3D pre-trained transformers for seismic fault detection, image denoising and dense horizon interpretation

Enning Wang, Peter Lovely, Lachlan Wright, Sarah Vitel, Anusha Sekar, Maisha Amaru

International Meeting for Applied Geoscience and Energy (IMAGE)

... image databases such as ImageNet, there are few geologically diverse, public 3D field seismic databases of similar scale in post-stack domain for model...

Abstracts: Revisiting Homomorphic Wavelet Estimation and Phase Unwrapping; #90173 (2015)

Roberto H. Herrera and Mirko van der Baan

Search and Discovery.com

.... The convolutional operator is denoted by  and η (t ) is the additive noise. In the frequency domain equation (1) can be expressed as: = W ( f ) R( f ) + Ν...

Seismic inversion with implicit neural representations

Juan Romero, Wolfgang Heidrich, Nick Luiken, Matteo Ravasi

International Meeting for Applied Geoscience and Energy (IMAGE)

... be mathematically represented via the socalled convolutional model (Goupillaud, 1961). This entails the convolution of a source function or wavelet w...

Abstract: Variable-factor S-transform for Time-frequency Decomposition, Deconvolution, and Noise Attenuation; #90172 (2014)

Todor I. Todorov, Gary F. Margrave

Search and Discovery.com

... to the physical phenomena of the seismic wave propagation in the earth over the traditional stationary convolutional model. Margrave and Lamoureux...

NLP applications in the oil and natural gas industry

Prashanth Pillai, Srikanth Ryali, Hiren Maniar, Purnaprajna Mangsuli, Aria Abubakar

International Meeting for Applied Geoscience and Energy (IMAGE)

..., natural language query translation and technical document classification. Introduction Oil exploration and production companies invest considerable time...

Realistic synthetic data generation using neural style transfer: Application to automatic fault interpretation

Min Jun Park, Joseph Jennings, Bob Clapp, Biondo Biondi

International Meeting for Applied Geoscience and Energy (IMAGE)

... suitable to be used as training images than the original synthetic images. To verify the effectiveness of our workflow, we train a model on the synthetic...

An application of FWI with progressive transfer learning

Shirui Wang, Jinjun Liu, Yuchen Jin, Xuqing Wu, Jiefu Chen

International Meeting for Applied Geoscience and Energy (IMAGE)

... be obtained by picking stack velocity in the time domain or by ray-based tomographic approach (Thurber 2007, Woodward et al, 2008, Zhou et al. 2001...

Time-lapse full-waveform inversion by model order reduction using radial basis function

Haipeng Li, Robert G. Clapp

International Meeting for Applied Geoscience and Energy (IMAGE)

...Time-lapse full-waveform inversion by model order reduction using radial basis function Haipeng Li, Robert G. Clapp Time-lapse full-waveform...

Accurate seismic data interpolation based on multiband intelligent training

Xueyi Sun, Benfeng Wang, Tongtong Mo

International Meeting for Applied Geoscience and Energy (IMAGE)

... information about subsurface structures and geological features. During the optimization of convolutional neural network (CNN)-assisted seismic data...

Internal multiple elimination with an inverse-scattering theory guided deep neural network

Zhiwei Gu, Liurong Tao, Haoran Ren, Ru-Shan Wu, Jianhua Geng

International Meeting for Applied Geoscience and Energy (IMAGE)

... with the convolutional operation. Combining the CNN with the autoencoder can improve the feature extraction ability of the network model and have higher computational...

Seismic Forward Modeling of Semberah Fluvio-Deltaic Reservoir

Adi Widyantoro, Wahyu Dwijo Santoso

Indonesian Petroleum Association

... Convention Proceedings, 2021   Figure 6 - Stratigraphic model framework in time domain with structurally smoothed seismic in the background (top). Noise...

ABSTRACT: Maximum Likelihood Deconvolution: a New Perspective, by Jerry M. Mendel; #91035 (2010)

Search and Discovery.com

Unsupervised compensation of spiral-shaped drone magnetic survey using a recurrent convolutional autoencoder

Brett Bernstein, Yaoguo Li, Richard Hammack, Colton Kohnke

International Meeting for Applied Geoscience and Energy (IMAGE)

...Unsupervised compensation of spiral-shaped drone magnetic survey using a recurrent convolutional autoencoder Brett Bernstein, Yaoguo Li, Richard...

