/1.3603806

[4] Shuyun LI, Yanlou GAO, Zhenhai TANG, Qingsheng JI. Sand Comprehensive Prediction Technology of Fuyang Reservoir [J]. Petroleum Geology & Oilfield Development in Daqing, 2002 (04).

[5] Shaohong ZHANG. Application of Probabilistic Neural Network in Seismic Lithological Inversion [J]. Journal of Liaoning Technical University (Social Science Edition), 2007 (S2).

[6] Fanchang ZHANG, Xingyao YIN, Guoshen WU, Guangzhi ZHANG. Wave Impedance Inversion Using Simulated Annealing Neural Network [J]. Journal of China University of Petroleum (Edition of Natural Science), 1997 (06).

[7] Xingyao YIN, Jingyi Zhou. A Review of Seismic Attribute Optimization Methods [J]. Oil Geophysical Prospecting, 2005 (04).

[8] Yanling Zhang, Changchun Yang, Shuguang Jia. Study and Application of Seismic Attribute Technology [J]. Progress in Geophysics, 2005 (04).

[9] Yanzhang Zhang, Shoupeng Yi, Qiaoling Zhang, et al. Geologic Significance of the Seismic Spectral Decomposition Technology and Its Application Analysis [J]. Petroleum Exploration and Development, 2006 (01).

[10] Xiangyang Cao, Jinshui Zhang, Wenming Han, et al. Research of Using Information Fusion Technology to Integrate Seismic Decomposition Spectrum Signals and its Application [J]. Computerized Tomography Theory and Applications, 2012 (04).

[11] Shuguang LI, Tianji Xu, Jianming Tang. Reservoir Fluid-Density Inversion and Application Based on PNN [J]. Geological Science and Technology Information, 2011 (01).

[12] Wanglin Xu, Xiongqi Pang, Shuying Lv, Michael R. Dynamic Probabilistic Neural Network and the Probability Distribution of Oil and Gas Prediction [J]. Oil Geophysical Prospecting, 2005 (01).