Deep-Learning Inversion of Seismic Data

Li, Shucai; Liu, Bin; Ren, Yuxiao; Chen, Yangkang; Yang, Senlin; Wang, Yunhai; Jiang, Peng

doi:10.1109/tgrs.2019.2953473

Cited by 252 publications

(86 citation statements)

References 49 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To make the comparison in a more realistic situation, we design the velocity models to have some complex geology structures like folding layers and faults, and 20 seismic sources and 32 receivers are evenly placed on the top layer to generate the corresponding observation data. By following the setup parameters shown in the reference [32], we train the SeisInvNet for 200 epochs and its inversion effect on the test dataset is compared with the SWINet, which is trained on the observation data of each test velocity model based on the same network setup as the color green indicates in Table 1. An example of the comparison experiment result is shown in Fig.…”

Section: Comparison With Seisinvnetmentioning

confidence: 99%

“…Wu et al [31] proposed a CNN-based network called InversionNet to directly map the raw seismic data to the corresponding seismic velocity model and it achieved good inversion effect on simple fault models with flat or curved subsurface layers. More recently, Li et al [32] deeply analyzed the features of mapping the time-series seismic data to a velocity image and then developed a novel DNN framework called SeisInvNet to perform the end-to-end velocity inversion mapping with enhanced single-trace seismic data as the input. In a word, various DNN frameworks have been adopted into the task of seismic velocity inversion and some of them have already outperformed the traditional FWI on simple velocity models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

Ren

Yang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Seismic full waveform inversion is a common technique that is used in the investigation of subsurface geology. Its classic implementation involves forward modeling of seismic wavefield based on a certain type of wave equation, which reflects the physics nature of subsurface seismic wavefield propagation. However, obtaining a good inversion result using traditional seismic waveform inversion methods usually comes with a high computational cost. Recently, with the emerging popularity of deep learning techniques in various computer vision tasks, deep neural network (DNN) has demonstrated an impressive ability in dealing with complex nonlinear problems, including seismic velocity inversion. Now, extensive efforts have been made in developing a DNN architecture to tackle the problem of seismic velocity inversion, and promising results have been achieved. However, due to the dependence of a labeled dataset, i.e., the barely accessible true velocity model corresponding to real seismic data, the current supervised deep learning inversion framework may suffer from limitations on generalization. One possible solution to mitigate this issue is to impose the governing physics into this kind of purely data-driven method. Thus, following the procedures of traditional seismic full waveform inversion, we propose a seismic waveform inversion network, namely SWINet, based on wave-equation-based forward modeling network cells. By treating the single-shot observation data and its corresponding shot position as training data pairs, the inverted velocity model can be obtained as the trainable network parameters. Moreover, since the proposed seismic waveform inversion method is performed in a neural-network way, its implementation and inversion effect could benefit from some built-in tools in Pytorch, such as automatic differentiation, Adam optimizer and minibatch strategy, etc. Numerical examples indicate that the SWINet method may possess great potential in resulting a good velocity inversion effect with relatively fast convergence and lower computation cost. INDEX TERMS acoustic wavefield modeling, deep learning inversion, seismic waveform inversion

show abstract

Section: Comparison With Seisinvnetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

Ren

Yang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Araya-Polo et al [34] use a velocity related feature cube transferred from raw seismic data to generate velocity model by CNNs, while Wu, Lin, and Zhou [35] treat seismic inversion as image mapping and build the mapping from seismic profiles to velocity model directly. Further, Li et al [36] figure out the weak spatial correspondence and the uncertain reflectionreception relationship problems between seismic data and velocity model, and propose to generate spatially aligned features by MLPs at first. The latter two works could build the mapping from raw seismic data to velocity model directly without data pre-processing.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Inversion of Electrical Resistivity Data

Liu

Guo

et al. 2020

IEEE Trans. Geosci. Remote Sensing

Self Cite

139

View full text Add to dashboard Cite

The inverse problem of electrical resistivity surveys (ERS) is difficult because of its nonlinear and ill-posed nature. For this task, traditional linear inversion methods still face challenges such as sub-optimal approximation and initial model selection. Inspired by the remarkable non-linear mapping ability of deep learning approaches, in this paper we propose to build the mapping from apparent resistivity data (input) to resistivity model (output) directly by convolutional neural networks (CNNs). However, the vertically varying characteristic of patterns in the apparent resistivity data may cause ambiguity when using CNNs with the weight sharing and effective receptive field properties. To address the potential issue, we supply an additional tier feature map to CNNs to help it get aware of the relationship between input and output. Based on the prevalent U-Net architecture, we design our network (ERSInvNet) which can be trained endto-end and reach real-time inference during testing. We further introduce depth weighting function and smooth constraint into loss function to improve inversion accuracy for the deep region and suppress false anomalies. Four groups of experiments are considered to demonstrate the feasibility and efficiency of the proposed methods. According to the comprehensive qualitative analysis and quantitative comparison, ERSInvNet with tier feature map, smooth constraints and depth weighting function together achieve the best performance.

show abstract

“…Richardson (2018) constructs FWI as recurrent neural networks. Araya-Polo et al (2018); Wu et al (2018); Li et al (2019) produce layered velocity models from shot gathers with DNN.…”

Section: Introductionmentioning

confidence: 99%

Extrapolated full-waveform inversion with deep learning

2020

View full text Add to dashboard Cite

The lack of low frequency information and a good initial model can seriously affect the success of full waveform inversion (FWI), due to the inherent cycle skipping problem. Computational low frequency extrapolation is in principle the most direct way to address this issue. By considering bandwidth extension as a regression problem in machine learning, we propose an architecture of convolutional neural network (CNN) to automatically extrapolate the missing low frequencies without preprocessing and post-processing steps. The bandlimited recordings are the inputs of the CNN and, in our numerical experiments, a neural network trained from enough samples can predict a reasonable approximation to the seismograms in the unobserved low frequency band, both in phase and in amplitude. The numerical experiments considered are set up on simulated P-wave data. In extrapolated FWI (EFWI), the low-wavenumber components of the model are determined from the extrapolated low frequencies, before proceeding with a frequency sweep of the bandlimited data. The proposed deep-learning method of low-frequency extrapolation shows adequate generalizability for the initialization step of EFWI. Numerical examples show that the neural network trained on several submodels of the Marmousi model is able to predict the low frequencies for the BP 2004 benchmark model. Additionally, the neural network can robustly process seismic data with uncertainties due to the existence of noise, poorly-known source wavelet, and different finite-difference scheme in the forward modeling operator. Finally, this approach is not subject to the structural limitations of other methods for bandwidth extension, and seems to offer a tantalizing solution to the problem of properly initializing FWI.

show abstract

Deep-Learning Inversion of Seismic Data

Cited by 252 publications

References 49 publications

A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

Deep Learning Inversion of Electrical Resistivity Data

Extrapolated full-waveform inversion with deep learning

Contact Info

Product

Resources

About