Physics-Constrained Deep Learning for Production Forecast in Tight Reservoirs

Nguyen T. Le, Roman J. Shor, Zhuoheng Chen

Unconventional Resources Technology Conference (URTEC)

... of a layer is fed back into that layer, hence the name "recurrent" (Figure 1). RNN employs a hidden state vector to store information about past steps...

Unconventional reservoir characterization by seismic inversion and machine learning of the Bakken Formation

Jackson R. Tomski, Mrinal K. Sen, Thomas E. Hess, and Michael J. Pyrcz

AAPG Bulletin

... in that prediction. α0,m = added bias between input and hidden layer neuron, m; α1,1 = weight that maps from input neuron 1 to hidden neuron 1; αp,m...

Abstract: Water Clarity Near Oil Production Platforms on Louisiana Continental Shelf and Source of Turbid Bottom Water Layer, by George M. Griffin; #90965 (1978).

Search and Discovery.com

Advanced Machine Learning Methods for Prediction of Fracture Closure Pressure, ClosureTime, Permeability and Time to Late Flow Regimes From DFIT

Mohamed Ibrahim Mohamed, Dinesh Mehta, Mohamed Salah, Mazher Ibrahim, Erdal Ozkan

Unconventional Resources Technology Conference (URTEC)

... of nodes: an input layer, a hidden layer, and an output layer. Except for the input nodes, each node is a neuron that uses a nonlinear activation function...

A hybrid deep learning network for tight and shale reservoir characterization using pressure and rate transient data

Hamzeh Alimohammadi, Hamid Rahmanifard, and Shengnan Nancy Chen

AAPG Bulletin

... type in retrograde gas reservoirs and got higher accuracy with the MLP model. AlMaraghi and El-Banbi (2015) used FCNNs with two hidden layers...

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)

... set (10%). In the training process, the parameters were adjusted according to the type of hidden-layer activation function, the presence or absence...

Abstracts: Microseismic Source Inversion in Anisotropic Media; #90173 (2015)

Scott Leaney, Chris Chapman, and Tadeusz Ulrych

Search and Discovery.com

...) and receiver polarization but also the propagation terms hidden inside G – times, spreading and transmission loss, and source and receiver impedance coupling...

Use of Neurosimulation in Well Placement for the Development of a Hydrocarbon Field

Hector Emilio Barrios Molano

Asociación Colombiana de Geólogos y Geofisicos del Petróleo (ACGGP)

... be modified in terms of number of neurons in the input and hidden layer, depending on what the case to analyze. Step 5: Generation of scenarios. Using...

Must Geologists Have High Spatial Ability to be Successful in Visual Penetration?; #120158 (2014)

Dale Klopfer, Charles Onasch, Guy Zimmerman, Laura Marie Leventhal, Justin Gilkey, Brandi A. Klein, and Samuel D. Jaffee

Search and Discovery.com

... between Structure Type X Cross Section Location (F(10,356) = 5.036, p < .05) on accuracy; see Table 1. The VP effect was seen with SE-Dipping Layer...

Abstract: AVAZ Inversion for Fracture Orientation and Intensity: a Physical Modeling Study; #90187 (2014)

Faranak Mahmoudian and Gary F. Margrave

Search and Discovery.com

... planes, and its elastic properties have already been determined using traveltime analysis. This experimental model represents a HTI layer. We follow...

Study of the Seismic Attenuation Generated by the Mud Layer in Lake Maracaibo, Venezuela

J. Perez, E. Andara, B. Malave

Asociación Colombiana de Geólogos y Geofisicos del Petróleo (ACGGP)

... the particles, the solid friction losses between the particles, the mud layer and the gassy sediment effect are factors proposed to account...

On the Stabilizing Influence of Silt on Sand Beds

Gerhard Bartzke, Karin R. Bryan, Conrad A. Pilditch, Katrin Huhn

Journal of Sedimentary Research (SEPM)

... treatment effect (homogeneity of slopes p  =  0.35; treatment p  =  0.88) on boundary-layer flow characteristics. Consequently data from all three...

