Low frequency extrapolation with deep learning
Hongyu Sun,Laurent Demanet +1 more
TL;DR: This paper proposes a deep-learning-based bandwidth extension method by considering low frequency extrapolation as a regression problem, and seems to offer a tantalizing solution to the problem of properly initializing FWI.
read more
Abstract: The lack of the low frequency information and good initial model can seriously affect the success of full waveform inversion (FWI) due to the inherent cycle skipping problem. Reasonable and reliable low frequency extrapolation is in principle the most direct way to solve this problem. In this paper, we propose a deep-learning-based bandwidth extension method by considering low frequency extrapolation as a regression problem. The Deep Neural Networks (DNNs) are trained to automatically extrapolate the low frequencies without preprocessing steps. The band-limited recordings are the inputs of the DNNs and, in our numerical experiments, the pretrained neural networks can predict the continuous-valued seismograms in the unobserved low frequency band. For the numerical experiments considered here, it is possible to find the amplitude and phase correlations among different frequency components by training the DNNs with enough data samples, and extrapolate the low frequencies from the band-limited seismic records trace by trace. The synthetic example shows that our approach is not subject to the structural limitations of other methods to bandwidth extension, and seems to offer a tantalizing solution to the problem of properly initializing FWI.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Deep learning for low-frequency extrapolation from multioffset seismic data
TL;DR: In this article, low-frequency seismic data are crucial for convergence of full-waveform inversion (FWI) to reliable subsurface properties, however, it is challenging to acquire field data with an appropria...
InversionNet: An Efficient and Accurate Data-Driven Full Waveform Inversion
Yue Wu,Youzuo Lin +1 more
TL;DR: In this paper, a convolutional neural network with an encoder-decoder structure was used to model the correspondence from seismic data to subsurface velocity structures, and a conditional random field (CRF) was employed on top of the CNN to generate structural predictions by modeling the interactions between different locations on the velocity model.
157
Extrapolated full-waveform inversion with deep learningEFWI-CNN
Hongyu Sun,Laurent Demanet +1 more
TL;DR: 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 as discussed by the authors.
140
Data-Driven Seismic Waveform Inversion: A Study on the Robustness and Generalization
Zhongping Zhang,Youzuo Lin +1 more
TL;DR: Zhang et al. as mentioned in this paper proposed a real-time data-driven technique called VelocityGAN, which is built on a generative adversarial network (GAN) and trained end-to-end to learn a mapping function from the raw seismic waveform data to the velocity image.
130
Deep learning for fast simulation of seismic waves in complex media
TL;DR: Two types of deep neural networks are presented as fast alternatives for simulating seismic waves in horizontally layered and faulted 2D acoustic media and it is shown that seismic inversion can be carried out by retraining the network with its inputs and outputs reversed, offering a fast alternative to existing inversion techniques.
References
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
Multilayer feedforward networks are universal approximators
TL;DR: It is rigorously established that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available.
23.1K
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 07 Dec 2015
TL;DR: In this paper, a Parametric Rectified Linear Unit (PReLU) was proposed to improve model fitting with nearly zero extra computational cost and little overfitting risk, which achieved a 4.94% top-5 test error on ImageNet 2012 classification dataset.
•Posted Content
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities.
15.1K
•Proceedings Article
Understanding the difficulty of training deep feedforward neural networks
Xavier Glorot,Yoshua Bengio +1 more
- 31 Mar 2010
TL;DR: The objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.