Applying deep learning for identifying bioturbation from core photographs

Eric Timmer, Calla Knudson, and Murray Gingras

AAPG Bulletin

... to the convolutional layers to reduce model overfitting (Srivastava et al., 2014). Overfitting occurs when the neural network memorizes the data set...

A deep learning workflow for petro-mechanical facies predictions in unconventionals

Noah R. Vento, Enru Liu, Mary Johns

International Meeting for Applied Geoscience and Energy (IMAGE)

... extracted from 23 well locations across the survey and used as inputs to the proposed DL model. Due to poor S/N ratio and the presence of residual...

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)

... Water Environment … Hartley & Ji et al. with the data to create a model of the multiples. This process is generally very effective at removing short...

Multiscale fault and fracture characterization methods

QiQi Ma, Taizhong Duan

International Meeting for Applied Geoscience and Energy (IMAGE)

...-layer weighted U-net(a) and branching model U-net(b) Figure 7: Comparison of seismic(a) and faults predication methods based on deep learning before (b...

Stability criteria for seismic data interpolation artificial neural networks

Yiying Xing, Wenlong Wang, Florian Bossmann, Xuexin An

International Meeting for Applied Geoscience and Energy (IMAGE)

... select three artificial neural networks that have been successfully applied in seismic data interpolation Deep Convolutional Neural Network (DnCNN...

Joint inversion of magnetotelluric and seismic travel time data with intelligent interpretation of geophysical models

Hongyu Zhou, Rui Guo, Maokun Li, Fan Yang, Shengheng Xu, Zuzhi Hu, Deqiang Tao

International Meeting for Applied Geoscience and Energy (IMAGE)

... models and seismic post-stack data. In the joint inversion, the output of the IntNet is used as the reference model to constrain the searching space...

3D ultra high resolution seismic processing „ A case study from offshore USA

Bertrand Caselitz, Luca Limonta, Julien Oukili, Jonas Tegnander, Vicky Catterall

International Meeting for Applied Geoscience and Energy (IMAGE)

... reflections. The demultiple step, utilizing methods like convolutional 3D Surface Related Multiple Elimination (SRME) and 3D wave-equation multiple...

A prior regularized 3D full-waveform inversion using 2D generative diffusion models

Fu Wang, Tariq Alkhalifah, Xinquan Huang

International Meeting for Applied Geoscience and Energy (IMAGE)

... in observation, this inverse problem is highly ill-posed, especially for recovering a 3D velocity model. To solve this problem, regularization is often...

This thin section doesnt exist: On the generation of synthetic petrographic datasets

Ivan Ferreira, Luis Ochoa, Ardiansyah Koeshidayatullah

International Meeting for Applied Geoscience and Energy (IMAGE)

... model, Generative Adversarial Networks (GANs), in the context of a petrographic dataset are presented. The StyleGAN2 architecture was selected to train...

Solving seismic inverse problems by an unsupervised hybrid machine-learning approach

Mrinal K. Sen, Arnab Dhara

International Meeting for Applied Geoscience and Energy (IMAGE)

... carried out by iterative data fitting in which the model updates are evaluated by solving the corresponding physics-based forward modeling. Local...

Automated Data and ML Pipelines to Accelerate Subsurface Digitalization

Raj Kannan, Vikas Jain

Unconventional Resources Technology Conference (URTEC)

... the ML craft and providing first principal guard-rails. An MLOps pipeline can manage model versions and continuously deliver qualified ML models...

Automated velocity modeling with domain transformations

Kevin Gullikson, Arnab Dhara, Ram Tuvi, Mrinal K. Sen

International Meeting for Applied Geoscience and Energy (IMAGE)

... a machine learning model that effectively learns to predict a velocity model of the subsurface directly from trace data. We do this by first transforming...

Application of Both Physics-Based and Data-Driven Techniques for Real-Time Screen-Out Prediction with High Frequency Data

Jianlei John Sun, Arvind Battula, Brandon Hruby, Paymon Hossaini

Unconventional Resources Technology Conference (URTEC)

..., we will introduce convolutional layers (i.e. CNN layers) to resolve this issue. Advanced CNN-LSTM Model Compared with the baseline model, CNN-LSTM...

Rock-physics based time-lapse inversion in Delivery4D: synthetic feasibility study for CO2CRC Otway Project

Stanislav Glubokokvskikh, James Gunning, Tess Dance, Roman Pevzner, Dmitry Popik, Christian Proud

Petroleum Exploration Society of Australia (PESA)

... seismic AVO-inversion based on convolutional model of seismic trace. A subsurface model consists of 1D ‘layered cakes’, inverted independently...

