Applying machine learning to 3D seismic image denoising and enhancement

Применение машинного обучения для шумоподавления и повышения качества трехмерных сейсмических изображений
Enning Wang, Jeff Nealon
2019-04-02

3D seismic image denoisingGulf of Mexico seismic datadeep 3D convolutional neural networkmigration artifact attenuationpoststack seismic image enhancement
We have trained a supervised deep 3D convolutional neural network (CNN) on marine seismic images for poststack structural seismic image enhancement and noise attenuation. Rather than adding artificial noise to training inputs, the difference in noise levels between the training inputs and labels was created by shot density differences. This design enables the trained CNN to mimic the results and power of stacking to specifically target random and coherent migration artifacts while enhancing low-amplitude reflections. We used field seismic from multiple Gulf of Mexico surveys to train the CNN and the SEG Advanced Modeling (SEAM) phase I synthetic data to evaluate the trained network. The diverse geologic features in the training data are needed to avoid overfitting. The processed outputs of the trained neural network are much cleaner than the inputs, and they highlight geologic structures for easier interpretation. Different scales of geologic structures, from high-resolution faults and diffractors to deep subsalt sediments, are well-preserved by the deep neural network. The trained network can be applied on either prestack gathers or poststack images. The approach is easy to implement and straightforward to parameterize, and it has proven to be an effective and flexible production tool for post-migration data conditioning.
1
A supervised deep 3D CNN was trained for poststack seismic image enhancement, noise attenuation, and preservation of geological structures.
2
Evaluation on SEAM phase I synthetic data showed substantially cleaner outputs that highlighted geological structures for easier interpretation.
3
The method preserved structures across scales, from high-resolution faults and diffractors to deep subsalt sediments, and was applicable to prestack gathers or poststack images.
4
The network targets random noise and coherent migration artifacts while enhancing low-amplitude seismic reflections.
5
Training used shot-density differences between inputs and labels rather than artificially added noise, allowing the CNN to mimic stacking effects.

marine 3D seismic images, including field Gulf of Mexico surveys and SEAM phase I synthetic data

poststack structural image enhancement and attenuation of random and coherent migration artifacts while preserving low-amplitude reflections and multiscale geologic structures

Publication Details
Publication Date
2019-04-02
Journal
Publisher
ISSN
Cited by
64
Access Type
Author Information
Authors
Enning Wang
Jeff Nealon
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%