... discriminator applied geoscience exploration geophysicist architecture gan generator seismogram international ricker wavelet Broadband reconstruction of seismic signal with generative recurrent adversarial network Zhijun Zhang* , TianJin Branch of CNOOC Ltd ;Wei Song, Institute of Geophysics,China...

...), the generative adversarial network (GAN), through which we separate up-going and down-going wave field form VSP wave field. Asymmetric convolution blocks are used to improve the network feature recognition ability and further reduce the loss of network prediction results. Training sample database is generated...

... the isotropic property of such 3D rocks by considering 2D μ CT from a different perspective from the given 2D scans. We then employ state of the art invert GAN and AE techniques to produce good inpainting results to reconstruct the 3D sample from the concatenation of inpainted 2D samples. Empirical evidence...

... resolution of the model solutions may be decreased due to the smooth effect of the regularization. In this study, we develop a constrained first-arrival traveltime tomography based on the Generative Adversarial Network (GAN), a machine learning approach. The GAN is applied to generate a prior model in each...

... ABSTRACT As one of machine learning techniques, deep learning has recently achieved the state-of-the-art performances in many areas, such as computer vision, natural language processing, to name a few. A generative model called Generative Adversarial Network (GAN) was invented in 2014...

... classification upstream oil & gas separation vsp data divergence reconstruction method gan neural network operator machine learning artificial intelligence adversarial network conditional generative adversarial network shot gather reservoir characterization geophysics waveform synthetic data...

... mechanism in realistic settings. In this study, we investigate the feasibility of using a supervised CNN and a semi-supervised generative adversarial network (GAN) for 3D facies classification from seismic data and well logs, to overcome these challenges. We assess the performance with varying data...

... a generative adversarial network (GAN) to process seismic migrated images in order to potentially obtain different kinds of outputs depending on the application target at training stage. We demonstrate the promising features of this tool through a couple of synthetic examples. In the first example, the GAN...

... of "deep" learning algorithms, offer opportunities to address both limitations by establishing relationships between low- and high-resolution versions of seismic images. Here, a generative adversarial network (GAN) is trained to produce higher-resolution realizations of previously-unseen low-resolution...

... ABSTRACT Generative adversarial networks (GANs) are a class of machine learning techniques that involve two networks trained simultaneously to generate a desired outcome. These schemes have had success in many traditional image processing tasks, such as style transfer and super-resolution...