.png){kind=icon}
返回
Reconstructing Regularly Missing Seismic Traces With a Classifier-Guided Diffusion Model
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3367354.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reconstructing missing seismic data is crucial for seismic processing and interpretation. Recent methods struggle when seismic traces are regularly missing, such as near-offset data. We proposed a classifier-guided conditional seismic denoising diffusion probabilistic model (CCSeis-DDPM) to enable consistent reconstructions. The CCSeis-DDPM adopts the Markov model architecture of DDPMs to generate high-quality results. The model involves classifier-guided training and tailored inference. During training, we use a U-Net with embedded timestep and three class labels for noise prediction, using classifier guidance to enhance reconstruction accuracy. In the inference phase, the model selectively samples unmasked regions using available seismic data. Our experiments on synthetic and field shot gathers with regularly missing near, mid, and far offsets show the proposed CCSeis-DDPM reconstructs regularly missing traces more accurately than current state-of-the-art methods, demonstrated qualitatively and quantitatively. This successful integration of diffusion probabilistic models with classification guidance and conditioning underscores the immense potential of this approach for enhancing seismic data reconstruction processes.
Keyword:
Training
Interpolation
Data models
Noise reduction
Image reconstruction
Gaussian noise
Gaussian distribution
Classifier
diffusion model
seismic reconstruction
U-Net
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
What can machine learning do for seismic data processing? An interpolation application.png)
GEOPHYSICS
GEOPHYSICSIF3.2
PREAI
分享收藏
查看更多内容