Machine-learning based arrival-picking in continuous DAS recordings „ Application to the Utah FORGE EGS project

Nepomuk Boitz, William Tegtow, Serge Shapiro

International Meeting for Applied Geoscience and Energy (IMAGE)

... a Convolutional Neural Network (CNN). In contrast to geophone-based picking methods, we suggest to train CNNs only on data from a specific dataset to best...

Seismic imaging uncertainty using deep learning predicted Greens functions

Han Liu, Anar Yusifov, Muhong Zhou, Linda Hodgson

International Meeting for Applied Geoscience and Energy (IMAGE)

... velocity model. We used U-net architecture (Ronneberger et al., 2015) with 5 layers, and each layer has 2 convolutional layers. Ensemble models were...

Prediction of porosity in CO2 sequestration tight reservoirs based on multi-source and multi-scale data fusion

Ping Lu, Peixue Jiang, Ruina Xu, Huaqing Xue, Haojie Li, Lei Yu, Jiashu Han

International Meeting for Applied Geoscience and Energy (IMAGE)

... it difficult for the reservoir porosity model to simultaneously consider prediction accuracy and generalization performance. Therefore, this study focuses...

A two-stage deep learning workflow for automated seismic inversion

Haibin Di, Wenyi Hu, Aria Abubakar

International Meeting for Applied Geoscience and Energy (IMAGE)

... of four major steps, (i) large-scale structural model construction, (ii) initial property model estimation via a multi-task convolutional neural...

Deep Convolutional Neural Networks for Seismic Salt-Body Delineation

Search and Discovery.com

Adapting Music Recognition Technology for Tops Picking and Quality Control

Alan Lindsey, Morgan Cox, Aaron Hugen

Unconventional Resources Technology Conference (URTEC)

... stratigraphy due to either faulting or unconformities. This can lead to false positive marker identifications. Convolutional Neural Networks (CNNs) CNNs...

Unlocking the Potential of Unlabeled Data in Building Deep Learning Model for Dynamometer Cards Classification

Ramdhan Wibawa, Rosyadi Rosyadi, Maulirany Nancy, Muhammad Awqi Gibran, Supriono Hariyadi

Indonesian Petroleum Association

... for building a Convolutional Neural Network (CNN) model using state of the art Self-Supervised Learning (SSL). The need to identify moretypes of failure has been...

Seismic super resolution method for enhancing stratigraphic interpretation

Chengbo Li, Qingrong Zhu, Baishali Roy

International Meeting for Applied Geoscience and Energy (IMAGE)

... 𝒎 and employ the convolutional model to illustrate the method. Assuming the wavelet is stationary within a given interval, the seismic can...

Reservoir prediction using graph-regularized deep learning

Kaiheng Sang, Nanying Lan, Fanchang Zhang

International Meeting for Applied Geoscience and Energy (IMAGE)

... of these explicit formulas are based on strong approximation to the underground media properties, such as convolution model, Aki-Richard approximate...

Abstract: A Convolutional Neural Network for Vuggy Facies Classification from Borehole Images;

Jiajun Jiang, Dawn McAlpin, Chicheng Xu, Rui Xu, Scott James, Weichang Li

Search and Discovery.com

...Abstract: A Convolutional Neural Network for Vuggy Facies Classification from Borehole Images; Jiajun Jiang, Dawn McAlpin, Chicheng Xu, Rui Xu, Scott...

Abstract: Horizontal Stress Prediction Using Seismic Velocities Based on Convolutional Neural Network; #91206 (2023)

Fatemeh Saberi, Esmael Makarian, Ayub Elyasi, Tomomewo Stanley Olusegun

Search and Discovery.com

...Abstract: Horizontal Stress Prediction Using Seismic Velocities Based on Convolutional Neural Network; #91206 (2023) Fatemeh Saberi, Esmael Makarian...

Accelerating innovation with software abstractions for scalable computational geophysics

Mathias Louboutin, Philipp Witte, Ali Siahkoohi, Gabrio Rizzuti, Ziyi Yin, Rafael Orozco, Felix J. Herrmann

International Meeting for Applied Geoscience and Energy (IMAGE)

...), Julia (Bezanson et al., 2017), and Matlab, to domain-specific languages (DSLs), including RVL (Padula et al., 2009), Firedrake (Rathgeber et al., 2016...

Bayesian RockAVO: Direct petrophysical inversion with hierarchical conditional GANs

Miguel Corrales, Muhammad Izzatullah, Matteo Ravasi, Hussein Hoteit

International Meeting for Applied Geoscience and Energy (IMAGE)

... originating from inaccuracies in the measurements, modeling errors, and complex geological processes. Moreover, the non-linearity of the rock-physics model...

