Counterfactual uncertainty for high dimensional tabular dataset

Prithwijit Chowdhury, Ahmad Mustafa, Mohit Prabhushankar, Ghassan AlRegib

International Meeting for Applied Geoscience and Energy (IMAGE)

... by varying one Feature at a time (1,2,3,4) and recording the model behavior to these changes against the values of the concerned feature. Figure 6...

Multi-information intelligent decision process for first-break picking

Fei Luo, Lanlan Yan

International Meeting for Applied Geoscience and Energy (IMAGE)

..., a visually intensive, time-consuming, and inefficient process. With the advancement of computer technology and firstarrival picking algorithms, fully...

Evaluation of Empirical Correlations and Time Series Models for the Prediction and Forecast of Unconventional Wells Production in Wolfcamp A Formation

Aimen Laalam, Houdaifa Khalifa, Habib Ouadi, Mouna Keltoum Benabid, Olusegun Stanley Tomomewo, Mouad Al Krmagi

Unconventional Resources Technology Conference (URTEC)

... with modern time series models like ARIMA, LSTM, and GRUs. The results indicate no single model consistently excels, necessitating tailored approaches for each...

An approach for three-dimensional quantitative carbonate reservoir characterization in the Pampo field, Campos Basin, offshore Brazil

Danilo Jotta Ariza Ferreira, and Wagner Moreira Lupinacci

AAPG Bulletin

... can use the convolutional model of the seismic trace-in-time domain,where s(t), r(t), ω(t), and n(t) represent, respectively, the seismic trace...

Delineation of Gas Sands by Seismic Stratigraphy in the Pericocal Area, Orinoco Heavy Oil Belt, Venezuela: Section IV. Exploration Methods

J. Licheri, N. Parra

AAPG Special Volumes

... are interpreted in terms of geology and/or presence of fluids, according to the convolutional model. -- The parameters that allow changes in the seismic...

Reservoir Modeling With Deep Learning

Search and Discovery.com

Application of intelligent fault identification and sealing evaluation technology in Lukeqin area

Sun bo, Lin Yu, Guo Xiang, Yin Xue Bin, Nie Zhiwei, Liu Hongyan

International Meeting for Applied Geoscience and Energy (IMAGE)

... as a whole. Through fault model construction, deep learning and direct prediction, the micro-fault prediction technology based on convolutional neural...

GeoMind: An intelligent earth model building tool

Saleh Al Saleh, Ewenet Gashawbeza, Mustafa Marzooq, Hussam Banaja, Husain Al Shakhs, Jianwu Jiao

International Meeting for Applied Geoscience and Energy (IMAGE)

...GeoMind: An intelligent earth model building tool Saleh Al Saleh, Ewenet Gashawbeza, Mustafa Marzooq, Hussam Banaja, Husain Al Shakhs, Jianwu Jiao...

Production Forecasting in Shale Reservoirs through Conventional DCA and Machine/Deep Learning Methods

Cenk Temizel, Celal Hakan Canbaz, Onder Saracoglu, Dike Putra, Ali Baser, Tomi Erfando, Shanker Krishna, Luigi Saputelli

Unconventional Resources Technology Conference (URTEC)

..., a situation in which huge error gradients get accumulated leading to huge modifications to the model weights at the time of training. This can cause...

Noise analysis and ML denoising of DAS VSP data acquired from ESP lifted wells

Ge Zhan, Yao Zhao, Cheng Cheng, Josef Heim, Weihong Fei, Mike Craven, Scott Baker, Gilles Hennenfent

International Meeting for Applied Geoscience and Energy (IMAGE)

... developed a machine learning (ML) workflow that uses a deep convolutional U-Net architecture to model the ESP noise first and then subtract it from...

Using Second-Order Adjoint State Methods in GPUS to Quantify Resolution on Full Waveform Inversions, #42034 (2017).

Sergio Abreo, Ana Ramirez, Oscar Mauricio Reyes Torres

Search and Discovery.com

... Inversion (FWI) allows quantifying resolution of the velocity model obtained. Although there are different ways to compute approximations of the Hessian...

Generating geophysical models from text for constructing the dataset of learning-based MT inversion

Yutong Li, Hongyu Zhou, Rui Guo, Maokun Li, Aria Abubakar

International Meeting for Applied Geoscience and Energy (IMAGE)

... of text embedding is the bag-of-words model, where each extracted key point is quantized into one of the visual words, and each image is represented...

