... characterization neural network machine learning inversion geophysics autoencoder exploration geophysicist applied geoscience american association full-waveform inversion regularization upstream oil & gas artificial intelligence elastic-adjointnet international fwi energy 10 mrinal sen...

... expanded abstract exploration geophysicist autoencoder applied geoscience verschuur society zhang u-net convergence energy 10 geophysics rectangle american association media international conference Internal multiple elimination with an inverse-scattering theory guided deep neural network...

... but was not presented at IMAGE 2022 in Houston, Texas. artificial intelligence autoencoder deep learning machine learning upstream oil & gas reservoir characterization reservoir prediction american association geophysics international information seismic inversion applied geoscience formula...

... augmentation, the process of creating new samples from Autoencoder the original data, addresses the data shortage problem (Shorten and Khoshgoftaar, 2019). But popular data augmentation meth- Our rst model is to build a regression model which can ods are not helpful for seismic imaging because of their lack...

... We have developed spatio-temporal neural-network-based models that can produce high-fidelity interpolated or extrapolated seismic images effectively and efficiently. Specifically, our models are built on an autoencoder, and incorporate the long short-term memory (LSTM) structure with a new loss...

.... The dimensionality reduction is in fact the key point to avoid the “curse of dimensionality”. Recently, it has been proposed to combine deep autoencoders with clustering algorithms to extract seismic facies from pre-stack seismic data. In this paper, we extend this strategy, using as input, not only a single channel...

... resolution requires a full description of the source signal to properly separate the reflectivity information from the recorded seismograms. We introduce a physics-guided convolutional autoencoder concept as a novel alternative to perform automatic deconvolution. This unsupervised deep learning structure...

...Surface-related multiple elimination through orthogonal encoding in the latent space of convolutional autoencoder Oleg Ovcharenko*, Anatoly Baumstein, and Erik Neumann, ExxonMobil Upstream Research Company Summary The abstract is organized as follows. First, we explain the We explore feasibility...

...: 351F Presentation Type: Oral log analysis upstream oil & gas climate change well logging dimension experiment information machine learning artificial intelligence autoencoder exploration geophysicist 10 denote path effect seg international exposition dataset symae reservoir...

... Newtonian machine learning (NML) inversion has been shown to accurately recover the low-to-intermediate wavenumber information of subsurface velocity models. This method uses the wave-equation inversion kernel to invert the skeletonized data that is automatically learned by an autoencoder...

... Neural Networks (CNNs). Specifically, a convolutional autoencoder is trained to compress wavefield snapshots and a specifically designed U-net is trained to reconstruct (i.e. interpolate) the wavefield in the temporal dimension. Results show that these promising techniques could help decreasing storage...

... learning with deep autoencoders, and supervised learning with cascaded autoencoders and convolutional neural networks for classification. Compared with familiar applications of computer vision such as common object recognition, classifying images of geological elements poses several challenges associated...

... ABSTRACT Deep learning leverages multi-layer neural networks architecture and demonstrates superb power in many machine learning applications. The deep denoising autoencoder technique extracts better coherent features from the seismic data. The technique allows us to automatically extract low...

... propose a completely novel approach for reconstructing missing traces of pre-stack seismic data, taking inspiration from computer vision and image processing latest developments. More specifically, we exploit a specific kind of convolutional neural networks known as convolutional autoencoder. We...

.... Specifically, we propose a novel approach based on a data-driven sparse autoencoder architecture that can automatically recognize and extract salient geologic features from unlabeled 3D seismic volumes. It is superior in learning sparse features from natural images, which is not limited by the lack of labeled...

... with a desirable accuracy. Presentation Date: Thursday, September 28, 2017 Start Time: 10:10 AM Location: 330A Presentation Type: ORAL autoencoder neural network upstream oil & gas gaussian distribution seg seg international exposition formation mineral composition machine learning mineral...