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)

..., Rapid surrogate modeling of electromagnetic data in frequency domain using neural operator: IEEE Transactions on Geoscience and Remote Sensing, 60...

Noise suppression and compressive sensing recovery with seismic-adapted DnCNN within RED

Nasser Kazemi

International Meeting for Applied Geoscience and Energy (IMAGE)

..., i.e., seismic domain. In this paper, we explore the transferability of feedforward denoising convolutional neural networks (DnCNN) learned operator...

GAN-based priors for Bayesian inference of subsurface geology at large scale

Kevin B. Daly, Tuan A. Tran, Brent D. Wheelock, Grant J. Seastream

International Meeting for Applied Geoscience and Energy (IMAGE)

... in the process stratigraphy simulations. One solution is to select a generative ML model with a fully convolutional architecture, where the latent coordinate...

AI to Improve the Reliability and Reproducibility of Descriptive Data: A Case Study Using Convolutional Neural Networks to Recognize Carbonate Facies in Cores

Search and Discovery.com

-- no title --

user1

Search and Discovery.com

... Lithotypes Classification with Convolutional Neural Networks Evgeny E. Baraboshkin1, Evdokiya A. Panchenko2, Andrey E. Demidov1, Ardiansyah...

Kutei Basin: Feasibility Study of a Broadband Acquisition

Gilbert Del Molino, Fabri Ikhlas Gumulya, Dedy Sulistiyo Purnomo, Paolo Battini, Bonita Nurdiana Ersan, Francesca Brega, Ferdinando Rizzo, Giorgio Cavanna, Buia Michele

Indonesian Petroleum Association

... conventional and broadband synthetic elastic inversions, the frequency bandwidth of prior model to be included in order to obtain optimal results appeared...

Horizontal Stresses Prediction Using Sonic Transition Time Based on Convolutional Neural Network; #42587 (2023)

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

Search and Discovery.com

...Horizontal Stresses Prediction Using Sonic Transition Time Based on Convolutional Neural Network; #42587 (2023) Esmael Makarian, Ayub Elyasi, Fatemeh...

Improving pre-stack inter-trace variation extraction with a self-supervised learning approach

Yifeng Fei, Xin He, Bangli Zou, Jiandong Liang, Dajun Li

International Meeting for Applied Geoscience and Energy (IMAGE)

.... Notable examples include utilizing a geological and geophysical model-driven convolutional neural network (CNN) for the extraction of elastic parameter...

Abstract: GAN-Based Multipoint Geostatistical Inversion Method and Application;

Pengfei Xie, Jiagen Hou

Search and Discovery.com

... technology. Multi-point statistics (MPS) generate model realizations by training image (TI) that are consistent with prior information. This method often...

Automatic low-order weak faults detection from carbonate reservoir based on deep learning and ant tracking

Han Wang, Xingwei Wu, Hanqing Wang, Jin Meng, Ji Chang, Tianrui Ye, Yujie Zhou, Dongwei Zhang, Yitian Xiao

International Meeting for Applied Geoscience and Energy (IMAGE)

... of the improved convolutional neural network (3D attention-based U-Net) for low-order fault detection. (a) The model structure. (b) The structure...

Development of deep learning method for automatic seismic first break picking

Albert Farkhutdinov, Ruslan Malikov, Izat Shahsenov

International Meeting for Applied Geoscience and Energy (IMAGE)

... learning based techniques, such as support vector machines, convolutional image segmentation, and U-Net networks, have been studied for automatic FBP (Qu et...

An unsupervised intelligent stacking velocity analysis based on clustering

Lide Wang, Xingrong Xu, Jie Wu, Huahui Zeng, Yundong Yong, Yanxiang Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

... efficiency and different standards. With the increasing application of wide-frequency, wide-azimuth and highdensity seismic exploration technology...

Fast self-supervised learning for reconstruction of 3D seismic data

Yinshuo Li, Wenkai Lu, We Cao

International Meeting for Applied Geoscience and Energy (IMAGE)

...) Complex convolution in the frequency domain Y f =CConv(X f ), X f =Xreal + iXimag , Yreal =Wreal Xreal − Wimag Ximag , (3) Yimag =Wreal Ximag + Wimag...