Drilling and Completion Anomaly Detection in Daily Reports by Deep Learning and Natural Language Processing Techniques

Hongbao Zhang, Yijin Zeng, Hongzhi Bao, Lulu Liao, Jian Song, Zaifu Huang, Xinjin Chen, Zhifa Wang, Yang Xu, Xin Jin

Unconventional Resources Technology Conference (URTEC)

...”, “grapple” and “bumper”, which are all fishing related tools, that means the model has learned the semantics of words. Convolutional neural network (CNN...

Seismic Data Compression by Variational Autoencoder With Hyperprior

Shirui Wang, Wenyi Hu, Aria Abubakar, Xuqing Wu, Jiefu Chen

International Meeting for Applied Geoscience and Energy (IMAGE)

..., end-to-end approach. Our experimental analyses demonstrate the efficacy of the introduced compression model on both pre-migration and post-migration...

Tops fingerprinting: Revolutionizing well log analysis with music recognition technology

Alan Lindsey, Morgan Cox, Aaron Hugen

International Meeting for Applied Geoscience and Energy (IMAGE)

..., false positives are a problem. Convolutional Neural Networks are quite powerful, but require substantial training, and they tend to be a black-box...

Multiple, Diffractions and Diffracted Multiples in the South China Sea: How Dense Does Our Acquisition Geometry Need to be? (Geophysics Paper 16)

Rosemary K Quinn, Lynn B Comeaux

Geological Society of Malaysia (GSM)

... be horizontal over the scale of the SRME aperture in order for the model to be predicted accurately. Clearly, this is rarely the case, but as long...

Improved Resolution of Thin Turbiditic Sands in Offshore Sabah with Bandwidth Extension … A Pilot Study (Paper C11)

G. Yu, N. Shah, M. Robinson, N. H. Nghi, A. A. Nurhono, G. S. Thu

Geological Society of Malaysia (GSM)

.... Methodology Bandwidth Extension algorithm utilizes the Continuous Wavelet Transform (CWT) to model harmonics and subharmonics to recover both high and low...

Abstract: Can Q Explain Observations Made from a VSP?, by Hamish Wilson, Scott W. Peters, and Robert W. Wiley; #90105 (2010)

Search and Discovery.com

2D isotropic and vertical transversely isotropic RTM using SEG Hess VTI Model

Richa Rastogi, Abhishek Srivastava, Monika Gawade, Nithu Mangalath, Laxmaiah Bathula, Bhushan Mahajan, Suhas Phadke

International Meeting for Applied Geoscience and Energy (IMAGE)

...2D isotropic and vertical transversely isotropic RTM using SEG Hess VTI Model Richa Rastogi, Abhishek Srivastava, Monika Gawade, Nithu Mangalath...

OpenFWI 2.0: Benchmark Datasets for Elastic Full-waveform Inversion

Shihang Feng, Hanchen Wang, Chengyuan Deng, Yinan Feng, Min Zhu, Peng Jin, Yinpeng Chen, Youzuo Lin

International Meeting for Applied Geoscience and Energy (IMAGE)

... into the inversion significantly expands the model space and introduces increased degrees of freedom, resulting in even more pronounced nonlinearity (Operto et...

Seismic facies segmentation via mask-assisted transformer

Jinlong Huo, Naihao Liu, Zhiguo Wang, Yang Yang, Yijie Zhang, Jinghuai Gao

International Meeting for Applied Geoscience and Energy (IMAGE)

... on the characteristics of seismic reflectors. The application of using convolutional neural networks (CNNs) in seismic facies segmentation is growing rapidly. However, CNN...

Optimized transparent boundary conditions for wave propagation

G. Roncoroni, B. Arntsen, E. Forte, M. Pipan

International Meeting for Applied Geoscience and Energy (IMAGE)

... topographies have been derived to accurately model wave propagation (Ruud & Hestholm, 2001). These formulations are crucial for representing...

Modeling Distributed Fiber Optic Sensor Signals Using Computational Rock Mechanics

Christopher S. Sherman, Robert J. Mellors, Joseph P. Morris, Frederick J. Ryerson

Unconventional Resources Technology Conference (URTEC)

... with the 3D thermo-hydro-mechanical (THM) code GEOS. GEOS is a flexible and well-validated code designed to model subsurface fractures. It has been used...