模型反演和深度学习反演联合的地震波阻抗优化反演  

Seismic impedance optimization inversion combining model inversion with deep learning inversion

作　　者：黄闻露 阎建国[1] 任立龙 谢锐 HUANG Wen-Lu;YAN Jian-Guo;REN Li-Long;XIE Rui(College of Geophysics,Chengdu University of Technology,Chengdu 610059,China)

机构地区：[1]成都理工大学地球物理学院,四川成都610059

出　　处：《物探与化探》2024年第4期1076-1085,共10页Geophysical and Geochemical Exploration

基　　金：中国石油勘探开发研究院项目“油气地球物理前沿理论与新技术”(RPED-2020-JS-121)。

摘　　要：基于“数据驱动和模型驱动”相结合的思想,通过模型反演结果扩展标签训练集,并在深度学习算法中加入模型反演目标函数,对损失函数进行重构,提出了一种模型反演和深度学习反演联合的地震波阻抗优化反演。采用RNN网络结构实现了一种“伪标签”下的半监督深度学习网络反演,并用网络反演结果作为初始模型参与模型反演,最终优化反演由网络反演和模型反演不断迭代优化完成。通过合成Marmousi模型和实际资料,验证了所提出的方法具有较高的反演精度和实用性。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.

关 键 词：数据驱动 模型驱动 伪标签 半监督 波阻抗反演 

分 类 号：P631.4[天文地球—地质矿产勘探]