How Machine Learning is Helping Seismic Structural Interpreters in The Age of Big Data

Çağil Karakaş, James Kiely

GEO ExPro Magazine

... is a very time-consuming task, often leading to a simplified fault model, a geology-driven, machine-learning workflow can significantly improve...

Seismic data reconstruction using denoising convolutional neural network combined with regularization by denoising

Nanying Lan, Kaiheng Sang, Fanchang Zhang

International Meeting for Applied Geoscience and Energy (IMAGE)

...Seismic data reconstruction using denoising convolutional neural network combined with regularization by denoising Nanying Lan, Kaiheng Sang...

Data selection for velocity model estimation using a circular shot OBN survey

Felipe T. Costa, Sergio L. E. F. da Silva, Ammir A. Karsou, Felipe Capuzzo, Roger M. Moreira, Jorge Lopez, Marco Cetale

International Meeting for Applied Geoscience and Energy (IMAGE)

..., Seismic waveform inversion in the frequency domain, Part 1: Theory and verification in a physical scale model: Geophysics, 64, 888–901, doi: https...

Identifying geologic facies through seismic dataset-to-dataset transfer learning using convolutional neural networks

Joseph Stitt, Adam Shugar, Rachael Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

... for the baseline model we used is a public-domain survey called “Parihaka,” which contains offshore seismic data from the New Zealand government...

Automated velocity modeling with domain transformations

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

International Meeting for Applied Geoscience and Energy (IMAGE)

... the data from the shot gather domain to the tau-p domain, then predicting the time-domain velocity model using a U-Net, and finally converting from...

Reliable uncertainty estimation for seismic interpretation with prediction switches

Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib

International Meeting for Applied Geoscience and Energy (IMAGE)

... interpretation and provide a novel measure of uncertainty based on neural network forgetting. Specifically, we quantify uncertainty by the frequency in which...

Finding the reservoir in an intensely scattered wavefield: A case study from the Central Sichuan Basin, China

John Coffin, Mengmeng Zhang, Panos Doulgeris, Peter Haffinger, Angie Kelsay, Jinsong Li

International Meeting for Applied Geoscience and Energy (IMAGE)

... an elastic modelling scheme including interbed multiples and multiple mode conversions for the well-tie. A linear convolutional model results in perfectly...

Machine-Learning-Assisted Segmentation of FIB-SEM Images with Artifacts for Improved of Pore Space Characterization of Tight Reservoir Rocks

Andrey Kazak, Kirill Simonov, Victor Kulikov

Unconventional Resources Technology Conference (URTEC)

... on a convolutional neural network (CNN) in the DeepUnet configuration. The implementation utilized the Pytorch framework in a Linux environment...

Abstract: Machine Learning Assisted Fracture Characterization with Borehole Image Logs in Geothermal Wells; #91204 (2023)

Chicheng Xu

Search and Discovery.com

... from multiple sources of data, we build a convolutional neural network model and train it with the labeled results from borehole image log. The model...

Simultaneous imaging of basement relief and varying susceptibility in deep-learning approach

Zhuo Liu, Yaoguo Li

International Meeting for Applied Geoscience and Energy (IMAGE)

... in the basement rock assuming a 2D model. Particularly, the U-net architecture followed by a fully connected (FC) layer is adopted to map the information...

Enhancing fiber-optic DAS microseismic event detection in imbalanced data using embedding space optimization

Min Jun Park, Hassan Almomin, Bob Clapp

International Meeting for Applied Geoscience and Energy (IMAGE)

... networks are trained, followed by the extraction of embeddings to define class centers in the embedding space. The embedding model is then fine-tuned...

Operator chains and seismic data decomposition

Sergey Fomel

International Meeting for Applied Geoscience and Energy (IMAGE)

... at Austin SUMMARY nating between the space domain and the frequency domain. Chains of elementary operators can be used to approximate more complex...