A rock physics inversion method based on physics-guided autoencoder network

Zhuofan Liu, Umair bin Waheed, Ammar El-Husseini, Jiajia Zhang

International Meeting for Applied Geoscience and Energy (IMAGE)

...- guided convolutional neural network: Interpretation, 7, no. 3, SE161–SE174, doi: https://doi.org/10.1190/INT-2018-0236.1. Bosch, M., T. Mukerji, and E. F...

Abstract: Interactive Deep Learning Assisted Seismic Interpretation Technology Applied to Reservoir Characterization: A Case Study From Offshore Santos Basin in Brazil;

Ana Krueger, Bode Omoboya, Paul Endresen, Benjamin Lartigue

Search and Discovery.com

... Convolutional Neural Networks (CNN), the deep neural network acts as an extension of the interpreter to assist in mapping sub-surface geological...

Abstract: Neural Networks Facilitate Precise at - Bit Formation Detection Suitable for Deployment in Automated Drilling Systems; #91204 (2023)

Lucas Katzmann, Stefan Wessling, Matthew Forshaw, Joern Koeneke

Search and Discovery.com

... an alternative, data-driven solution using a multi-layer supervised machine learning model to identify such formation changes. Methods Analysis...

Chapter 2: Basics of Reflection Seismology that Relate to Seismic Stratigraphy

Tom Wittick

North Texas Geological Society

... for those prospective signatures. The Convolutional Model Figure 2-4 is a cartoon showing the relationship between a lithologic column...

Basics of Reflection Seismic Technology

Abilene Geological Society

... for those prospective signatures. The Convolutional Model Figure 2-4 is a cartoon showing the relationship between a lithologic column...

Rock Thin-section Analysis and Mineral Detection Utilizing Deep Learning Approach

Fatick Nath, Sarker Asish, Shaon Sutradhar, Zhiyang Li, Nazmul Shahadat, Happy R. Debi, S M Shamsul Hoque

Unconventional Resources Technology Conference (URTEC)

... of rock thin sections. In a similar objective, Nanjo et al. (2019) implemented convolutional neural network-based model to classify four types of rock...

Vision-based Sedimentary Structure Identification of Core Images using Transfer Learning and Convolutional Neural Network Approach

Baosen Zhang, Shiwang Chen, Yitian Xiao, Laiming Zhang, Chengshan Wang

Unconventional Resources Technology Conference (URTEC)

...Vision-based Sedimentary Structure Identification of Core Images using Transfer Learning and Convolutional Neural Network Approach Baosen Zhang...

Deep Dix: Enhancing interval velocity model estimation through adversarial regularization

Joseph Stitt, Robert Clapp, Biondo Biondi

International Meeting for Applied Geoscience and Energy (IMAGE)

... that Convolutional Neural Networks (CNNs) have successfully generated mappings from low-frequency shot gathers to low-wavenumber Earth model...

Embedding Physical Flow Functions into Deep Learning Predictive Models for Improved Production Forecasting

Syamil Mohd Razak, Jodel Cornelio, Young Cho, Hui-Hai Liu, Ravimadhav Vaidya, Behnam Jafarpour

Unconventional Resources Technology Conference (URTEC)

...trained model is composed of several fully-connected regression layers and one- URTeC 3702606 6 dimensional (1D) convolutional layers. A fully-co...

Seismic absolute acoustic impedance inversion using domain adversarial based transfer learning

Anjali Dixit, Animesh Mandal

International Meeting for Applied Geoscience and Energy (IMAGE)

..., saturation, to name a few. However, to obtain absolute AI, incorporation of low-frequency impedance model is essential. This work presents a unified...

Massive focal mechanism solutions from deep learning in west Texas

Yangkang Chen, Omar M. Saad, Alexandros Savvaidis, Fangxue Zhang, Yunfeng Chen, Dino Huang, Huijian Li, Farzaneh Aziz Zanjani

International Meeting for Applied Geoscience and Energy (IMAGE)

... to quantitatively pick the first-motion polarity using a pre-trained model from a rela- tively high-quality dataset. The fundamental principle of deep...

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...

Deep learning software accelerators for full-waveform inversion

Sergio Botelho, Souvik Mukherjee, Vinay Rao, Santi Adavani

International Meeting for Applied Geoscience and Energy (IMAGE)

... is the use of (deep) neural networks, which have proven to be capable of learning complex non-linear relationships between the velocity model...

