Reservoir characterization using seismic waveform and feedforword neural networks

Geophysics ◽  
2001 ◽  
Vol 66 (5) ◽  
pp. 1450-1456 ◽  
Author(s):  
P. An ◽  
W. M. Moon ◽  
F. Kalantzis
Keyword(s):  
Neural Networks ◽  
Reservoir Characterization ◽  
Random Noise ◽  
Feedforward Neural Networks ◽  
Oil Field ◽  
Seismic Survey ◽  
Coherent Noise ◽  
Reservoir Properties ◽  
Seismic Waveform ◽  
The Neural Networks

Feedforward neural networks are used to estimate reservoir properties. The neural networks are trained with known reservoir properties from well log data and seismic waveforms at well locations. The trained neural networks are then applied to the whole seismic survey to generate a map of the predicted reservoir property. Both theoretical analysis and testing with synthetic models show that the neural networks are adaptive to coherent noise and that random noise in the training samples may increase the robustness of the trained neural networks. This approach was applied to a mature oil field to explore for Devonian reef‐edge oil by estimating the product of porosity and net pay thickness in northern Alberta, Canada. The resulting prediction map was used to select new well locations and design horizontal well trajectories. Four wells were drilled based on the prediction; all were successful. This increased production of the oil field by about 20%.

scholarly journals APPLICATION OF SEISMIC METHODS FOR INTEGRATED RESERVOIR CHARACTERIZATION

Neft i gaz ◽  
2020 ◽  
Vol 3-4 (117-1118) ◽  
pp. 84-92
Author(s):  
A.K. ZHUMABEKOV ◽  
◽  
V.S. PORTNOV ◽  
Keyword(s):  
Reservoir Characterization ◽  
Research Work ◽  
Seismic Signal ◽  
Point Of View ◽  
Oil Field ◽  
Seismic Survey ◽  
Reservoir Properties ◽  
Seismic Methods ◽  
Sedimentation Environment ◽  
Analysis Of Results

3D seismic survey is the undisputed leader among tools of identifying potential exploration targets and reservoir characterization. This paper shows surveys that are crucial in the exploration and development of significant amounts of hydrocarbon resources, and can be used by operator companies to map complex geological structures and select better drilling locations. The purpose of research work is to have better understandings of formations and update previous studies in oil field of Mangyshlak Basin, Western Kazakhstan. The Main resultsare the acoustic impedance, Vp / Vs ratio, lithological and reservoir properties data. The quality *Автор для переписки. E-mail: [email protected] НЕФТЬ И ГАЗ 2020. 3–4 (117–118) 85 ГЕОФИЗИКА controls and analysis of results show good match with well logs and good recovery of seismic signal in inversion, but it should be improved in some areas. The results, from a scientific point of view, expand the already known geological and geophysical studies of the reservoir and improve the quality of interpretation using seismic methods in studying the sedimentation environment of the site.

scholarly journals Integrated reservoir characterization based on a comprehensive study of the geological structure using 3D seismic survey

2021 ◽  
Vol 266 ◽  
pp. 07009
Author(s):  
A.K. Zhumabekov ◽  
V.S. Portnov ◽  
L. Zhen
Keyword(s):  
Reservoir Characterization ◽  
Seismic Signal ◽  
Geological Structure ◽  
Point Of View ◽  
Oil Field ◽  
Seismic Survey ◽  
3D Seismic ◽  
Reservoir Properties ◽  
Sedimentation Environment ◽  
Analysis Of Results

The 3D seismic survey is the undisputed leader among tools of identifying potential exploration targets and reservoir characterization. This paper shows surveys that are crucial in the exploration and development of significant amounts of hydrocarbon resources, and enables operator companies to map complex geological structures and select better drilling locations. The purpose of the research is to have better understandings of formations and update previous studies in the oil field of Mangyshlak Basin, Western Kazakhstan. The Main results are the acoustic impedance, Vp/Vs ratio, lithological and reservoir properties data. The quality controls and analysis of results show a good match with well logs and good recovery of seismic signal in inversion, but it should be improved in some areas. The results, from a scientific point of view, expand the already known geological and geophysical studies of the reservoir and improve the quality of interpretation using seismic methods in studying the sedimentation environment.

Integrated seismic texture segmentation and cluster analysis applied to channel delineation and chert reservoir characterization

Geophysics ◽  
2011 ◽  
Vol 76 (5) ◽  
pp. P11-P21 ◽  
Author(s):  
Marcilio Castro de Matos ◽  
Malleswar (Moe) Yenugu ◽  
Sipuikinene Miguel Angelo ◽  
Kurt J. Marfurt
Keyword(s):  
Texture Analysis ◽  
Reservoir Characterization ◽  
Three Dimensional ◽  
Seismic Survey ◽  
Self Organizing Maps ◽  
Early Introduction ◽  
Statistical Measures ◽  
Seismic Waveform ◽  
Occurrence Matrix ◽  
Single Trace

In recent years, 3D volumetric attributes have gained wide acceptance by seismic interpreters. The early introduction of the single-trace complex trace attribute was quickly followed by seismic sequence attribute mapping workflows. Three-dimensional geometric attributes such as coherence and curvature are also widely used. Most of these attributes correspond to very simple, easy-to-understand measures of a waveform or surface morphology. However, not all geologic features can be so easily quantified. For this reason, simple statistical measures of the seismic waveform such as rms amplitude and texture analysis techniques prove to be quite valuable in delineating more chaotic stratigraphy. In this paper, we coupled structure-oriented texture analysis based on the gray-level co-occurrence matrix with self-organizing maps clustering technology and applied it to classify seismic textures. By this way, we expect that our workflow should be more sensitive to lateral changes, rather than vertical changes, in reflectivity. We applied the methodology to a remote sensing image and to a 3D seismic survey acquired over Osage County, Oklahoma, USA. Our results indicate that our method can be used to delineate meandering channels as well as to characterize chert reservoirs.

