石油物探2026，Vol.65Issue(2)：195-206,12.DOI:10.12431/issn.1000-1441.2025.0257
基于相似度测量的无监督学习方法压制地震外源相干噪声
Unsupervised learning method based on similarity measurement for suppressing seismic external source coherent noise
摘要
Abstract
Seismic external source coherent noise(ESCN)is generated by vibrations other than the main seismic source,and it overlaps significantly with effective signals in both the time domain and the frequency domain.ESCN tends to obscure the effective signals,thereby interfering with the effectiveness of seismic exploration.To suppress ESCN,this study proposes an unsupervised learning method based on similarity measurement.The study uses the average cosine similarity function to determine the apparent velocity of the noise,obtain the noise propagation direction,and calculate the proportion of the noise in the original data,thereby deriving the predicted ESCN.There are differences in amplitudes between the predicted ESCN and the true ESCN.Unsupervised deep neural networks,with excellent nonlinear mapping capability,can correct amplitudes of the predicted ESCN and obtain the amplitude-corrected estimated value of ESCN as well as the results of effective signals by minimizing the mean absolute error loss function.The proposed unsupervised learning method,which does not rely on true labeled data,can effectively address the issue of missing training datasets in field data acquisition,and exhibits a broad applicability.Examples of synthetic and field data demonstrate that the proposed method in this study can effectively suppress ESCN,with its performance superior to that of the traditional similarity measurement method,the conventional frequency-wavenumber(FK)filter method,and the Karhunen-Loeve(KL)filter method.关键词
无监督学习/地震信号/外源噪声/相干噪声/相似度测量Key words
unsupervised learning/seismic signal/external source noise/coherent noise/similarity measurement分类
能源科技引用本文复制引用
王坤喜,饶莹,胡天跃,赵振聪,陈涛,王春明,张征..基于相似度测量的无监督学习方法压制地震外源相干噪声[J].石油物探,2026,65(2):195-206,12.基金项目
国家自然科学基金项目(42025402,42430803,42504113)、中国石油大学(北京)科研基金项目(2462024BJRC019)和中国石油大学(北京)学科前沿交叉探索专项(2462024XKQY005)共同资助. This research is financially supported by the National Natural Science Foundation of China(Grant Nos.42025402,42430803 and 42504113),the Science Foundation of China University of Petroleum(Beijing)(Grant No.2462024BJRC019),and the Frontier Interdisciplinary Exploration Research Program of China University of Petroleum(Beijing)(Grant No.2462024XKQY005). （42025402,42430803,42504113）
