1-20 OF 296 RESULTS FOR

generative adversarial network models

Results shown limited to content with bounding coordinates.
Follow your search
Access your saved searches in your account

Would you like to receive an alert when new items match your search?
Close Modal
Sort by
Journal Article
Journal: Geophysics
Published: 20 February 2023
Geophysics (2023) 88 (2): M87–M103.
...Shuai Sun; Luanxiao Zhao; Huaizhen Chen; Zhiliang He; Jianhua Geng ABSTRACT Model-data-driven (MDD) generative adversarial networks (GANs) using prestack seismic data to estimate elastic parameters are proposed. First, by traverse sampling of elastic parameter model space and Gaussian sampling...
FIGURES | View All (20)
Image
Assessment of the quality of our best‐conditional <span class="search-highlight">generative</span> <span class="search-highlight">adversarial</span> ne...
Published: 22 April 2022
Figure 4. Assessment of the quality of our best‐conditional generative adversarial network model trained using three conditional variables: event–station distance, magnitude, and V S 30 . In each of the panels (a–f), average normalized amplitude spectra (upper pane) and average
Journal Article
Journal: The Leading Edge
Published: 01 February 2024
The Leading Edge (2024) 43 (2): 102–116.
... familiar with the actual rock than the geophysical data. A novel generative adversarial network (GAN) application is presented that constructs a photorealistic 3D virtual outcrop behind-the-outcrop model. The method combines GPR forward modeling with a conditional generative adversarial network (CGAN...
FIGURES | View All (11)
Image
Overview of the analysis framework. (a) The dataset consists of     M  w   ...
Published: 19 April 2024
a conditional generative adversarial network (cGAN) to generate temporal characteristics and another model using the generalized inversion technique (GIT) to generate amplitude characteristics. The conditions are M w , R hyp , and SITE. (c) In the prediction step, the generator of cGAN
Journal Article
Published: 22 April 2022
Bulletin of the Seismological Society of America (2022) 112 (4): 1979–1996.
...Figure 4. Assessment of the quality of our best‐conditional generative adversarial network model trained using three conditional variables: event–station distance, magnitude, and V S 30 . In each of the panels (a–f), average normalized amplitude spectra (upper pane) and average...
FIGURES | View All (11)
Journal Article
Journal: Geophysics
Published: 05 April 2024
Geophysics (2024) 89 (3): S235–S250.
... an opportunity to implement the wavefield decomposition using the statistical neural network method. Using extrapolated wavefields as the input and the decomposed up-, down-, left-, and rightgoing wavefields as the labeled data, we train a pair of generative adversarial networks to predict the directional...
FIGURES | View All (20)
Journal Article
Published: 21 October 2020
Seismological Research Letters (2021) 92 (1): 388–395.
... perturbations r adv at random, VAT generates perturbations in the virtual adversarial direction, which corresponds to the direction of greatest change in model output, enabling more effective regularization and which Miyato et al. (2018) demonstrated to be superior to random additive noise...
FIGURES | View All (5)
Journal Article
Published: 19 April 2024
Bulletin of the Seismological Society of America (2024)
... a conditional generative adversarial network (cGAN) to generate temporal characteristics and another model using the generalized inversion technique (GIT) to generate amplitude characteristics. The conditions are M w , R hyp , and SITE. (c) In the prediction step, the generator of cGAN...
FIGURES | View All (20)
Journal Article
Journal: Geophysics
Published: 05 September 2023
Geophysics (2023) 88 (6): D357–D369.
... the slowness models by using all the wellbore data. In addition, the Real-enhanced super-resolution generative adversarial networks (ESRGAN) method is applied to borehole imaging to further improve the preceding inversion. The inversion results regarding the slowness value, wellbore structure, and interface...
FIGURES | View All (20)
Journal Article
Published: 19 March 2024
Bulletin of the Seismological Society of America (2024)
... learning have been made in the last decade on the topic of deep generative models, in which the goal is to learn an unknown data distribution given a large dataset for training. Generative adversarial networks, or GANs ( Goodfellow et al. , 2014 ), are a class of generative models well suited for time...
