










摘要: 針對海洋可控源電磁(MCSEM)信號在勘探中極易受各種噪聲干擾, 影響后期反演以及數據處理準確性的問題, 提出一種注意力機制引導的卷積自編碼器海洋可控源電磁數據消噪方法. 首先基于自編碼器, 構建基于卷積自編碼器的海洋可控源電磁數據消噪網絡, 然后根據數據中存在噪聲的特點對其進行優化, 加深網絡深度、 引入注意力機制, 使網絡能更關注數據中的有效信號特征, 增強特征提取能力, 構建網絡模型, 實現對海洋可控源電磁數據噪聲的壓制. 實驗結果表明, 在對海洋可控源電磁數據噪聲壓制中, 該方法比db8小波消噪方法和變分模態分解消噪方法信噪比更高、 均方誤差更低, 同時應用到實測數據中仍能較完整地保留信號特征并增加偏移距的可解釋范圍, 證明了該方法在海洋可控源電磁數據噪聲壓制中的有效性.
關鍵詞: 海洋可控源電磁法; 深度學習; 卷積自編碼器; 注意力機制; 噪聲抑制
中圖分類號: TP391 文獻標志碼: A 文章編號: 1671-5489(2023)04-0929-08
A Noise Suppression Method for MCSEM Data
LI Suyi1, ZHANG Xinyu1, YANG Qiang1, ZHANG Yi1, DIAO Shu2
(1. College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130061, China;
2. School of Control Technology, Wuxi Institute of Technology, Wuxi 214121, Jiangsu Province, China)
Abstract: Aiming at" the problem that marine controlled-source electromagnetic (MCSEM) signals were prone to be interfered by various noises in exploration, which" affected the accuracy of later inversion and data processing, we proposed an attention mechanism-guided convolutional autoencoder marine controlled-source electromagnetic data denoising method. Firstly, based on" the" autoencoder, we constructed a noise suppression network based on convolutional autoencoder for marine controlled-source electromagnetic data. Secondly, we opimized it according to the characteristics of noise in the data, deepened the depth of the network, introduced attention mechanism to make the network pay more attention to the effective signal features in the data, enhanced the feature extraction ability, constructed the network model, and realized the noise suppression of marine" controlled-source electromagnetic data. The experimental results show that this method has higher signal-to-noise ratio and lower mean square error than the db8 wavelet noise suppression method and the variational mode decomposition noise suppression method. Meanwhile, it can still retain the signal features and increase the interpretable range of offset distance in the measured data, which proves the effectiveness of this method in the noise suppression of marine controlled-source electromagnetic data.
Keywords: marine controlled-source electromagnetic method; deep learning; convolutional autoencoder; attention mechanism; noise suppression
隨著全球經濟的高速發展和陸地資源的逐漸減少, 世界各國開始將資源勘探目光轉向海洋[1]. 海洋可控源電磁法(marine controlled-source electromagnetic method, MCSEM)是利用海底巖石層與油氣層電阻率的不同, 對海底油氣資源進行勘探的新興技術, 目前在海底資源勘探上已取得顯著效果, 提高了鉆井的成功率[2]. MCSEM法不僅可以探測海底油氣儲層, 還可以應用于海底天然氣水合物勘探, 探明其所處的位置以及分布范圍, 從而減少鉆井……