Deep Learning for Enhancing Multisource Reverse Time Migration

Yaxing Li

doi:10.1109/TGRS.2022.3206283

Deep Learning for Enhancing Multisource Reverse Time Migration

2022-01-01

6

OA

AI

DOI：10.1109/TGRS.2022.3206283

Original

Original request for help

Save

Abstract

En 中文

Reverse time migration (RTM) is a technique used to obtain high-resolution images of underground reflectors; however, this method is computationally intensive when dealing with large amounts of seismic data. Multisource RTM can significantly reduce the computational cost by processing multiple shots simultaneously. However, multisource-based methods frequently result in crosstalk artifacts in the migrated images, causing serious interference in the imaging signals. Plane-wave migration, as a mainstream multisource method, can yield migrated images with plane waves in different angles by implementing phase encoding of the source and receiver wavefields; however, this method frequently requires a trade-off between computational efficiency and imaging quality. We propose a method based on deep learning for removing crosstalk artifacts and enhancing the image quality of plane-wave migration images. We designed a convolutional neural network that accepts an input of seven plane-wave images at different angles and outputs a clear and enhanced image. We built over 500 1024 x 256 velocity models, and employed each of them using plane-wave migration to produce raw images at 0 degrees, +/- 10 degrees, +/- 20 degrees, and +/- 30 degrees as input of the network. Labels are high-resolution images computed from the corresponding reflectivity models by convolving with a Ricker wavelet. Random sub-images with a size of 512 x 128 were used for training the network. Numerical examples demonstrated the effectiveness of the trained network in crosstalk removal and imaging enhancement. The proposed method is superior to both the conventional RTM and plane-wave RTM (PWRTM) in imaging resolution. Moreover, the proposed method requires only seven migrations, significantly improving the computational efficiency. In the numerical examples, the processing time required by our method was approximately 1.6% and 10% of that required by RTM and PWRTM, respectively.

Keywords:

Computational efficiency

deep learning

high-resolution imaging

seismic waves

Deep Learning for Enhancing Multisource Reverse Time Migration

Abstract

Journal

Organization

Cited Papers