Joint data and physics model driven full-waveform inversion using CMP gathers and well-logging data

Shuliang Wu, Jianhua Geng

International Meeting for Applied Geoscience and Energy (IMAGE)

..., and J. Ma, 2018, Velociy model building with a modified fully convolutional network: 88th Annual International Meeting, SEG, Expanded Abstracts, 2086...

Development and Application of a Real-Time Drilling State Classification Algorithm with Machine Learning

Yuxing Ben, Chris James, Dingzhou Cao

Unconventional Resources Technology Conference (URTEC)

... data. A rules-based model was then applied to classify the data into seventeen rig states. For the state “drilling”, a sub-classification was made...

Training data versus deep learning architectures in the seismic fault attribute computation

Bo Zhang, Yitao Pu, Zhaohui Xu, Naihao Liu, Shizhen Li, Fangyu Li

International Meeting for Applied Geoscience and Energy (IMAGE)

...” and predicted result of side outputs (o1-o4). The model generates a “fuse” set to combine the side outputs at different scales. It is common that one...

Automated machine learning first-break picking in the Sichuan Basin „ A case study

Jianfa Wu, Xuewen Shi, Qiyong Gou, Ersi Xu, Dongjun Zhang, Dingxue Wang, Phil Bilsby, Qing Zhou, Rong Li

International Meeting for Applied Geoscience and Energy (IMAGE)

... to the various machine learning model architectures employed and demonstrate the uplift in both the resulting reservoir imaging and the reduction...

Aiding self-supervised coherent noise suppression by the introduction of signal segmentation using blind-spot networks

Sixiu Liu, Claire Birnie, Tariq Alkhalifah, Andrey Bakulin

International Meeting for Applied Geoscience and Energy (IMAGE)

... al., 2019; Wang and Chen, 2019; Birnie et al., 2021a). A number of NN-based denoising procedures utilise Convolutional Neural Networks (CNNs) to learn...

Joint 3D inversion of gravity and magnetic data using deep learning neural networks

Nanyu Wei, Dikun Yang, Zhigang Wang, Yao Lu

International Meeting for Applied Geoscience and Energy (IMAGE)

... uses a supervised deep neural network, developed based on fully convolutional networks and further combined with a U-Net architecture. Two multi-model...

3D velocity model building based upon hybrid neural network

Herurisa Rusmanugroho, Junxiao Li, M. Daniel Davis Muhammed, Jian Sun

International Meeting for Applied Geoscience and Energy (IMAGE)

... as an image are passed through some convolutional layers to estimate P-velocity model. This network is expected to learn from the features obtained from...

Lithofacies identification in cores using deep learning segmentation and the role of geoscientists: Turbidite deposits (Gulf of Mexico and North Sea)

Oriol Falivene, Neal C. Auchter, Rafael Pires de Lima, Luuk Kleipool, John G. Solum, Pedram Zarian, Rachel W. Clark, and Irene Espejo

AAPG Bulletin

... of convolutional neural networks (CNNs) using semantic segmentation architectures to automate the identification of common lithofacies from core images. Images...

Deep learning-based Vz-noise attenuation for OBS data

Jing Sun, Arash Jafargandomi, Julian Holden

International Meeting for Applied Geoscience and Energy (IMAGE)

... for the shear-noise model. We show that the proposed approach can effectively capture the substantial variability of shear noise and remove it from...

Deep learning velocity model building using an ensemble regression approach

Stuart Farris, Guillaume Barnier, Robert Clapp

International Meeting for Applied Geoscience and Energy (IMAGE)

... framework that uses a convolutional neural network (CNN) to form an ensemble of low wavenumber model predictions which can be integrated to form...

Correlating Versus Inverting Vibroseis Records: Recovering What You Put into the Ground; #41577 (2015)

Glen Larsen, Paul Hewitt, Art Siewert

Search and Discovery.com

...) based on work of Allen et al. (1998). In effect, spiking the trace reduces it to a phase only operator. The usual vibroseis convolutional model is: x...

Machine learning and seismic attributes for prospect identification and risking: An example from offshore Australia

Mohammed Farfour, Douglas Foster

International Meeting for Applied Geoscience and Energy (IMAGE)

... and convert them to Gas chimney probability cube, and to Gamma Ray cube. Next, pre-trained Convolutional Neural Network (CNN) is trained using...