Automated Data and ML Pipelines to Accelerate Subsurface Digitalization

Raj Kannan, Vikas Jain

Unconventional Resources Technology Conference (URTEC)

... change over time rendering an ML model unable to perform as well as it did when it was first trained. Automated escalations to both domain experts...

Time-lapse matching of OBN seismic data using 2D convolutional neural networks

Ramon C. F. Araújo, Gilberto Corso, Samuel Xavier-de-Souza, João M. de Araújo, Tiago Barros

International Meeting for Applied Geoscience and Energy (IMAGE)

...Time-lapse matching of OBN seismic data using 2D convolutional neural networks Ramon C. F. Araújo, Gilberto Corso, Samuel Xavier-de-Souza, João M. de...

Predicting Facies, Rock, and Geomechanical Properties Using Convolutional Neural Networks: A Case Study From an Unconventional Shale Reservoir

Ted Holden, Ruth Kurian, Mohammed Ibrahim, Daniel Hampson, Jonathan Downton

Unconventional Resources Technology Conference (URTEC)

...) Synthetic angle gathers are then generated for each pseudo-well using a convolutional model in which the P-wave reflection coefficients calculated using...

An immersed absorbing boundary condition for scalar wavefield modeling under topography

KeJi Chen, Hanming Chen, Hui Zhou

International Meeting for Applied Geoscience and Energy (IMAGE)

... can be predicted by the wavefields at one-side (the side close to the interior domain) neighbouring fractional nodes at current and past time steps...

Demultiple of High Resolution P-Cable Data in the Norwegian Barents Sea „ An Iterative Approach

A.J. Hardwick, S. Jansen, B. Kjolhamar

Petroleum Exploration Society of Australia (PESA)

... from the latest The final adapted model is then subtracted in the curvelet n. A data driven, iterative approach is domain. For the first time, through...

Physics-Constrained Deep Learning for Production Forecast in Tight Reservoirs

Nguyen T. Le, Roman J. Shor, Zhuoheng Chen

Unconventional Resources Technology Conference (URTEC)

... patterns emerges in different time frames. In this paper, the ability of a purely data driven deep learning model to handle non-stationary production...

S/N RATIO AND BANDWIDTH CONSIDERATIONS WHEN UTILIZING SEISMIC DATA IN EXPLORING FOR SUBTLE TRAPS - EXAMPLES FROM THE KNOX PLAY

Edward R. Tegland, Exploration Development, Inc., S. Pikes Peak Dr., Parker, CO Patrick H. Bygott, Exploration Development, Inc., S. Pikes Peak Dr., Parker, CO

Ohio Geological Society

..., this is defined as the ratio of peak signal amplitude to RMS noise level in the general time window of interest. In areas...

Deep carbonate reservoir characterization with unsupervised machine-learning approaches

Xuanying Zhu, Luanxiao Zhao, Xiangyuan Zhao, Yuchun You, Minghui Xu, Tengfei Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

.... Cheng, J., T. Wang, C. Wang, and J. Geng, 2012, Azimuth-preserved local angle-domain prestack time migration in isotropic, vertical transversely...

Source location using physics-informed neural networks with hard constraints

Xinquan Huang, Tariq Alkhalifah

International Meeting for Applied Geoscience and Energy (IMAGE)

... imaging of subsurface microseismic events, in which the image is a slice of the wavefield in the time domain. Specifically, we use three inputs to the NN...

Do We Really Need Deep Learning? A Study on Play Identification using SEM Images

Hanyan Zhang, Max T. Kasumov, Deepak Devegowda, Mark E. Curtis

Unconventional Resources Technology Conference (URTEC)

... classification. For all image resolutions considered, surprisingly, the simplest and shallowest one-convolutional layer model performs remarkably well...

Semisupervised learning with knowledge embedding for horizon volumes calculation

Rui Guo, He Lin, Maoshan Chen, Chunfeng Tao, Yingnan Gao, Ruochong Wen

International Meeting for Applied Geoscience and Energy (IMAGE)

... horizon volumes by calculating relative geologic time (RGT). To enhance model’s generalization capability, we integrate two unsupervised losses...

Demultiple for Wide-Tow Broadband Acquisition in a Shallow Water Environment: A Case Study from the NW Shelf, Australia

Mike Hartley, Shuo Ji, Alex Browne

Petroleum Exploration Society of Australia (PESA)

... in shallow water, especially for outer cables. Rcvr depth(m) Shot: channel Frequency(Hz) Time (sec) Model base water-layer demultiple predicts...