Application of Bayesian Optimized Deep Bi-LSTM Neural Networks for Production Forecasting of Gas Wells in Unconventional Shale Gas Reservoirs

Y. Kocoglu, S. Gorell, P. McElroy

Unconventional Resources Technology Conference (URTEC)

... in the future. Another well-known method for production forecasting is history matching a reservoir simulation model created for a real field...

Applying Conditional Generative Adversarial Networks for Seismic Data Reconstruction

Search and Discovery.com

Geological Facies Prediction Using Computed Tomography in a Machine Learning and Deep Learning Environment

Uchenna Odi, Thomas Nguyen

Unconventional Resources Technology Conference (URTEC)

...-defined geological facie classifications. Once the machine understands the relationship between geological facies and CT scan physics, the resulting model...

Neural network-based seismic data conditioning: Case study of engineering seismic survey data

Juan Lee, Yongchae Cho

International Meeting for Applied Geoscience and Energy (IMAGE)

... to generate training data of varying sizes. These data are then employed to construct an artificial neural network model. To address limitations...

Complex structure pattern and its control on reservoir distribution in the Apsheron ridge of South Caspian Basin, insights from integrated study of OBN seismic

Xiao Dengyi, Li Jianlin, Song Jiawen, Zhao Min, Li Xiaoliang, Chen Xin, Qi Qunli, Chen Shuangting, Li Qiang, Wang Bo, An Fuli, Wang Li, Liu Qiang, Cui Jinglin

International Meeting for Applied Geoscience and Energy (IMAGE)

.... Kabazi, 2021, An enhanced fault detection workflow combining machine learning and seismic attributes yields an improved fault model for Caspian Sea asset...

AAPG Rocky Mountain Section Annual Meeting; - Abstracts, #90301 (2017).

Search and Discovery.com

Leveraging source-over-cable marine seismic field data for near offset reconstruction with deep learning

Owen Rohwer Huff, Jan Erik Lie, Andreas Kjelsrud Evensen, Aina Juell Bugge

International Meeting for Applied Geoscience and Energy (IMAGE)

... data collected with source-over-cable acquisition geometry as training data. First, a convolutional neural network (CNN) is trained to reconstruct...

Active gamma-ray well logging pattern localization with reinforcement learning

Yuan Zi, Lei Fan, Xuqing Wu, Jiefu Chen, Shirui Wang, Zhu Han

International Meeting for Applied Geoscience and Energy (IMAGE)

... series target as a reference. The proposed model follows a top-down search procedure, which starts by investigating the whole welllog record...

A step towards the automatization of predictive geological mapping

Rafael Pires de Lima, Marcos Ferreira, Iago Costa

International Meeting for Applied Geoscience and Energy (IMAGE)

... Process Data Clip to extent Feature files  Remote sensing Raster Clipped Clipped Preprocess Data selection Fit model Comparison Predict...

Sedimentary History of Upper Ordovician Geosynclinal Rocks, Girvan, Scotland

John f. Hubert

Journal of Sedimentary Research (SEPM)

... "convolutional balls"--(D) upper zone of horizontal lamination--(E) pelite (figs. 9, 10, 11). In order to avoid the genetic assumption of gravity-controlled...

Generating Missing Unconventional Oilfield Data using a Generative Adversarial Imputation Network (GAIN)

Justin Andrews, Sheldon Gorell

Unconventional Resources Technology Conference (URTEC)

... convolutional or RELU networks, in this effort it was necessary to train the GAIN model using a hyperbolic tangent. When initially trained with RELU, the test...

Fault surface extraction based on computational topology

Cheng Zhou, Cun Yang, Ruoshui Zhou, Xingmiao Yao, Guangmin Hu

International Meeting for Applied Geoscience and Energy (IMAGE)

..., time range: 1.536s to 1.844s) to demonstrate the effectiveness of our method. We adopt a convolutional neural network method described in Zhou et al...

Improved Nanoscale Image-based Reservoir Characterization using Supervised Machine Learning

Shannon L. Eichmann, Poorna Srinivasan, Kevin Kenga, Mohammed Khan, Fabian Duque, Felix Oyarzabal, James Howard, Shawn Zhang

Unconventional Resources Technology Conference (URTEC)

..., the model is applied to all of the tiled images in the LgFOV image. In the IB method (Fig.1B), gray-scale values from all pixels in the image are used...

Innovative disorder seismic attribute for reservoir characterization

Qiang Fu, Saleh Al-Dossary

International Meeting for Applied Geoscience and Energy (IMAGE)

... seismic attribute is a convolutional filtering based algorithm designed using an optimization approach. By design, the attribute is insensitive to faults...

Sedimentology and Dispersal pattern of a Cretaceous Flysch Sequence, Patagonian Andes, Southern Chile

Kevin M. Scott

AAPG Bulletin

... unit. Frequency of occurrence of each type in three detailed sections is shown in Table I. The sections represent positions on a west-to-east...

Optimization of Relative Geological Time Derived From Flow Field A Label Free Approach

Zhun Li

International Meeting for Applied Geoscience and Energy (IMAGE)

..., Using relative geologic time to constrain convolutional neural network-based seismic interpretation and property estimation: Geophysics, 87, IM25–IM35...

Remote Well Site Biostratigraphy and Advances in Automated Fossil Analysis; #41930 (2016)

Gunilla Gard, Iain Prince, Jason A. Crux, J. M. Shin, Bernard Lee

Search and Discovery.com

... Convolutional Neural Network (CNN) is applied to training fossil recognition. Accuracy 4. In each iteration, the training software checks the training quality...

Oriented ellipsoidal DBSCAN for clustering faults from deep learning attributes

Samuel Chambers, Jesse Lomask

International Meeting for Applied Geoscience and Energy (IMAGE)

..., and A. Z. Yusifov, 2019, FaultNet3D: Predicting fault probabilities, strikes, and dips with a single convolutional neural network: IEEE Transactions...

AAPG International Conference and Exhibition; - Abstracts, #91209 (2025).

Search and Discovery.com

Horizon detection with CNN-based multiscale volumetric flattening

Jesse Lomask

International Meeting for Applied Geoscience and Energy (IMAGE)

... combines the power of Convolutional Neural Network (CNNs) and traditional geophysical inversion methods, flattening a seismic volume into a pseudo...

Large Mudstone-Nucleus Sandstone Spheroids in Submarine Channel Deposits: NOTES

Daniel J. Stanley

Journal of Sedimentary Research (SEPM)

...-balls (Dzulynski, et al., 1957) and convolutional balls (Dott and Howard, 1962) may be cited as examples. The above-mentioned ball structures, however...

Deep adversarial multiview clustering network for unsupervised seismic facies analysis

Hanpeng Cai, Xiuyi Zou, Yuting Zhao, Sheng Zhang, Tengyu Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

.... Huang, and Y. Wang, 2021, The use of 3D convolutional autoencoder in fault and fracture network characterization: Geofluids, 2021, doi: https://doi.org...

Convolute Lamination, its Origin, Preservation, and Directional Significance

Stanislaw Dzulynski, Alec J. Smith

Journal of Sedimentary Research (SEPM)

... asymmetry can give rise to "convolutional balls" in sections at right angles to the direction of current flow (ten Haaf, 1956). End_Page 616...

Dynamics of Subaqueous Gravity Depositional Processes

R. H. Dott, Jr.

AAPG Bulletin

.... Cline (1960, p. 76) records even larger, remarkable examples. Roll-up structures (including convolutional balls, slump balls, etc.) undoubtedly result...