Deep learning for multidimensional seismic impedance inversion

Wu, Xinming; Yan, Shangsheng; Bi, Zhengfa; Zhang, Sibo; Si, Hongjie

doi:10.1190/geo2020-0564.1

Cited by 58 publications

(23 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lateral discontinuity is a common problem in current data-driven inversion. Wu solves this problem using a multidimensional inversion approach [11], which uses a 2D neural network to learn 1D labels and sets the weight of unlabeled regions to 0. Learning using sparse labels was first proposed in 3D UNet and used in 3D medical image segmentation [33], later applied to geophysical fields such as inversion and fault detection [5], [6], [11].…”

Section: A Semi-supervised Learningmentioning

confidence: 99%

“…4, 7) still requires 34 logging labels, and its predictions have significant discontinuities in the horizontal direction, the same drawback is also reflected in other semi-supervised impedance inversion methods [30]- [32]. The discontinuity in the horizontal direction is due to the fact that these methods try to match the dimensionality of the logs by downscaling the 3D or 2D seismic data, which is avoided by the multidimensional inversion proposed by Wu et al [11], the idea of this method originates from medical image segmentation [33], where the model is trained using labels of the same dimensionality as the seismic and the weights of the unlabeled regions are set to zero. The method achieved a significant performance improvement with the use of 40 logs in SEAM.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ContrasInver: Voxel-wise Contrastive Semi-supervised Learning for Seismic Inversion

Dou¹,

Li²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent studies have shown that learning theories have been very successful in hydrocarbon exploration. Inversion of seismic into various attributes through the relationship of 1D well-logs and 3D seismic is an essential step in reservoir description, among which, acoustic impedance is one of the most critical attributes, and although current deep learningbased impedance inversion obtains promising results, it relies on a large number of logs (1D labels, typically more than 30 well-logs are required per inversion), which is unacceptable in many practical explorations. In this work, we define acoustic impedance inversion as a regression task for learning sparse 1D labels from 3D volume data and propose a voxel-wise semisupervised contrastive learning framework, ContrasInver, for regression tasks under sparse labels. ConstraInver consists of several key components, including a novel pre-training method for 3D seismic data inversion, a contrastive semi-supervised strategy for diffusing well-log information to the global, and a continuous-value vectorized characterization method for a contrastive learning-based regression task, and also designed the distance TopK sampling method for improving the training efficiency. We performed a complete ablation study on SEAM Phase I synthetic data to verify the effectiveness of each component and compared our approach with the current mainstream methods on this data, and our approach demonstrated very significant advantages. In this data we achieved an SSIM of 0.92 and an MSE of 0.079 with only four well-logs. ConstraInver is the first purely data-driven approach to invert two classic field data, F3 Netherlands (only four well-logs) and Delft (only three well-logs) and achieves very reasonable and reliable results.

show abstract

Section: A Semi-supervised Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ContrasInver: Voxel-wise Contrastive Semi-supervised Learning for Seismic Inversion

Dou¹,

Li²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Compared with traditional methods, deep learning does not require manually defined criteria and automatically picks up the deep-level information of images. Deep learning has been successfully employed for data processing and interpretation in seismic exploration, for example, seismic data noise attenuation [30] [31] [32] [33], first-arrival picking [34] [35] [36], velocity model building [37] [38] [39], impedance inversion [40] [41], and seismic structural interpretation [42] [43] [44]. Although, a few advances in deep learning have been reported for simultaneous-source data deblending [45] [46] [47], few studies have used deep learning for image denoising in multi-source seismic migration.…”

Section: Startmentioning

confidence: 99%

Deep Learning for Enhancing Multisource Reverse Time Migration

Jia

et al. 2022

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Reverse time migration (RTM) is a technique used to obtain high-resolution images of underground reflectors; however, this method is computationally intensive when dealing with large amounts of seismic data. Multi-source RTM can significantly reduce the computational cost by processing multiple shots simultaneously. However, multi-source-based methods frequently result in crosstalk artifacts in the migrated images, causing serious interference in the imaging signals. Plane-wave migration, as a mainstream multi-source method, can yield migrated images with plane waves in different angles by implementing phase encoding of the source and receiver wavefields; however, this method frequently requires a trade-off between computational efficiency and imaging quality. We propose a method based on deep learning for removing crosstalk artifacts and enhancing the image quality of plane-wave migration images. We designed a convolutional neural network that accepts an input of seven plane-wave images at different angles and outputs a clear and enhanced image. We built 505 1024×256 velocity models, and employed each of them using plane-wave migration to produce raw images at 0°, ±20°, ±40°, and ±60°as input of the network. Labels are high-resolution images computed from the corresponding reflectivity models by convolving with a Ricker wavelet. Random sub-images with a size of 512×128 were used for training the network. Numerical examples demonstrated the effectiveness of the trained network in crosstalk removal and imaging enhancement. The proposed method is superior to both the conventional RTM and plane-wave RTM (PWRTM) in imaging resolution. Moreover, the proposed method requires only seven migrations, significantly improving the computational efficiency. In the numerical examples, the processing time required by our method was approximately 1.6% and 10% of that required by RTM and PWRTM, respectively.

show abstract

“…The inversion method based on trace by trace does not exploit the spatial correlation in the horizontal direction, which may lead to poor horizontal continuity of inversion results. To improve the continuity, Wu et al (2021) proposed a 2D network-based inversion method.…”

Section: Introductionmentioning

confidence: 99%

Multichannel seismic impedance inversion based on Attention U-Net

Ning

Li²,

Ma³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Recently, seismic inversion has made extensive use of supervised learning methods. The traditional deep learning inversion network can utilize the temporal correlation in the vertical direction. Still, it does not consider the spatial correlation in the horizontal direction of seismic data. Each seismic trace is inverted independently, which leads to noise and large geological variations in seismic data, thus leading to lateral discontinuity. Given this, the proposed method uses the spatial correlation of the seismic data in the horizontal direction. In the network training stage, several seismic traces centered on the well-side trace and the corresponding logging curve form a set of training sample pairs for training, to enhance the lateral continuity and anti-noise performance. Additionally, Attention U-Net is introduced in acoustic impedance inversion. Attention U-Net adds attention gate (AG) model to the skip connection between the encoding and decoding layers of the U-Net network, which can give different weights to different features, so the model can focus on the features related to the inversion task and avoid the influence of irrelevant data and noise during the inversion process. The performance of the proposed method is evaluated using the Marmousi2 model and the SEAM model and compared with other methods. The experimental results show that the proposed method has the advantages of high accuracy of acoustic impedance value inversion, good transverse continuity of inversion results, and strong anti-noise performance.

show abstract

Deep learning for multidimensional seismic impedance inversion

Cited by 58 publications

References 32 publications

ContrasInver: Voxel-wise Contrastive Semi-supervised Learning for Seismic Inversion

ContrasInver: Voxel-wise Contrastive Semi-supervised Learning for Seismic Inversion

Deep Learning for Enhancing Multisource Reverse Time Migration

Multichannel seismic impedance inversion based on Attention U-Net

Contact Info

Product

Resources

About