CT理论与应用研究2025，Vol.34Issue(6)：1017-1028,12.DOI:10.15953/j.ctta.2025.167
VSP数据波场分离方法评价及深度学习标签方案优选
Evaluation of Wavefield Separation Methods for Vertical Seismic Profile Data and Optimization of Deep Learning Labeling Schemes
汪洋 1郑多明 1尚江伟 1张恩嘉 2王腾宇 1周强 2张振 1魏巍 1黄录忠1
作者信息
- 1. 中国石油天然气股份有限公司塔里木油田公司,新疆库尔勒 841000||中国石油天然气集团有限公司超深层复杂油气藏勘探开发技术研发中心,新疆库尔勒 841000||新疆维吾尔自治区超深层复杂油气藏勘探开发工程研究中心,新疆库尔勒 841000
- 2. 东方地球物理勘探有限责任公司物探技术研究中心,河北涿州 072750
- 折叠
摘要
Abstract
The core of vertical seismic profile(VSP)data processing lies in accurately separating upgoing and downgoing waves,and the quality of this separation directly affects the reliability of imaging and inversion of formation parameters.Current mainstream methods include frequency-wavenumber(f-k)filtering,the Radon transform and its improved high-precision algorithms,median filtering,and sparse constraint-based optimization methods.However,these methods incur high trial-and-error costs because of parameter sensitivity and difficulty in balancing fidelity and efficiency in complex wavefields.This study conducted a detailed theoretical analysis and data testing on common methods from the aspects of separation accuracy,processing efficiency,and operation procedures.Considering label generation in deep learning,the study tested the adaptability of different methods for label production,thereby making suggestions for label optimization to improve the quality and production efficiency of training data.In addition,the study constructs a rich label library based on data from multiple work areas,trains a general wavefield separation model,and realizes efficient processing of unknown data,which ultimately improve the accuracy and efficiency of wavefield separation.关键词
VSP波场分离/深度学习标签/高精度Radon变换/标签优选Key words
VSP wavefield separation/deep learning labels/high-precision Radon transform/label optimization分类
天文与地球科学引用本文复制引用
汪洋,郑多明,尚江伟,张恩嘉,王腾宇,周强,张振,魏巍,黄录忠..VSP数据波场分离方法评价及深度学习标签方案优选[J].CT理论与应用研究,2025,34(6):1017-1028,12.
