3D GPR data mel-frequency cepstral coefficients features for effective CNN classification of urban utilities

Jide Nosakare Ogunbo, Sang Hun Baek, Sang-Wook Kim

International Meeting for Applied Geoscience and Energy (IMAGE)

...3D GPR data mel-frequency cepstral coefficients features for effective CNN classification of urban utilities Jide Nosakare Ogunbo, Sang Hun Baek...

ABSTRACT: Maximum Likelihood Deconvolution: a New Perspective, by Jerry M. Mendel; #91035 (2010)

Search and Discovery.com

3D real-time imaging for electromagnetic fracturing monitoring based on deep learning

Zhigang Wang, Yao Lu, Ying Hu, Yinchu Li, Ke Wang, Dikun Yang

International Meeting for Applied Geoscience and Energy (IMAGE)

.../10.1093/gji/ggz204. Wang, Z., G. Yu, L. Zhang, C. Wang, J. Zhang, and Z. Liu, 2017, The use of time-frequency domain electromagnetic technique to monitor hydraulic...

ABSTRACT: Shaping the Wavelet, by Wang, Yuchun E.; Huo, Shoudong; #90141 (2012)

Search and Discovery.com

Increasing signal-to-noise ratio of borehole image logs using convolutional neural networks

Mustafa A. Al Ibrahim, Mokhles M. Mezghani

International Meeting for Applied Geoscience and Energy (IMAGE)

... using a convolutional neural network. Results are evaluated quantitatively and qualitatively. Finally, the model is applied on the image log...

Feasibility Study Methodology for Fracture Analysis Studies Using Seismic Azimuthal Amplitude Variation: Application in Southern Mexico

Alexis Ferrer Balas, Nahum Campos, Jesus Garcia Hernandez

GCAGS Transactions

... the well from depth to time domain. Horizons in the vicinity of the well are also required. Their extent depends on the size we want to model and may...

The Hybrid Theory-Guided Data Science-Based Method: Unlocking the Full Potential of Seismic Reservoirs Characterization

Rino Saputra, Akash Mathur, Awal Mandong

Indonesian Petroleum Association

... Base) that are later needed for the low-frequency model generation. The well WTR-4A has more complete data and was used as reference well...

A simultaneous denoising and event picking approach using supervised machine learning

Salman Abbasi, Motaz Alfarraj, Dmitry Borisov, Vikram Jayaram, Iftekhar Alam, Bakhtawer Sarosh

International Meeting for Applied Geoscience and Energy (IMAGE)

... problems (i.e., denoising and event detection) using a single network. A convolutional neural network is used to capture the high frequency times series...

Automated velocity model building using Fourier neural operators

Guanghui Huang, Sean Crawley, Ramzi Djebbi, Jaime Ramos-Martinez, Nizar Chemingui

International Meeting for Applied Geoscience and Energy (IMAGE)

... efficiently computed in the Fourier domain. We show the advantages of using global FNOs over conventional convolutional neural networks (CNN), to achieve...

Seismic image-to-image translation using a conditional GAN with Bayesian inference

Xiaolei Song, Muhong Zhou, Petr Jilek, Rodney Johnston, Sean Cardinez, Kareem Vincent

International Meeting for Applied Geoscience and Energy (IMAGE)

... uncertainties. We take a similar approach by adopting two convolutional Bayesian layers as the network output layers to capture the model...

Bayesian variational auto-encoder for seismic wavelet extraction

Ammar Ghanim, Ricard Durall, Norman Ettrich

International Meeting for Applied Geoscience and Energy (IMAGE)

...-shift. b) using a model trained with time- and frequency-domain loss. c) using the same model as above, but with noise superimposed on the input. a) b...

Time-lapse matching of OBN seismic data using 2D convolutional neural networks

Ramon C. F. Araújo, Gilberto Corso, Samuel Xavier-de-Souza, João M. de Araújo, Tiago Barros

International Meeting for Applied Geoscience and Energy (IMAGE)

...Time-lapse matching of OBN seismic data using 2D convolutional neural networks Ramon C. F. Araújo, Gilberto Corso, Samuel Xavier-de-Souza, João M. de...

