Seismic Interpolation Transformer for Consecutively Missing Data: A Case Study in DAS-VSP Data

TL;DR

This paper introduces a transformer-based seismic data interpolation method, SIT, designed to effectively reconstruct consecutively missing DAS-VSP seismic traces, outperforming CNN-based approaches by capturing global features.

Contribution

The paper presents a novel transformer architecture with a U-shaped swin-transformer and a combined SSIM-L1 loss for improved consecutive missing data reconstruction in seismic signals.

Findings

SIT outperforms U-Net and swin-transformer in experiments.

The new architecture effectively captures global features for missing data reconstruction.

Ablation studies confirm the benefits of the proposed network design and loss function.

Abstract

Distributed optical fiber acoustic sensing (DAS) is a rapidly-developed seismic acquisition technology with advantages of low cost, high resolution, high sensitivity, and small interval, etc. Nonetheless, consecutively missing cases often appear in real seismic data acquired by DAS system due to some factors, including optical fiber damage and inferior coupling between cable and well. Recently, some deep-learning seismic interpolation methods based on convolutional neural network (CNN) have shown impressive performance in regular and random missing cases but still remain the consecutively missing case as a challenging task. The main reason is that the weight sharing makes it difficult for CNN to capture enough comprehensive features. In this paper, we propose a transformer-based interpolation method, called seismic interpolation transformer (SIT), to deal with the consecutively missing case. This proposed SIT is an encoder-decoder structure connected by some U-shaped swin-transformer blocks. In encoder and decoder part, the multi-head self-attention (MSA) mechanism is used to capture global features which is essential for the reconstruction of consecutively missing traces. The U-shaped swin-transformer blocks are utilized to perform feature extraction operations on feature maps with different resolutions. Moreover, we combine the loss based on structural similarity index (SSIM) and L1 norm to propose a novel loss function for SIT. In experiments, this proposed SIT outperforms U-Net and swin-transformer. Moreover, ablation studies also demonstrate the advantages of new network architecture and loss function.