Rapid Seismic Domain Transfer: Seismic Velocity Inversion and Modeling Using Deep Generative Neural Networks

Mosser, Lukas; Kimman, W.; Dramsch, Jesper Sören; Purves, Steve; Fuente, Alfredo De la; Ganssle, Graham

doi:10.3997/2214-4609.201800734

Cited by 51 publications

(23 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zheng et al (2017) applied recurrent neural networks to arrival picking microseismic or acoustic emission. Mosser et al (2018) used generative adversarial networks in seismic forward and inversion process. Qian et al (2018) used unsupervised deep convolutional autoencoder in seismic facies clustering.…”

Section: Introductionmentioning

confidence: 99%

Automatic Waveform Classification and Arrival Picking Based on Convolutional Neural Network

Chen

Zhang

Bai

et al. 2019

Earth and Space Science

View full text Add to dashboard Cite

Automatic waveform classification and arrival picking methods are widely studied to reduce or replace the manual works. Machine learning based methods, especially neural networks, and clustering based methods have shown great potentials in previous studies. However, most of the existing methods are sensitive to noise. The convolution neural networks (CNNs), developed from the traditional neural networks, have been successfully applied in many different fields, but are rarely studied in seismic waveform classification. In this paper, we propose a novel antinoise CNN architecture for waveform classification and also propose to combine k‐means clustering (KC) with CNN classification to pick arrivals (CNN‐KC). Seismic data are sampled to 1‐D vectors using a specific time window. Using the trained CNN classifier, these 1‐D vectors are classified into two categories: waveform and nonwaveform. With the constraint of the first waveform, CNN‐KC can pick the arrival more accurately. We also apply the proposed methods to the synthetic microseismic data with different noise levels and the actual field microseismic data to test their robustness. CNNs perform much better than the traditional multilayer perceptron on the waveform classification of the noisy microseismic data. Based on the analysis of the CNN internal architecture, we also conclude that the main reason that CNN is insensitive to noise is the convolution and pooling layers which behave like smooth operation in some ways. The final results show that the CNN and CNN‐KC are effective and robust methods for waveform classification and arrival picking.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Waveform Classification and Arrival Picking Based on Convolutional Neural Network

Chen

Zhang

Bai

et al. 2019

Earth and Space Science

View full text Add to dashboard Cite

show abstract

“…CycleGAN requires unpaired data, which is less of a strength in InSAR because interferograms and atmospheric models are paired data. Although it has shown good results when working with paired data [Zhu et al, 2017a, Mosser et al, 2018, using a more adapted method [Isola et al, 2017] could improve the results.…”

Section: Discussionmentioning

confidence: 99%

“…Such approach does not need paired images between input and output, so it is applicable to a wider range of problems, while showing accuracies close to methods requiring paired images. Cycle-consistency can also make CycleGAN more robust to noise even when paired images are available, as reported in seismic velocity inversion [Mosser et al, 2018]. Temporal decorrelation introduces noise in interferograms, making such robustness an attractive property.…”

Section: Image-to-image Translation Using Generative Adversarial Netwmentioning

confidence: 97%

An attempt at improving atmospheric corrections\\in InSAR using cycle-consistent adversarial networks

Rongier¹,

Rude²,

Herring³

et al. 2020

Preprint

View full text Add to dashboard Cite

“…Extracted features are obtained before the training process and are used as DNN inputs to train the network. Mosser et al (2018) used a generative adversarial network (Goodfellow et al, 2014) with cycle-constraints (Zhu et al, 2017) to perform seismic inversion by formulating this problem as a domain-transfer problem. The mapping between the post-stack seismic traces and P-wave velocity models was approximated through this learning method.…”

Section: Introductionmentioning

confidence: 99%

Deep-learning inversion: A next-generation seismic velocity model building method

2019

View full text Add to dashboard Cite

Seismic velocity is one of the most important parameters used in seismic exploration.Accurate velocity models are key prerequisites for reverse-time migration and other high-resolution seismic imaging techniques. Such velocity information has traditionally been derived by tomography or full-waveform inversion (FWI), which are time consuming and computationally expensive, and they rely heavily on human interaction and quality control. We investigate a novel method based on the supervised deep fully convolutional neural network (FCN) for velocity-model building (VMB) directly from raw seismograms. Unlike the conventional inversion method based on physical models, the supervised deep-learning methods are based on big-data training rather than prior-knowledge assumptions. During the training stage, the network establishes a nonlinear projection from the multi-shot seismic data to the corresponding velocity models.During the prediction stage, the trained network can be used to estimate the velocity models from the new input seismic data. One key characteristic of the deep-learning method is that it can automatically extract multi-layer useful features without the need for human-curated activities and initial velocity setup. The data-driven method usually requires more time during the training stage, and actual predictions take less time, with only seconds needed. Therefore, the computational time of geophysical inversions, including real-time inversions, can be dramatically reduced once a good generalized network is built. By using numerical experiments on synthetic models, the promising performances of our proposed method are shown in comparison with conventional FWI even when the input data are in more realistic scenarios. Discussions on the deep-learning methods, training dataset, lack of low frequencies, and advantages and disadvantages of the new method are also provided.

show abstract

Rapid Seismic Domain Transfer: Seismic Velocity Inversion and Modeling Using Deep Generative Neural Networks

Cited by 51 publications

References 10 publications

Automatic Waveform Classification and Arrival Picking Based on Convolutional Neural Network

Automatic Waveform Classification and Arrival Picking Based on Convolutional Neural Network

An attempt at improving atmospheric corrections\\in InSAR using cycle-consistent adversarial networks

Deep-learning inversion: A next-generation seismic velocity model building method

Contact Info

Product

Resources

About