DOAJ Open Access 2021

A SPD-UNet Model for Seismic Fault Image Identification

XI Yingjie, LI Kewen, XU Yanhui, ZHU Jianbing

Lihat Sumber DOI

Abstrak

Fault is the main factor that controls the formation and distribution of oil and gas fields, so the detection and identification of fault plays an important role in the exploration oil and gas fields.Based on the Attention-UNet model, this paper proposes an improved SPD-UNet model for fault identification in earthquake images.SPD-UNet introduces dilated convolution, which can effectively enhance image feature extraction while expanding the receptive field and preventing resolution loss.At the same time, the dilated convolutions in the pyramid structure are stacked to form the SPD module, which avoids the local information loss of dialted convolutions, and improves the correlation between fault information and image identification accuracy.Experimental results show that SPD-UNet exhibits a higher identification accuracy than SegNet and ResUNet.The fault position and shape identified by SPD-UNet are closer to actual information.

Topik & Kata Kunci

Computer engineering. Computer hardware Computer software

Penulis (1)

XI Yingjie, LI Kewen, XU Yanhui, ZHU Jianbing

Format Sitasi

APA MLA BibTeX

Jianbing, X.Y.L.K.X.Y.Z. (2021). A SPD-UNet Model for Seismic Fault Image Identification. https://doi.org/10.19678/j.issn.1000-3428.0059327

Akses Cepat

Lihat di Sumber doi.org/10.19678/j.issn.1000-3428.0059327

Informasi Jurnal

Tahun Terbit: 2021
Sumber Database: DOAJ
DOI: 10.19678/j.issn.1000-3428.0059327
Akses: Open Access ✓