High resolution seismic inversion by convolutional neural network
Zhang Fanchang1, Liu Hanqing1, Niu Xuemin2, Dai Ronghuo1
1. School of Geoscience, China University of Petroleum (East China), Qingdao, Shandong 266555, China;
2. Geophysical Research Institute, Shengli Oilfield Branch Co., SINOPEC, Dongying, Shandong 257022, China
Abstract：With the requirements of high-accuracy seismic exploration, the inversion technique for thin beds and complex reservoirs with large lateral variation is becoming more and more important. However, the current inversion methods are mainly based on the convolutional model, bearing with poor resolution. In order to improve the resolution of inversion results, this paper presents an inversion method based on the convolutional neural network, which is totally driven by data and not restricted by convolutional model. The convolutional neural network has a layered structure, whose mapping relationship between its input and output is described by convolutional operators instead of inner product operators. Based on the convolutional neural network structure, the paper further provides the optimization algorithm for mapping operators and applies it to seismic inversion process. Application results show that the convolutional neural network inversion can get higher resolution impedance profile than the conventional sparse pulse inversion method.
Li Guofa, Yue Ying, Xiong Jinliang et al. Experimental study on seismic amplitude attribute of thin interbed based on 3D model. OGP, 2011, 46(1):115-120.
Lin Zhongmin. Carbonate rock reservoir features and oil gas accumulating conditions in the Ordovician of Tahe Oilfield in northern Tarim Basin. Acta Petrolei Sinica, 2002, 23(3): 23-26.
Li Aishan, Yin Xingyao, Zhang Fanchang et al. Application of prestack simultaneous AVA multi-parameter inversion in gas-bearing reservoir prediction. GPP, 2007,46(1):64-68.
[5]
印兴耀, 张世鑫, 张繁昌等. 利用基于 Russell 近似的弹性波阻抗反演进行储层描述和流体识别. 石油地球物理勘探, 2010,45(3): 373-380.
Yin Xingyao, Zhang Shixin, Zhang Fanchang et al. Utilizing Russell approximation-based elastic wave impedance inversion to conduct reservoir description and fluid identification.OGP,2010,45(3):373-380.
Xu Lei, Chi Huisheng. Research advances on supervised learning of static feedforward networks. Acta Electronica Sinica, 1992, 20(10): 106-113.
[7]
王钰, 郭其一, 李维刚. 基于改进 BP 神经网络的预测模型及其应用. 计算机测量与控制,2005, 13(1): 39-42.
Wang Yu, Guo Qiyi and Li Weigang. Predictive model based on improved BP neural networks and Its application. Computer Measurement & Control, 2005, 13(1): 39-42.
[8]
郑永爱. 内积空间的特征. 数学杂志, 1995, 15(4):477-484.
Zheng Yongai. Characterizations of inner product spaces. Journal of Mathematics, 1995, 15(4): 477-484.
[9]
Fukushima K, Miyake S and Ito T. Neocognitron: A neural network model for a mechanism of visual pattern recognition. IEEE Transactions on Systems, Man and Cybernetics, 1983, 13(5): 826-834.
[10]
Lawrence S, Giles C L, Tsoi A C et al. Face recog-nition: A convolutional neural-network approach. IEEE Transactions on Neural Networks,1997,8(1): 98-113.
[11]
Fu L Y. Caianiello neural network method for geophysical inverse problems. Handbook of Geophysical Exploration: Seismic Exploration, 2001, 30: 187-215.
[12]
Lecun Y et al. Backpropagation applied to handwritten zip code recognition. Neural Computation, 1989, 1(4): 541-551.
[13]
Olshausen B A. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 1996, 381(6583): 607-609.
Zhang Fanchang, Yin Xingyao and Yin Haiyan. Pre-stack three-term inversion based on conjugate direction substitution and realization. OGP, 2009,44(4):430-435.
[17]
Robinson E A. Predictive decomposition of time series with application to seismic exploration.Geophysics, 1967, 32(3):418-484.
[18]
Robinson E A. Predictive decomposition of seismic traces. Geophysics, 1957, 22(4): 767-778.
