Fault Imaging of Seismic Data Based on a Modified U-Net with Dilated Convolution

Abstract

Fault imaging follows the processing and migration imaging of seismic data, which is very important in oil and gas exploration and development. Conventional fault imaging methods are easily influenced by seismic data and interpreters’ experience and have limited ability to identify complex fault areas and micro-faults. Conventional convolutional neural network uniformly processes feature maps of the same layer, resulting in the same receptive field of the neural network in the same layer and relatively single local information obtained, which is not conducive to the imaging of multi-scale faults. To solve this problem, our research proposes a modified U-Net architecture. Two functional modules containing dilated convolution are added between the encoder and decoder to enhance the network’s ability to select multi-scale information, enhance the consistency between the receptive field and the target region of fault recognition, and finally improve the identification ability of micro-faults. Training on synthetic seismic data and testing on real data were carried out using the modified U-Net. The actual fault imaging shows that the proposed scheme has certain advantages.

Keywords

• dilation rate
• deep learning
• data processing
• receptive field