Characteristics of the Free Surface Multiple Attenuation Using Wave Field Extrapolation; #40504 (2010)

Patrícia P. Ferreira, Marco Antonio, Cetale Santos, and Luiz Landau

Search and Discovery.com

... be interpreted as the wave field propagation along the water layer such that, the primaries are turned into first-order reverberations. A convolution...

Assessment of Rate Normalization and Pressure Deconvolution Techniques to History-Match and Forecast Production of Tight-Oil Reservoirs Using a Physics-Based Rate-Time Model

Leopoldo M. Ruiz Maraggi, Larry W. Lake, Mark P. Walsh

Unconventional Resources Technology Conference (URTEC)

... conditions. Second, we present the concepts of time superposition, convolution, deconvolution, and rate normalization. Third, we introduce the numerical...

The Characteristics and Origins of Dish and Pillar Structures

Donald R. Lowe, Robert D. LoPiccolo

Journal of Sedimentary Research (SEPM)

... crosslaminations deformed near top into convolute laminations: anticlinal convolution containing plant debris (1) and synclinal convolution showing...

Thickness Estimation Using Gradient of Spectral Amplitudes from Spectral Decomposition

Tri Wuri Asri Sulistyoati, Lita Novitasari, Sonny Winardhi

Indonesian Petroleum Association

.... In the frequency domain, the convolution theory dictates that the spectrum of the seismic trace is a multiplication of the reflectivity and the wavelet spectra...

Extending Engine Change Out Respective to Running Hours Using Data Driven Using One Dimension (1-D) Convolutional Neural Network Algorithm

Subhan Malik, Harry Poetra Soedarsono

Indonesian Petroleum Association

...) algorithm. During each iteration of the BP, the gradient magnitude (or sensitivity) of each network parameter such the weights of the convolution...

Implications from Transfer Functions when Comparing Seismic Data from MEMS Accelerometers and Geophones

Michael S. Hons

Search and Discovery.com

... a symmetrical ‘zerophase’ appearance (Figure 4), which very closely resembles the result of double time differentiation and convolution with a MEMS...

Implications from Transfer Functions when Comparing Seismic Data from MEMS Accelerometers and Geophones

Michael S. Hons

Search and Discovery.com

... a symmetrical ‘zerophase’ appearance (Figure 4), which very closely resembles the result of double time differentiation and convolution with a MEMS...

Amplitude Mapping of Reservoirs in North Africa

Search and Discovery.com

... spectrum. A “match filter” is a simple convolution filter designed on the difference in phase and amplitude spectra between two wavelets. An operator...

Abstract: Monte Carlo Markov Chain Methods in Seismic Deconvolution; #90174 (2014)

Andres Medina and Mirko van der Baan

Search and Discovery.com

..., **[email protected]. Summary One prevailing assumption in reflection seismology is that the observed trace can be described as a convolution...

Abstract: Acceleration on Sparse Promoting Seismic Applications; #90187 (2014)

Lina Miao and Felix Herrmann

Search and Discovery.com

..., we run SPGℓ1 and PQNℓ1 to perform a spike de-convolution to the same data residual, the different behaviors are listed in figure 3. a is the original...

New Technology to Acquire, Process, and Interpret Transient EM Data; #41579 (2015)

Anton Ziolkowski, Richard Carson, David Wright

Search and Discovery.com

... and is the convolution: vCD(t) = ΔxsΔxriAB(t)* gCD;AB(t) + nCD(t) (1) where vCD(t) is the voltage at the receiver, iAB(t) is the current at the source, gCD...

CGG 3D Surface-Related Multiple Modelling: A Unique Approach, #41590 (2015).

David Le Meur, Antonio Pica, Terje Weisser

Search and Discovery.com

... is a reliable representation of the actual subsurface reflectivity. By comparison, SRME convolution of the data with the primaries (Verschuur and Berkhout...

Convolution Neural Networks … If They can Identify an Oncoming Car, can They Identify Lithofacies in Core?; #42312 (2018)

Rafael Pires de Lima, Fnu Suriamin, Kurt Marfurt, Matthew Pranter, Gerilyn Soreghan

Search and Discovery.com

...Convolution Neural Networks … If They can Identify an Oncoming Car, can They Identify Lithofacies in Core?; #42312 (2018) Rafael Pires de Lima, Fnu...

