Noisy2Noisy: Denoise Pre-Stack Seismic Data Without Paired Training Data With Labels
Noisy2Noisy: Denoise Pre-Stack Seismic Data Without Paired Training Data With Labels
复制标题
Noisy2Noisy：在没有带有标签的配对训练数据的情况下对叠前地震数据进行降噪
DOI：
10.1109/lgrs.2022.3145835
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
Tonglin Li
中科院分区：
文献类型：
--
作者：
Dan Shao;Yuxing Zhao;Yue Li;Tonglin Li
近年来，基于监督式深度学习的去噪方法在地震数据处理领域得到了快速推广和发展。然而，监督训练受到成对训练数据（噪声）的质量和数量的限制
In recent years, supervised deep learning-based denoising methods have been popularized and developed rapidly in the field of seismic data processing. Supervised training, however, is limited by the quality and quantity of the paired training data (noisy