Automatic velocity picking using dual-path convolutional neural network
In conventional seismic data processing,velocity analysis relies heavily on manually picking the ve-locity spectrum.However,this method is time-consuming,labor-intensive,and restricts the efficiency and ac-curacy of large-scale 3D seismic data processing.To address this issue,this paper propose an automatic velo-city spectrum picking method using a dual-path convolutional neural network(DCNN).Firstly,this paper uti-lize a convolutional neural network combined with an attention mechanism as the main network,extract the fea-tures of energy clusters from velocity spectrum data,and realize the automatic picking of velocity.Secondly,this paper train a main neural network to integrate the information of velocity and the hidden representation of the uncorrected CMP gather input by another convolutional neural network(auxiliary network)through feature fusion and feature transformation before outputting the time-velocity sequence,reconstructing the corrected CMP gather.Finally,the process of CMP gather dynamic correction is simulated through the auxiliary net-work,and the accuracy of speed picking is optimized using dynamic correction.Model and real data tests dem-onstrate that,after incorporating dynamic correction information through the auxiliary neural network,the pro-posed velocity spectrum picking method achieves a higher accuracy than a single CNN in velocity picking.
万方数据
维普
