Seismic surface wave detection method based on convolutional neural network

The invention provides a seismic surface wave detection method based on a convolutional neural network. The seismic surface wave detection method based on the convolutional neural network comprises the steps of 1, preprocessing seismic data; step 2, extracting high-dimensional features of the seismic signals by using a convolutional network; and step 3, generating a surface wave distribution area by using the deconvolution network. According to the seismic surface wave detection method based on the convolutional neural network, the problem that surface wave noise in seismic pre-stack data cannot be automatically and accurately positioned is solved, the distribution area of surface waves in seismic pre-stack signals can be automatically detected through the convolutional neural network, and the precision and the intelligent degree of surface wave labeling can be improved. 本发明提供一种基于卷积神经网络的地震面波检测方法，该基于卷积神经网络的地震面波检测方法包括：步骤1，对地震资料做预处理；步骤2，使用卷积网络提取地震信号的高维特征；步骤3，使用反卷积网络生成面波分布区域。该基于卷积神经网络的地震面波检测方法针对地震叠前数据中面波噪音无法自动精确定