Super-resolution reconstruction of seismic section image via multi-scale convolution neural network

• Published in: E3S web of conferences 2021-01, Vol.303, p.1058
• Main Authors: Deng, Meng-Di, Jia, Rui-Sheng, Sun, Hong-Mei, Zhang, Xing-Li
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Convolution; High resolution; Image processing; Image reconstruction; Image resolution; Neural networks; Pixels; Signal to noise ratio; Spatial discrimination; Spatial resolution
• ISSN: 2267-1242; 2555-0403; 2267-1242
• DOI: 10.1051/e3sconf/202130301058

The resolution of seismic section images can directly affect the subsequent interpretation of seismic data. In order to improve the spatial resolution of low-resolution seismic section images, a super-resolution reconstruction method based on multi-scale convolution is proposed. This method designs a multi-scale convolutional neural network to learn high-low resolution image feature pairs, and realizes mapping learning from low-resolution seismic section images to high-resolution seismic section images. This multi-scale convolutional neural network model consists of four convolutional layers and a sub-pixel convolutional layer. Convolution operations are used to learn abundant seismic section image features, and sub-pixel convolution layer is used to reconstruct high-resolution seismic section image. The experimental results show that the proposed method is superior to the comparison method in peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the total training time and reconstruction time, our method is about 22% less than the FSRCNN method and about 18% less than the ESPCN method.