Artificial Intelligence Integration for Optimal Reservoir Data Analysis and Pattern Recognition

Dr. Leon Hamilton, Dr. Marianne Rauch

Unconventional Resources Technology Conference (URTEC)

... 4054687 Figure 1: Top left, final seismic pre-stack time migrated stack, below, AI derived rock property volume and right model that was used for the AI...

3D seismic image-to-image translation

Xiaolei Song, Muhong Zhou, Lifeng Wang, Rodney Johnston

International Meeting for Applied Geoscience and Energy (IMAGE)

... by adopting two convolutional Bayesian layers as the network output layers to analyze the model uncertainties by calculating an uncertainty map from a local...

Automatic facies classification using convolutional neural network for three-dimensional outcrop data: Application to the outcrop of the mass-transport deposit

Ryusei Sato, Kazuki Kikuchi, and Hajime Naruse

AAPG Bulletin

... point clouds used as training data for the convolutional neural network (CNN) model. (A, C) Original point cloud used as training data for the CNN model...

Imaging and fold comparison of mirror reverse time migration vs. interferometric imaging for VSP data

Liwei Cheng, James Simmons, Ali Tura

International Meeting for Applied Geoscience and Energy (IMAGE)

...Imaging and fold comparison of mirror reverse time migration vs. interferometric imaging for VSP data Liwei Cheng, James Simmons, Ali Tura Imaging...

Abstract: Towards the Identification of Coal Macerals through Deep Learning

Na Xu, Qingfeng Wang, Pengfei Li, Mark A. Engle

The Society for Organic Petrology (TSOP)

... are compared with the other three existing image segmentation methods, including K-means [4], Gaussian mixture model (GMM), [5] and convolutional neural...

Methods of estimating wavelet stationarity, stabilizing non-stationarity, and evaluating its impact on inversion: A synthetic example using SEAM II Barrett unconventional model

Jesse Buckner, Michael Fry, Joe Zuech, Peter Harris, Bill Shea

International Meeting for Applied Geoscience and Energy (IMAGE)

... is simulated across a continuous 3D convolutional synthetic seismic volume, derived from the earth model of the SEAM II Barrett dataset. Multiple...

Deep learning based microearthquake location prediction at Newberry EGS using physics-informed synthetic dataset

Zi Xian Leong, Tieyuan Zhu

International Meeting for Applied Geoscience and Energy (IMAGE)

... the velocity model, making it beneficial for near real-time EGS monitoring. Lastly, the significantly quick inference speeds of DL-based source...

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)

... wavefield computation and RTM results are shown for SEG Hess VTI model and dataset. Compute time and memory utilized for ISO and VTI RTM has been...

Seismic Data Preconditioning for Improved Reservoir Characterization (Inversion and Fracture Analysis); #41347 (2014)

Darren Schmidt, Alicia Veronesi, Franck Delbecq, and Jeff Durand

Search and Discovery.com

...) or convolutional Zoeppritz-type synthetics (in which only primaries are modeled). Comparing the real seismic to the well synthetic response is the best...

Fluid distribution modeling impact on estimating CO2 saturation in Cranfield: A capillary pressure equilibrium approach with invertible neural networks

Sohini Dasgupta, Arnab Dhara, Mrinal K. Sen

International Meeting for Applied Geoscience and Energy (IMAGE)

... a-prior fluid distribution model. This model can be used for saturation analysis uniquely surpassing the two saturation model problem in time-lapse...

Machine learning-based residual moveout picking

Farhad Bazargani, Wenjun Zhang, Anu Chandran, Zaifeng Liu, Harry Rynja

International Meeting for Applied Geoscience and Energy (IMAGE)

... picking with minimum human intervention and no need for editing. INTRODUCTION In travel time tomography for velocity model building, residual moveout (RMO...

Transfer Learning with Multiple Aggregated Source Models in Unconventional Reservoirs

J. Cornelio, S. Mohd Razak, Y. Cho, H-H. Liu, R. Vaidya, B. Jafarpour

Unconventional Resources Technology Conference (URTEC)

..., 𝑥 to the production from the target field, 𝑑i81j6J,1L0J directly, The model is trained in the same way as explained in Table 1. This F6 time 𝑅𝑒𝑔E_`SaT...

Abstract: Integrating Geologic and Geophysical Data in Geostatistical Inversion; #90187 (2014)

John V. Pendrel

Search and Discovery.com

..., a rock physics model can be used. The stratigraphic grids on which the reservoir properties are generated can be in either depth or time. If the grid...