Application of deep learning optimization algorithm in full waveform inversion

2020 ◽  
Author(s):  
Jiachun You ◽  
Junxing Cao
Keyword(s):  
Deep Learning ◽  
Optimization Algorithm ◽  
Waveform Inversion ◽  
Full Waveform Inversion ◽  
Full Waveform

Layered low-frequency extrapolation with deep learning in full-waveform inversion

2021 ◽  
Author(s):  
Yao Liu ◽  
Baodi Liu ◽  
Jianping Huang ◽  
Jun Wang ◽  
Honglong Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Waveform Inversion ◽  
Low Frequency ◽  
Full Waveform Inversion ◽  
Full Waveform

Deep-learning seismic full-waveform inversion for realistic structural models

Geophysics ◽  
2021 ◽  
Vol 86 (1) ◽  
pp. R31-R44
Author(s):  
Bin Liu ◽  
Senlin Yang ◽  
Yuxiao Ren ◽  
Xinji Xu ◽  
Peng Jiang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Waveform Inversion ◽  
Structural Models ◽  
Velocity Model ◽  
Dense Layer ◽  
Full Waveform Inversion ◽  
Model Inversion ◽  
Full Waveform ◽  
Inversion Methods ◽  
The Common

Velocity model inversion is one of the most important tasks in seismic exploration. Full-waveform inversion (FWI) can obtain the highest resolution in traditional velocity inversion methods, but it heavily depends on initial models and is computationally expensive. In recent years, a large number of deep-learning (DL)-based velocity model inversion methods have been proposed. One critical component in those DL-based methods is a large training set containing different velocity models. We have developed a method to construct a realistic structural model for the DL network. Our compressional-wave velocity model building method for creating dense-layer/fault/salt body models can automatically construct a large number of models without much human effort, which is very meaningful for DL networks. Moreover, to improve the inversion result on these realistic structural models, instead of only using the common-shot gather, we also extract features from the common-receiver gather as well. Through a large number of realistic structural models, reasonable data acquisition methods, and appropriate network setups, a more generalized result can be obtained through our proposed inversion framework, which has been demonstrated to be effective on the independent testing data set. The results of dense-layer models, fault models, and salt body models that we compared and analyzed demonstrate the reliability of our method and also provide practical guidelines for choosing optimal inversion strategies in realistic situations.

scholarly journals ML-descent: An optimization algorithm for full-waveform inversion using machine learning

Geophysics ◽  
2020 ◽  
Vol 85 (6) ◽  
pp. R477-R492 ◽  
Author(s):  
Bingbing Sun ◽  
Tariq Alkhalifah
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Inverse Problem ◽  
Optimization Algorithm ◽  
Waveform Inversion ◽  
Slight Modification ◽  
Descent Method ◽  
Quadratic Functions ◽  
Full Waveform Inversion ◽  
Full Waveform

Full-waveform inversion (FWI) is a nonlinear optimization problem, and a typical optimization algorithm such as the nonlinear conjugate gradient or limited-memory Broyden-Fletcher-Goldfarb-Shanno (LBFGS) would iteratively update the model mainly along the gradient-descent direction of the misfit function or a slight modification of it. Based on the concept of meta-learning, rather than using a hand-designed optimization algorithm, we have trained the machine (represented by a neural network) to learn an optimization algorithm, entitled the “ML-descent,” and apply it in FWI. Using a recurrent neural network (RNN), we use the gradient of the misfit function as the input, and the hidden states in the RNN incorporate the history information of the gradient similar to an LBFGS algorithm. However, unlike the fixed form of the LBFGS algorithm, the machine-learning (ML) version evolves in response to the gradient. The loss function for training is formulated as a weighted summation of the L2 norm of the data residuals in the original inverse problem. As with any well-defined nonlinear inverse problem, the optimization can be locally approximated by a linear convex problem; thus, to accelerate the training, we train the neural network by minimizing randomly generated quadratic functions instead of performing time-consuming FWIs. To further improve the accuracy and robustness, we use a variational autoencoder that projects and represents the model in latent space. We use the Marmousi and the overthrust examples to demonstrate that the ML-descent method shows faster convergence and outperforms conventional optimization algorithms. The energy in the deeper part of the models can be recovered by the ML-descent even when the pseudoinverse of the Hessian is not incorporated in the FWI update.

scholarly journals A Hybrid Method Applied to Improve the Efficiency of Full-Waveform Inversion for Pavement Characterization

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 2916 ◽  
Author(s):  
Jingwei Zhang ◽  
Shengbo Ye ◽  
Li Yi ◽  
Yuquan Lin ◽  
Hai Liu ◽  
...  
Keyword(s):  
Hybrid Method ◽  
Optimization Algorithm ◽  
High Efficiency ◽  
Estimation Error ◽  
Waveform Inversion ◽  
Multilayer Perceptrons ◽  
Full Waveform Inversion ◽  
Inversion Algorithm ◽  
Full Waveform ◽  
Two Stages

Ground penetrating radar (GPR), as a nondestructive testing tool, is suitable for estimating the thickness and permittivity of layers within the pavement. However, it would become problematic when the layer is thin with respect to the probing pulse width, in which case overlapping between the reflected pulses occurs. In order to deal with this problem, a hybrid method based on multilayer perceptrons (MLPs) and a local optimization algorithm is proposed. This method can be divided into two stages. In the first stage, the MLPs roughly estimate the thickness and the permittivity of the GPR signal. In the second stage, these roughly estimated values are used as the initial solution of the full-waveform inversion algorithm. The hybrid method and the conventional global optimization algorithm are respectively used to perform the full-waveform inversion of the simulated GPR data. Under the same inversion precision, the objective function needs to be calculated for 450 times and 30 times for the conventional method and the hybrid method, respectively. The hybrid method is also applied to a measured data, and the thickness estimation error is 1.2 mm. The results show the high efficiency and accuracy of such hybrid method to resolve the problem of estimating the thickness and permittivity of a “thin layer”.

Sign in / Sign up

Export Citation Format

Share Document