Seismic wave impedance inversion based on the fully convolutional residual shrinkage network
WANG Kang1(), LIU Cai-Yun2(), XIONG Jie1, WANG Yong-Chang1, HU Huan-Fa1, KANG Jia-Shuai1
1. School of Electronics & Information Engineering,Yangtze University,Jingzhou 434023,China 2. School of Information and Mathematics,Yangtze University,Jingzhou 434023,China
Convolutional neural networks(CNNs) have achieved good results in seismic wave impedance inversion,but the inversion accuracy and anti-noise performance need to be improved.Hence,this study proposed a seismic wave impedance inversion method based on the fully convolutional residual shrinkage network with channel-wise thresholds(FCRSN-CW).In this method,the attention mechanism and the soft thresholding were first added to the structure of the residual network to form a inversion network.Then,a synthetic seismic dataset was obtained through forward calculation using wave impedance data.Subsequently,the dataset was applied to train the FCRSN-CW.Finally,the seismic data were put into the trained FCRSN-CW to obtain the inversion results directly.The inversion results of the theoretical model show that the FCRSN-CW can accurately invert the wave impedance and possesses satisfactory learning capacity and anti-noise performance.The inversion results of field data demonstrates that the method based on FCRSN-CW can effectively achieve seismic wave impedance inversion.
Kang WANG,Cai-Yun LIU,Jie XIONG, et al. Seismic wave impedance inversion based on the fully convolutional residual shrinkage network[J]. Geophysical and Geochemical Exploration,
2023, 47(6): 1538-1546.
Zhang F C, Yin X Y, Wu G C, et al. Impedance inversion using simulated annealing neural network technique[J]. Journal of the University of Petroleum,China:Natural Science Edition, 1997, 21(6):16-18.
Nie R, Yue J H, Deng S Q. Application of immune genetic algorithm in wave impedance inversion[J]. Application Research of Computers, 2010, 27(4):1273-1276.
[7]
Yang H J, Xu Y Z, Peng G X, et al. Particle swarm optimization and its application to seismic inversion of igneous rocks[J]. International Journal of Mining Science and Technology, 2017, 27(2):349-357.
[8]
Conti C R, Roisenberg M, Neto G S, et al. Fast seismic inversion methods using ant colony optimization algorithm[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(5):1119-1123.
[9]
Wang B F, Zhang N, Lu W K, et al. Deep-learning-based seismic data interpolation:A preliminary result[J]. Geophysics, 2019, 84(1):V11-V20.
Fu C, Lin N T, Zhang D, et al. Prediction of reservoirs using multi-component seismic data and the deep learning method[J]. Chinese Journal of Geophysics, 2018, 61(1):293-303.
[11]
赵明, 陈石, Dave Yuen. 基于深度学习卷积神经网络的地震波形自动分类与识别[J]. 地球物理学报, 2019, 62(1):374-382.
[11]
Zhao M, Chen S, Yuen D. Waveform classification and seismic recognition by convolution neural network[J]. Chinese Journal of Geophysics, 2019, 62(1):374-382.
[12]
Zhang H H, Zhang G Z, Gao J H, et al. Seismic impedance inversion based on geophysical-guided cycle-consistent generative adversarial networks[J]. Journal of Petroleum Science and Engineering, 2022, 218:111003.
Liang L F, Liu X J, Zhang H B, et al. A study of the effect of hyperparameters on GRU-CNN hybrid deep learning EI inversion[J]. Geophysical and Geochemical Exploration, 2021, 45(1):133-139.
[14]
Das V, Pollack A, Wollner U, et al. Convolutional neural network for seismic impedance inversion[J]. Geophysics, 2019, 84(6):R869-R880.
[15]
Puzyrev V, Egorov A, Pirogova A, et al. Seismic inversion with deep neural networks:A feasibility analysis[C]// London:81st EAGE Conference and Exhibition 2019,European Association of Geoscientists & Engineers, 2019:1-5.
[16]
Xu P C, Lu W K, Tang J, et al. High-resolution reservoir prediction using convolutional neural networks[C]// London:81st EAGE Conference and Exhibition 2019,European Association of Geoscientists & Engineers, 2019:1-5.
[17]
Guo R, Zhang J J, Liu D, et al. Application of bi-directional long short-term memory recurrent neural network for seismic impedance inversion[C]// London:81st EAGE Conference and Exhibition 2019,European Association of Geoscientists & Engineers,2019, 2019(1):1-5.
[18]
Wu B Y, Xie Q, Wu B H. Seismic impedance inversion based on residual attention network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-17.
[19]
Wu B Y, Meng D L, Wang L L, et al. Seismic impedance inversion using fully convolutional residual network and transfer learning[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(12):2140-2144.
[20]
Zhao M H, Zhong S S, Fu X Y, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7):4681-4690.
