石油地球物理勘探2025，Vol.60Issue(3)：643-653,11.DOI:10.13810/j.cnki.issn.1000-7210.20240270
应用MMTONet的迁移学习智能盐体分割方法
Transfer learning-based intelligent salt body segmentation method using MMTONet
摘要
Abstract
Salt bodies are geological structures with good airtightness,which are conducive to oil and gas stor-age.It is extremely necessary to achieve refined interpretation of salt bodies.However,unlike faults,salt bod-ies have more complex characteristics and significant morphological differences,and thus conventional methods can easily lead to confusion and misjudgment.In addition,since data-driven salt body recognition models have poor generalization ability on actual datasets,there are still challenges in interpreting and visualizing salt bodies in seismic exploration.The paper regards salt body interpretation as a semantic segmentation problem for seis-mic images and proposes an intelligent salt body segmentation method based on the context fusion of transfer learning and mixed attention(multi-path structure mixed attention and transfer optimized net,MMTONet).At the same time,a salt body context feature fusion module is designed,and an improved attention convolution mixed skip connection mechanism is established to better compensate for the information loss caused by down-sampling,thereby improving the pixel-level discrimination ability of the model for salt body boundaries and highamplitude noise.On this basis,a transfer learning adapter fine-tuning strategy is also designed to improve the generalization ability of the model on actual data.The experimental results on seismic datasets show that MMTONet outperforms mainstream semantic segmentation methods in improving segmentation accuracy and reducing computational and parameter complexity.关键词
深度学习/盐体分割/地震图像/迁移学习/MMTONet方法Key words
deep learning/salt body segmentation/seismic image/transfer learning/MMTONet method分类
地质学引用本文复制引用
李克文,范娅婷,徐志峰,贾韶辉..应用MMTONet的迁移学习智能盐体分割方法[J].石油地球物理勘探,2025,60(3):643-653,11.基金项目
本项研究受国家自然科学基金重大基金项目"储层天然气水合物相变和渗流多场时空演化规律"(51991365)和山东省自然科学基金项目"基于多源数据融合的浊积岩有效储层预测方法"(ZR2021MF082)联合资助. （51991365）
