Seismic impedance optimization inversion combining model inversion with deep learning inversion

HUANG Wen-Lu; YAN Jian-Guo; REN Li-Long; XIE Rui

doi:10.11720/wtyht.2024.1288

2024 Vol. 48, No. 4

Article Contents

Article navigation > Geophysical and Geochemical Exploration > 2024 > 48(4): 1076-1085

Next Article Previous Article

HUANG Wen-Lu, YAN Jian-Guo, REN Li-Long, XIE Rui. 2024. Seismic impedance optimization inversion combining model inversion with deep learning inversion. Geophysical and Geochemical Exploration, 48(4): 1076-1085. doi: 10.11720/wtyht.2024.1288

Citation:

HUANG Wen-Lu, YAN Jian-Guo, REN Li-Long, XIE Rui. 2024. Seismic impedance optimization inversion combining model inversion with deep learning inversion. Geophysical and Geochemical Exploration, 48(4): 1076-1085. doi: 10.11720/wtyht.2024.1288

Seismic impedance optimization inversion combining model inversion with deep learning inversion

College of Geophysics, Chengdu University of Technology, Chengdu 610059, China

Received Date: 07 July 2023

Revised Date: 17 November 2023

Abstract

Abstract

Based on the combination ofdata- and model-driven approaches, this study expanded the labels of the training set through model inversion results, and added the model inversion objective function to the deep learning algorithm. By constructing a new loss function, this study proposed a seismic impedance optimization inversion method combining model inversion with deep learning inversion. The semi-supervised deep learning network inversion under a pseudo-label was achieved using the RNN network structure. The network inversion results were used as the initial model to participate in the model inversion. The final optimization inversion was completed by continuous iterative optimization of both network and model inversion. The method proposed in this study proves to possess high inversion accuracy and practicability, as demonstrated by the synthesis of the Marmousi model and the actual data.
- data-driven /
- model-driven /
- pseudo-label /
- semi-supervision /
- wave impedance inversion

FullText(HTML)

References

[1]	Chen Y K, Chen H M, Xiang K, et al.Geological structure guided well log interpolation for high-fidelity full waveform inversion[J].Geophysical Journal International, 2016, 207(2):1313-1331. Google Scholar
[2]	王华忠, 王雄文, 王西文.地震波反演的基本问题分析[J].岩性油气藏, 2012, 24(6):1-9. Google Scholar Wang H Z, Wang X W, Wang X W.Analysis of the basic problems of seismic wave inversion[J].Lithologic Reservoirs, 2012, 24(6):1-9. Google Scholar
[3]	蒋星达, 张伟, 杨辉.地球物理反演问题中的贝叶斯方法研究[J].地球与行星物理论评, 2022, 53(2):159-171. Google Scholar Jiang X D, Zhang W, Yang H.The research on Bayesian inference for geophysical inversion[J].Reviews of Geophysics and Planetary Physics, 2022, 53(2):159-171. Google Scholar
[4]	邢文军, 曹思远, 陈思远, 等.基于谱反演方法的叠后纵波阻抗反演[J].物探与化探, 2023, 47(2):429-437. Google Scholar Xing W J, Cao S Y, Chen S Y, et al.Post-stack P-wave impedance inversion based on spectral inversion[J].Geophysical and Geochemical Exploration, 2023, 47(2):429-437. Google Scholar
[5]	凡友华, 刘雪峰, 陈晓非.面波频散反演地下层状结构的拟牛顿法[J].物探与化探, 2006, 30(5):456-459. Google Scholar Fan Y H, Liu X F, Chen X F.The quasi Newton method in the inversion of the dispersion curve of Rayleigh wave in multilayered media[J].Geophysical and Geochemical Exploration, 2006, 30(5):456-459. Google Scholar
[6]	Reichstein M, Camps-Valls G, Stevens B, et al.Deep learning and process understanding for data-driven Earth system science[J].Nature, 2019, 566:195-204. Google Scholar
[7]	Yu S W, Ma J W.Deep learning for geophysics:Current and future trends[J].Reviews of Geophysics, 2021, 59(3):1-36. Google Scholar
[8]	肖立志.机器学习数据驱动与机理模型融合及可解释性问题[J].石油物探, 2022, 61(2):205-212. Google Scholar Xiao L Z.The fusion of data-driven machine learning with mechanism models and interpretability issues[J].Geophysical Prospecting for Petroleum, 2022, 61(2):205-212. Google Scholar
[9]	Das V, Pollack A, Wollner U, et al.Convolutional neural network for seismic impedance inversion[J].Geophysics, 2019, 84(6):R869-R880. Google Scholar
[10]	Alfarraj M, AlRegib G.Semisupervised sequence modeling for elastic impedance inversion[J].Interpretation, 2019, 7(3):SE237-SE249. Google Scholar
[11]	Biswas R, Sen M K, Das V, et al.Prestack and poststack inversion using a physics-guided convolutional neural network[J].Interpretation, 2019, 7(3):SE161-SE174. Google Scholar
[12]	Luo R, Chen H Z, Wang B F.Semisupervised seismic impedance inversion with data augmentation and uncertainty analysis[J].Geophysics, 2023, 88(4):M213-M224. Google Scholar
[13]	Su Y Q, Cao D P, Liu S Y, et al.Seismic impedance inversion based on deep learning with geophysical constraints[J].Geoenergy Science and Engineering, 2023, 225:211671. Google Scholar
[14]	王蓉, 熊杰, 刘倩, 等.基于深度神经网络的重力异常反演[J].物探与化探, 2022, 46(2):451-458. Google Scholar Wang R, Xiong J, Liu Q, et al.Inversion of gravity anomalies based on a deep neural network[J].Geophysical and Geochemical Exploration, 2022, 46(2):451-458. Google Scholar
[15]	吴嵩, 宁晓斌, 杨庭伟, 等.基于神经网络的探地雷达数据去噪[J].物探与化探, 2023, 47(5):1298-1306. Google Scholar Wu S, Ning X B, Yang T W, et al.Neural network-based denoising for ground-penetrating radar data[J].Geophysical and Geochemical Exploration, 2023, 47(5):1298-1306. Google Scholar
[16]	卞保力.基于高密度三维地震河道砂体储层预测方法研究与应用[D].成都:成都理工大学, 2019.Bian B L.Research and application of reservoir prediction method of channel sands based on high density three-dimensional seismic data[D].Chengdu:Chengdu University of Technology, 2019. Google Scholar