The mapping of seismic facies from seismic data is considered a multi-class image semantic segmentation problem. Despite the signification progress made by deep learning methods in seismic prospecting, the dense prediction problem of seismic facies requires large amounts of annotated seismic facies data, which is often unavailable. And these valuable labels are only helpful in one model and field due to geologic heterogeneity. To overcome these challenges, we developed a few-shot seismic facies segmentation model. Few-shot learning has been designed to learn to perform with very few labels, and we design reconstructing masked traces as a pretext task for self-supervised learning to get a good feature extractor. By these, this model can use all seismic data from different fields, which is different from image data as texture-based data. With two different seismic data in turn as a meta-training set and a meta-testing set, the proposed model works well in one-shot and five-shot settings, which means only one label and five labels, respectively.

No abstract

No abstract

No abstract

No abstract