联系我们
意见反馈

关注公众号

获得最新科研资讯

SWPI_QU Lab

Intro block Seismic Wave Propagation and Imaging

Share

Topic 9: AI for seismic velocity building

1.  We present a multiscale fusion network with shot record attention (MFNSR) module, which can construct velocity models directly from the original seismic record. The proposed network can obtain fine-grained complete semantic information in the shot record by multilayer fusion operation. Shot record attention (SR-attention) is proposed to reveal the medium-to-low frequency information in the shot record. The proposed random noise block enables better generalization of the model and higher accuracy in modeling the shot record speed of the entrained noise.

“Multiscale Fusion Network With SR-Attention for Seismic Velocity Model Building” can be downloaded and viewed as a pdf, or click this link.

Created: May 03, 2024 | 17:04