.png){kind=icon}
返回
Optimizing a transformer-based network for a deep-learning seismic processing workflow
.png){kind=icon}
OA
AI
DOI：10.1190/GEO2023-0403.1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
StorSeismic is a recently introduced model based on the transformer network to adapt to various seismic processing tasks through its pretraining and fine-tuning strategy. In the original implementation, StorSeismic uses a sinusoidal positional encoding (PE) and a conventional self-attention mechanism, borrowed from natural language processing applications. For seismic processing, they provide good results but also indicate limitations in efficiency and expressiveness. We develop modifications to these two key components, by using relative PE and low-rank attention matrices as replacements for the standard ones. Our changes are tested on processing tasks applied to realistic Marmousi and offshore field data as a sequential strategy, starting from denoising, direct-arrival removal, multiple attenuation, and mal moveout correction. We observe faster pretraining and competitive results on the fine-tuning tasks and, in addition, fewer parameters to train compared with the standard model.
期刊
IF:
3.2
论文数:
8.4K
被引数:
3.3W
机构
引用论文
Distributed acoustic sensing for near-surface imaging using submarine telecommunication cable: A case study in the Trondheimsfjord, Norway.png)
GEOPHYSICSOAAI
GEOPHYSICSIF3.2
OAAI分享收藏Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
OAAI
OAAI分享收藏Multi-Task Learning for Low-Frequency Extrapolation and Elastic Model Building From Seismic DataOAAI
OAAI分享收藏
查看更多内容