Orogenic gold prospectivity mapping using machine learning

Mike McMillan, Jen Fohring, Eldad Haber, Justin Granek

Petroleum Exploration Society of Australia (PESA)

... developed a new algorithm for mineral prospectivity mapping using a VNet deep convolutional neural network and applied it to finding gold at the Committee...

Pushing the limit of 5D interpolation using deep learning

Yangkang Chen, Hang Wang, Chao Li, Omar M. Saad

International Meeting for Applied Geoscience and Energy (IMAGE)

... prepare the initial model in the COP domain instead of the CMP domain is that, in a COP domain with certain offset values, the travel times for adjacent...

Integrated well data and 3D seismic inversion study for reservoir delineation and description

Qazi Sohail Imran, Numair Ahmad Siddiqui, Abdul Halim Abdul Latif, Yasir Bashir, Almasgari Abdalsalam, Abduh Saeed Ali, Muhammad Jamil

Geological Society of Malaysia (GSM)

... because of its bandlimited nature. A plausible broader band frequency is difficult to build when as the model (known as an a priori model) building...

Insights using machine learning in predicting faults and horizons: A case study onshore Texas

Dan Ferdinand Fernandez, Mustafa Karer, Richard Hearn, Ryan King, Sunil Manikani, Gavin Menzel-Jones

International Meeting for Applied Geoscience and Energy (IMAGE)

... Texas dataset. By employing ML technology through convolutional neural networks (CNNs) trained on real data we predict multiple layers of faults from...

GAN based data enhancement for first arrival picking on both onshore and offshore seismic data

Ding Jicai, Wei Yanwen, Wang Yichuan, Sun Wenbo, Wang Jianhua

International Meeting for Applied Geoscience and Energy (IMAGE)

... be studied from three perspectives: data, models, and algorithms (Wang et al., 2020; Ding et al., 2024). Among the three perspectives of data, model...

NATS on WATS seismic imaging, rock property modeling and interpretation using machine-learning techniques to inform reservoir quality and deliverability in the Gulf of Mexico

Peter Lanzarone, Shenghui Li, Kang Fu, Kenny Gullette, Jeff Thompson, Gabriel Ritter

International Meeting for Applied Geoscience and Energy (IMAGE)

... mute, RMO correction, trim statics, structural conformable filtering (SCF), inverse Q, and frequency spectral angle balancing. The resulting gathers...

HIGH-PRECISION ALGORITHM FOR GRAIN SEGMENTATION OF THIN SECTIONS BY MULTI-ANGLE OPTICAL-MICROSCOPIC IMAGES

Timur Murtazin, Zufar Kayumov, Vladimir Morozov, Radik Akhmetov, Anton Kolchugin, Dmitrii Tumakov, Danis Nurgaliev, Vladislav Sudakov

Journal of Sedimentary Research (SEPM)

.... (2020) for semantic segmentation of the porosity of petrographic thin sections. The U-Net model is a fully connected convolutional neural network...

Predicting Hydrocarbon Production Behavior in Heterogeneous Reservoir Utilizing Deep Learning Models

Fatick Nath, Sarker Asish, Happy R. Debi, Mohammed Omar S Chowdhury, Zackary J. Zamora, Sergio Muñoz

Unconventional Resources Technology Conference (URTEC)

... of their cumbersome processing. To overcome this limitation, a supervised deep neural network (DNN) model is established in this paper to forecast hydrocarbon...

Enhancement of the reliability of the ant-tracking algorithm via U-net and dual-threshold iteration

Seunghun Choi, Yongchae Cho

International Meeting for Applied Geoscience and Energy (IMAGE)

... squared error, root mean squared error) to determine the most effective for model training, and the Mean Squared Error function excelled in five...

A Deep Learning-Based Surrogate Model for Rapid Assessment of Geomechanical Risks in Geologic CO2 Storage

Fangning Zheng, Birendra Jha, Behnam Jafarpour

Carbon Capture, Utilization and Storage (CCUS)

... storage. Using simulated data, we train a U-Net convolutional neural network to learn a mapping between well locations s and spatially distributed model...

Generalization Capability of Data-driven Deep Learning Models for Seismic Full-waveform Inversion: An Example Using the OpenFWI Dataset

Ayrat Abdullin, Umair Bin Waheed

International Meeting for Applied Geoscience and Energy (IMAGE)

... model, and ill-posedness of the inverse problem. There is a lack of Data-driven approaches have witnessed development for FWI, including multilayer...

Robust Event Recognition in Real-Time Hydraulic Fracturing Data for Live Reporting and Analysis

Samid Hoda, Jessica Iriarte

Unconventional Resources Technology Conference (URTEC)

... by the model and the frequency of the analysis can be modified to accommodate a variety of internet and streaming conditions. This approach URTeC 2782...