Convolution model theory-based intelligent AVO inversion method for VTI media

Yuhang Sun, Yang Liu, Hongli Dong

International Meeting for Applied Geoscience and Energy (IMAGE)

... network technology and propose an intelligent seismic AVO inversion method founded on the convolutional model theory. The proposed method formulates...

Efficient Bayesian full-waveform inversion using a deep convolutional autoencoder prior

Shuhua Hu, Mrinal K Sen, Zeyu Zhao, Abdelrahman Elmeliegy, Shuo Zhang

International Meeting for Applied Geoscience and Energy (IMAGE)

... that model reparametrization using deep convolutional neural networks (CNN) naturally introduces regularization to FWI. To leverage the benefits of DNN...

Attention-based self-calibrated convolution neural network for efficient facies classification

Motaz Alfarraj

International Meeting for Applied Geoscience and Energy (IMAGE)

... and production operations. Deep convolutional neural networks have been widely used for seismic interpretation tasks including detection, classification...

Separation of simultaneous source wavefields using convolutional neural network

Zhehao Li, Hua-Wei Zhou, Kang Fu

International Meeting for Applied Geoscience and Energy (IMAGE)

... not exhibit image Gaussian noise features, we modified the network to train the model in common receiver gathers domain to directly predict...

Application of transfer learning and multi-scale feature fusion in intelligent suppression of seismic random noise

Xin Xu, Wuyang Yang, Xinjian Wei, Haishan Li, Nang Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

.... Key Laboratory of lnternet of Things,CNPC Summary Denoising Convolutional Neural Networks (DnCNN), a data-driven learning algorithm, has been widely...

An application of FWI with progressive transfer learning

Shirui Wang, Jinjun Liu, Yuchen Jin, Xuqing Wu, Jiefu Chen

International Meeting for Applied Geoscience and Energy (IMAGE)

..., University of Houston Summary The lack of low-frequency data components has been a major obstacle in FWI applications for velocity model building...

Abstract: Impedance Inversion of Blackfoot 3D Seismic Dataset; #90171 (2013)

A. Swisi and Igor B. Morozov

Search and Discovery.com

... by using the methods below. 2) Model-based inversion is also called blocky inversion. This method is based on the convolutional seismic model: S =W * R + n...

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...

A geophysical prior knowledge guided semisupervised deep learning framework for AVA inversion

Lei Zhu

International Meeting for Applied Geoscience and Energy (IMAGE)

... forward model. This reduces the dependence of the framework on training data. This GPKGS framework preserves the physical process of AVA inversion, making...

Identification of vehicles from seismic signals using machine learning

Xiaoxuan Zhu, Ji Zhang, Jie Zhang

International Meeting for Applied Geoscience and Energy (IMAGE)

... to record seismic signals generated by passing vehicles. We then conduct analyses in the time domain to roughly categorize traffic vehicles into three...

Stochastic inversion method based on a priori information of compression-sensing divided-frequency waveform indication

Ying Lin, Siyuan Chen, Guangzhi Zhang, Baoli Wang, Minmin Huang

International Meeting for Applied Geoscience and Energy (IMAGE)

... the models in different frequency bands are integrated in the frequency domain to obtain the final required elasticity parameter model. Next, we simplify...

Accurate seismic data interpolation based on multiband intelligent training

Xueyi Sun, Benfeng Wang, Tongtong Mo

International Meeting for Applied Geoscience and Energy (IMAGE)

... in the frequency domain (Porsani, 1985; Spitz, 1991; Naghizadeh and MD Sacchi, 2009; Li et al., 2018). The second is the rank reduction-based...

Abstract: Post-stack Inversion of the Hussar Low Frequency Seismic Data; #90187 (2014)

Patricia E. Gavotti, Don C. Lawton, Gary F. Margrave, and J. Helen Isaac

Search and Discovery.com

... when the low-frequency component is absent in the seismic data. Filtered seismic-data (10-15-60-85 Hz) and an initial model with a 10-15 Hz cut-off were...