基于轻量化U-Net的高效地震速度反演方法

打开文本图片集

中图分类号：P631 文献标识码：A DOI：10.13810/j.cnki.issn.1000-7210.20240352

Abstract： Intellgent seismic velocity inversion is currently a hot and challenging topic in seismic exploration re search.Nevertheless， the complex structure of deep learning networks demands significant computing power from hardware devices，which restricts the application of the model in scenarios with large data volumes and high timeliness requirements. To address these practical issues，in this paper，the U-Net is improved based on the concepts of feature engineering and model lightweighting，and the inversion networks U-Net vG for GPU and U-Net vC for CPU are proposed.Firstly，the characteristics of the velocity inversion network are analyzed to deduce the lightweighting principles of convolutional neural networks. Subsequently，lightweight processing is conducted on the multi-scale module，atention gate module，and feature extraction module to obtain a lightweight convolutional neural network for velocity modeling，which reduces the network volume while maintaining prediction accuracy. Data test results demonstrate that the training processof the proposed network has lower requirements for high-performance hardware resources，and that the network enables eficient velocity inversion，possesses higher seismic velocity inversion accuracy，and exhibits superior noise resistance. It pro vides a new idea for solving the computing power bottleneck problem in seismic data inversion. Keywords：seismic velocity inversion，deep learning，U-Net，lightweight，feature extraction

张岩，王海潮，姚亮亮，等.基于轻量化U-Net的高效地震速度反演方法[J].石油地球物理勘探，2025，60（4）： 817-827.

ZHANG Yan，WANG Haichao， YAO Liangliang，et al. Efficient seismic velocity inversion method based on lightweight U-Net[J]. Oil Geophysical Prospecting，2025，60（4） ：817-827.

0 引言

键，影响着储层预测的精度。（剩余15470字）