{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automatic-seismic-salt-interpretation-with","title":"Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks","arxiv_id":"1812.01101","date":"2018-11-24","proceeding":null,"authors":["Yu Zeng","Kebei Jiang","Jie Chen"],"abstract":"One of the most crucial tasks in seismic reflection imaging is to identify\nthe salt bodies with high precision. Traditionally, this is accomplished by\nvisually picking the salt/sediment boundaries, which requires a great amount of\nmanual work and may introduce systematic bias. With recent progress of deep\nlearning algorithm and growing computational power, a great deal of efforts\nhave been made to replace human effort with machine power in salt body\ninterpretation. Currently, the method of Convolutional neural networks (CNN) is\nrevolutionizing the computer vision field and has been a hot topic in the image\nanalysis. In this paper, the benefits of CNN-based classification are\ndemonstrated by using a state-of-art network structure U-Net, along with the\nresidual learning framework ResNet, to delineate salt body with high precision.\nNetwork adjustments, including the Exponential Linear Units (ELU) activation\nfunction, the Lov\\'{a}sz-Softmax loss function, and stratified $K$-fold\ncross-validation, have been deployed to further improve the prediction\naccuracy. The preliminary result using SEG Advanced Modeling (SEAM) data shows\ngood agreement between the predicted salt body and manually interpreted salt\nbody, especially in areas with weak reflections. This indicates the great\npotential of applying CNN for salt-related interpretations.","url_abs":"http://arxiv.org/abs/1812.01101v1","url_pdf":"http://arxiv.org/pdf/1812.01101v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automatic-seismic-salt-interpretation-with","repo_url":"https://github.com/mallerao/Seismic_CNN_Saltbody","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}