Horizon tracking is basic and important work in seismic data interpretation,but the accuracy of con-ventional methods makes it difficult to meet the requirements of actual production.Therefore,this paper pro-poses a method for high-precision multi-set horizon tracking based on U2-Net.Firstly,a method is designed to produce filling labels,which traverse each pixel of seismic data to determine the location of each pixel and di-vide a horizon region for it.The method can automatically search for the adjacent horizons for the fault-crossing horizons,thus realizing the production of filling labels for the seismic reflection horizons and unconformities un-der the complex conditions of partial horizons and faults.Then,a U2-Net model is used to train the F3 data and the M-zone seismic data by utilizing the filling labels.Compared with the U-Net+PPM model,the U2-Net model has higher prediction accuracy,better stability,stronger generalization,and shorter training time.In ad-dition,its accuracy and Mean Intersection over Union both exceed 95％in predicting the seismic reflection hori-zons in complex areas.The proposed method can be better adapted to the horizon tracking of seismic data with low signal-to-noise ratio.
万方数据