摘要：Seismic velocity analysis is the basis for seismic imaging and understanding complex subsurface geological structures. Although the performance of automatic velocity analysis methods based on Common Middle Point (CMP) data or Velocity Spectra (VS) is encouraging, particularly deep learning methods. However, most methods ignore the complementarity between CMP data and VS data, and only one of them is selected for velocity modelling. We propose a multimodal neural network (MMN) that combines the advantages of CMP data details representation and simplification of VS. MMN includes multilayer convolution structures and auto-encoder structures, which are used to extract time-space amplitude information from CMP gathers and energy groups features from VS data, respectively. This paper compared MMN with the CMP single-modal network (CSN) and the velocity spectra single-modal network (VSSN). Based on synthetic data, we investigated their differences in terms of continuity, accuracy, noise resistance and generalization. The MMN prediction results makes a trade-off between the overall continuity and local details. Visualization analysis of the intermediate feature maps explains the MMN velocity prediction mechanism, that is, the multi-angle representation and complementary fusion of velocity information. Finally, the performance of the proposed method is demonstrated using the braided river deposited field data example.

关键字：Image processing; Inverse theory; Joint inversion; Neural networks; fuzzy logic; Waveform inversion

ISSN号：0956-540X

卷、期、页：卷235期1: 216-230

发表日期：2023-05-27

影响因子：0.000000

期刊分区（SCI为中科院分区）：二区

收录情况：SCI（科学引文索引印刷版）,地学领域高质量科技期刊分级目录（国外T2）,EI（工程索引）,SCIE（科学引文索引网络版）

发表期刊名称：GEOPHYSICAL JOURNAL INTERNATIONAL

参与作者：Zeng, Huahui,Yuan, Huan

通讯作者：张海风,高杨

第一作者：袁三一,王尚旭

论文类型：期刊论文

论文概要：张海风,袁三一,Zeng, Huahui,Yuan, Huan,高杨,王尚旭，Automatic velocity analysis using interpretable multimode neural networks，GEOPHYSICAL JOURNAL INTERNATIONAL，2023，卷235期1: 216-230

论文题目：Automatic velocity analysis using interpretable multimode neural networks