Reliability estimation of the prediction results by 1D deep learning ATEM inversion using maximum depth of investigation

Hyeonwoo Kang, Minkyu Bang, Soon Jee Seol, Joongmoo Byun

International Meeting for Applied Geoscience and Energy (IMAGE)

... “group convolution” of ResNeXt and “Patchifiy” strategy of Swin-Transformer that achieves state-of-the-art (SOTA) in a rapidly developing image-network...

Operator chains and seismic data decomposition

Sergey Fomel

International Meeting for Applied Geoscience and Energy (IMAGE)

... of migration and modeling, which is a comparatively expensive approach. Alternatively, it can be approximated by using non-stationary convolution (Hu et al...

Anti-aliasing seismic data interpolation by dip-informed self-supervised learning

Shirui Wang, Xuqing Wu, Jiefu Chen

International Meeting for Applied Geoscience and Energy (IMAGE)

... nature of seismic data, a suitable (a) Figure 1: Illustration of the dip-informed deformable convolution. (a) An example seismic gather, in which...

Fracture-cavity carbonate reservoir identification based on channel attention mechanisms

Liuxin Yang, Yongqiang Ma, Guangxiao Deng, Zhen Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

... information from input data. The kernel size is generally the same as the length of wavelet. The output layer is also a convolutional layer with one convolution...

Estimating soil strength using ultra high-resolution seismic and geological unit

Donglin Zhu, Ge Jin, Yi Shen, Xuefeng Shang, Shuang Hu, Jinbo Chen, Vanessa Goh

International Meeting for Applied Geoscience and Energy (IMAGE)

...t simple and straightforward to prevent overfitting. It comprises four convolution blocks and two dense layers (Figure 1). Each convolution block include...

Explainable AI: Can neural networks recognize first arrivals after wave separation?

Yanwen Wei, Zhenyu Zhu, Jicai Ding, Yichuan Wang

International Meeting for Applied Geoscience and Energy (IMAGE)

... layer that contains convolution and activation operations, its forward propagation process can be represented as follows: � = ����(�� + �), where...

The Marchenko internal multiple elimination based on focal transform and its application on seismic data reconstruction

Zhen Liao, Xiaohong Chen, Wenjin Li

International Meeting for Applied Geoscience and Energy (IMAGE)

... internal multiples, necessitating solely a background velocity model or the original data. This method involves conducting correlation and convolution...

Seismic absolute acoustic impedance inversion using domain adversarial based transfer learning

Anjali Dixit, Animesh Mandal

International Meeting for Applied Geoscience and Energy (IMAGE)

... predictor, and c) Domain discriminator. The role of each module is discussed as follow. Feature extractor 𝐺! (. ): It contains six convolution blocks...

Sparse time-frequency representation based on Unet with domain adaptation

Yuxin Zhang, Naihao Liu, Yang Yang, Zhiguo Wang, Jinghuai Gao, Xiudi Jiang

International Meeting for Applied Geoscience and Energy (IMAGE)

... model consists of three modules, i.e. the transformation, the feature learning, and the upsample modules. First, there is a 1x3 convolution operation...

A hybrid machine learning model for improving regression of mineral composition estimation using well logging data

Xiaojun Liu, Kezhen Hu, Stephen E. Grasby, Benjamin Lee

International Meeting for Applied Geoscience and Energy (IMAGE)

... mathematical operation of convolution followed by non-linear activators, pooling layers, and a deep neural network classifier. The expansive path...

An automatic velocity picking method based on object detection

Ce Bian, Weifeng Geng, Ping Yang, Pengyuan Sun, Guiren Xue, Haikun Lin

International Meeting for Applied Geoscience and Energy (IMAGE)

... on five feature layers with different sizes, so as to realize accurate recognition of small and multi-scale objects. In this paper, both the convolution...

Interactive channel interpretation using deep learning

Hao Zhang, Peimin Zhu, Zhiying Liao, Zewei Li, Dianyong Ruan

International Meeting for Applied Geoscience and Energy (IMAGE)

...× 256. The Encoder part contains 3 groups of convolution-pooling combined layers. Each group contains two convolutional layers and one pooling layer...