FIGURES | View All (17)
Journal Article
Journal: Geophysics
Published: 27 September 2021
Geophysics (2021) 86 (6): V471–V488.
...Qing Wei; Xiangyang Li; Mingpeng Song ABSTRACT During acquisition, due to economic and natural reasons, irregular missing seismic data are always observed. To improve accuracy in subsequent processing, the missing data should be interpolated. A conditional generative adversarial network (cGAN...
FIGURES | View All (31)
Journal Article
Published: 26 February 2024
Petroleum Geoscience (2024) petgeo2022-032.
... that reproduce the sedimentary events and develop the geometry. However, the complex dynamic processes are extremely expensive to simulate, making process-based models difficult to be conditioned to field data. In this work, we propose a comprehensive generative adversarial network framework as a machine...
Journal Article
Journal: Geophysics
Published: 10 June 2020
Geophysics (2020) 85 (4): E121–E137.
... information into the inversion network is established based on analysis of the network and kernels of the convolutional layers. The performance of the proposed method is demonstrated through experiments on test data generated for resistivity models for complex salt structures. The trained cooperative...
FIGURES | View All (27)
Journal Article
Journal: Geophysics
Published: 15 June 2023
Geophysics (2023) 88 (4): IM87–IM99.
... developed a self-supervised TF representation based on a generative adversarial networks (STFR-GANs) model to map a 1D seismic signal into a 2D STF image. This model includes three components: a generator, a discriminator, and a reconstruction module. The generator is used to generate the STF spectrum...
FIGURES | View All (15)
Journal Article
Journal: The Leading Edge
Published: 01 August 2018
The Leading Edge (2018) 37 (8): 578–583.
.... To remediate this blurring problem and enhance confidence of inferences, we demonstrate a preprocessing technique in the image domain by using generative adversarial networks (GANs) that sharpen the seismic image prior to training and prediction. This sharpening solution consists of two neural networks...
FIGURES | View All (8)
Journal Article
Journal: The Leading Edge
Published: 01 September 2022
The Leading Edge (2022) 41 (9): 599–610.
... resolution and difficulty visualizing seismic signals as “band-limited rocks.” This study proposes a methodology using a combination of forward modeling and conditional generative adversarial network (cGAN) to translate seismic-derived acoustic impedance (AI) into a pseudo-high-resolution virtual outcrop. We...
FIGURES | View All (12)
Journal Article
Journal: Geophysics
Published: 10 June 2020
Geophysics (2020) 85 (4): O47–O58.
..., imbalanced facies class distribution, and lack of rigorous performance evaluation metrics. To overcome these challenges, we have developed a supervised convolutional neural network (CNN) and a semisupervised generative adversarial network (GAN) for 3D seismic facies classification in situations...
FIGURES | View All (19)
Journal Article
Published: 08 December 2022
Bulletin of the Seismological Society of America (2023) 113 (1): 453–467.
... histories for earthquake engineering (e.g., nonlinear dynamic analysis), simulations of time histories are therefore required. In this study, we present a model for simulating nonstationary ground‐motion recordings, which combines a conditional generative adversarial network to predict the amplitude part...
FIGURES | View All (13)
Journal Article
Journal: The Leading Edge
Published: 01 November 2019
The Leading Edge (2019) 38 (11): 872a1–872a9.
.... In this paper, we leverage generative adversarial networks (GANs) ( Goodfellow et al., 2014 ) to learn a geologic representation from a finite number of model examples. We then sample from the learned distribution to obtain a large number of unique, geologically feasible models. By doing so, we mimic...
FIGURES | View All (6)
Journal Article
Journal: Geophysics
Published: 05 June 2020
Geophysics (2020) 85 (4): WA173–WA183.
... and x B is the true reflectivity ( m ) ( Kaur et al., 2019 ). This makes it possible to engage the learned generative model in different “modes” by providing it with different contextual information ( Gauthier, 2014 ). Further, the network uses adversarial loss L GAN ( Goodfellow...
FIGURES | View All (12)