A Label-Free High-Precision Residual Moveout Picking Method for Depth-Domain Tomography Based on Deep Learning

Residual moveout (RMO) provides critical information for depth-domain tomography. The current industry-standard method for fitting RMO involves scanning high-order polynomial equations. However, this analytical approach does not accurately capture abrupt variation of the RMO, leading to low iteration efficiency in tomographic inversion. Supervised learning-based image segmentation methods for picking can effectively capture local variations; however, they encounter challenges, such as a scarcity of reliable training samples and the high complexity of postprocessing. To address these issues, this study proposes a deep learning-based cascade picking method. It distinguishes accurate and robust RMOs using a segmentation network and a postprocessing technique based on trend regression. Additionally, a data synthesis method is introduced, enabling the segmentation network to be trained on synthetic datasets for effective picking in field data. Furthermore, a set of metrics are proposed to quantify the quality of automatically picked RMOs. Experimental results based on both model and real data demonstrate that compared to semblance-based methods, our approach achieves greater picking density and accuracy.