Enhancing the Process of Knowledge Discovery from Integrated Geophysical Databases Using Geo-Ontologies

Shastri L. Nimmagadda, Heinz Dreher, Andi Noventiyanto, Aswin Mostafa, Giuseppe Fiume

Indonesian Petroleum Association

... requirements, data patterns and trends hidden in these voluminous integrated data, non-trivial data mining and interpretation solutions are required. Data...

Fold Development in Zagros Simply Folded Belt, Southwest Iran

S. P. Colman-Sadd

AAPG Bulletin

..., they must change in style to similar or chevron folds, or the folded layer must become detached from the rocks both above and below. In the case...

Some Applications of Pure Seismology to Geological Problems

L. Don Leet

Tulsa Geological Society

..., the latter at thiry-five. These depths are respectively the base of the granitic layer and the base of the surface layers. Such an effect could have been...

Machine Learning Models for Predicting the Rheology of Nanoparticle-Stabilized-CO2-Foam Fracturing Fluid in Reservoir Conditions

Toluwalase Adeola Olukoga, Yin Feng

Unconventional Resources Technology Conference (URTEC)

...). MLP neural network is made up of three layers: an input layer, one or more hidden layers, and a final output layer. (Zare et Al., 2013). The MLPNN...

Deep learning to predict subsurface properties from injected CO2 plume bodies using time-lapse seismic shot gathers

Son Phan, Wenyi Hu, Aria Abubakar

International Meeting for Applied Geoscience and Energy (IMAGE)

... aims at reducing the emission of carbon dioxide (CO2) into the atmosphere by injecting this greenhouse-effect gas into an underground storage...

Ignimbrites

Harold E. Enlows

Tulsa Geological Society

..., has a strong fluxing effect markedly lowering the melting point of the melt and, to a lesser extent, decreasing the viscosity. It was also generally...

Worldwide Examples of Low Resistivity Pay

Robert M. Sneider

Houston Geological Society Bulletin

... hydrocarbon accumulations are "hidden" in low-resistivity, low-contrast (LRLC) sands in many of the world's basins. LRLC reservoirs have been found...

Generating Missing Unconventional Oilfield Data using a Generative Adversarial Imputation Network (GAIN)

Justin Andrews, Sheldon Gorell

Unconventional Resources Technology Conference (URTEC)

... for the pooled wells, can lead to good data to be ignored. Even changes in company policy can have a huge effect on the availability of recorded...

South Atlantic Rifting and Some General Principles for Rift Exploration on Continental Margins, #10675 (2014).

Ian Davison, Eoin O. Beirne

Search and Discovery.com

... and there is little matrix. These ‘hidden reservoirs’ host significant oil reserves on both sides of the Atlantic (e.g. Rio do Bu Field Recôncavo, M'Boundi...

Data-Driven Approach to Optimize Stimulation Design in Eagle Ford Formation

Francisco Herrero Clar, Agustin Monaco

Unconventional Resources Technology Conference (URTEC)

... a few variables with production; an ANN model with one hidden layer was selected for this approach. This kind of model is a biologically inspired...

Machine Learning Prediction for Fluid Identification in Kujung Formation East Java

Freddy Calvin Bryan, Violita Indrayani Putri, Ardian Nengkoda, Andy Noorsaman Sommeng, Sutrasno Kartohardjono

Indonesian Petroleum Association

... variable are located in the hidden layers of a multi-layer perceptron (MLP), typically consisting of three layers. Each neuron processes the information...

ABSTRACT: Normal Faulting Beneath a Ductile Layer: Experimental Modeling of Deformation Patterns in the Cover Sequence, by M. O. Withjack and J. S. Callaway; #91021 (2010)

Search and Discovery.com

Geoscience Technology Workshops (GTW)

Search and Discovery.com