A new petrophysical joint inversion workflow: Advancing on reservoir’s characterization challenges

2018 ◽  
Vol 6 (3) ◽  
pp. SG33-SG39 ◽  
Author(s):  
Fabio Miotti ◽  
Andrea Zerilli ◽  
Paulo T. L. Menezes ◽  
João L. S. Crepaldi ◽  
Adriano R. Viana
Keyword(s):  
Reservoir Characterization ◽  
Joint Inversion ◽  
Oil Field ◽  
Well Log ◽  
Complementary Information ◽  
Reservoir Properties ◽  
Reservoir Rocks ◽  
Controlled Source ◽  
Fluid Properties

Reservoir characterization objectives are to understand the reservoir rocks and fluids through accurate measurements to help asset teams develop optimal production decisions. Within this framework, we develop a new workflow to perform petrophysical joint inversion (PJI) of seismic and controlled-source electromagnetic (CSEM) data to resolve for reservoirs properties. Our workflow uses the complementary information contained in seismic, CSEM, and well-log data to improve the reservoir’s description drastically. The advent of CSEM, measuring resistivity, brought the possibility of integrating multiphysics data within the characterization workflow, and it has the potential to significantly enhance the accuracy at which reservoir properties and saturation, in particular, can be determined. We determine the power of PJI in the retrieval of reservoir parameters through a case study, based on a deepwater oil field offshore Brazil in the Sergipe-Alagoas Basin, to augment the certainty with which reservoir lithology and fluid properties are constrained.

scholarly journals Estimation of reservoir properties from seismic data by smooth neural networks

Geophysics ◽  
2003 ◽  
Vol 68 (6) ◽  
pp. 1969-1983 ◽  
Author(s):  
M. M. Saggaf ◽  
M. Nafi Toksöz ◽  
H. M. Mustafa
Keyword(s):  
Seismic Data ◽  
Reservoir Characterization ◽  
Back Propagation ◽  
Reservoir Rock ◽  
Seismic Survey ◽  
Rock Properties ◽  
Reservoir Properties ◽  
Network Parameters ◽  
Generalization Problem ◽  
Validation Tests

The performance of traditional back‐propagation networks for reservoir characterization in production settings has been inconsistent due to their nonmonotonous generalization, which necessitates extensive tweaking of their parameters in order to achieve satisfactory results and avoid overfitting the data. This makes the accuracy of these networks sensitive to the selection of the network parameters. We present an approach to estimate the reservoir rock properties from seismic data through the use of regularized back propagation networks that have inherent smoothness characteristics. This approach alleviates the nonmonotonous generalization problem associated with traditional networks and helps to avoid overfitting the data. We apply the approach to a 3D seismic survey in the Shedgum area of Ghawar field, Saudi Arabia, to estimate the reservoir porosity distribution of the Arab‐D zone, and we contrast the accuracy of our approach with that of traditional back‐propagation networks through cross‐validation tests. The results of these tests indicate that the accuracy of our approach remains consistent as the network parameters are varied, whereas that of the traditional network deteriorates as soon as deviations from the optimal parameters occur. The approach we present thus leads to more robust estimates of the reservoir properties and requires little or no tweaking of the network parameters to achieve optimal results.

NEW LEARNING AUTOMATA BASED ALGORITHMS FOR ADAPTATION OF BACKPROPAGATION ALGORITHM PARAMETERS

2002 ◽  
Vol 12 (01) ◽  
pp. 45-67 ◽  
Author(s):  
M. R. MEYBODI ◽  
H. BEIGY
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Learning Automata ◽  
Feedforward Neural Networks ◽  
Bp Algorithm ◽  
Backpropagation Algorithm ◽  
New Learning ◽  
The Neural Networks ◽  
Factor Α ◽  
High Possibility

One popular learning algorithm for feedforward neural networks is the backpropagation (BP) algorithm which includes parameters, learning rate (η), momentum factor (α) and steepness parameter (λ). The appropriate selections of these parameters have large effects on the convergence of the algorithm. Many techniques that adaptively adjust these parameters have been developed to increase speed of convergence. In this paper, we shall present several classes of learning automata based solutions to the problem of adaptation of BP algorithm parameters. By interconnection of learning automata to the feedforward neural networks, we use learning automata scheme for adjusting the parameters η, α, and λ based on the observation of random response of the neural networks. One of the important aspects of the proposed schemes is its ability to escape from local minima with high possibility during the training period. The feasibility of proposed methods is shown through simulations on several problems.

Neural Networks Predictive Controller Using an Adaptive Control Rate

2016 ◽  
pp. 614-633 ◽  
Author(s):  
Ahmed Mnasser ◽  
Faouzi Bouani ◽  
Mekki Ksouri
Keyword(s):  
Neural Networks ◽  
Gradient Method ◽  
Feedforward Neural Networks ◽  
Neural Model ◽  
Asymptotic Convergence ◽  
Marquardt Method ◽  
Predictive Controller ◽  
The Neural Networks ◽  
The Stability ◽  
Unknown Nonlinear Dynamics

A model predictive control design for nonlinear systems based on artificial neural networks is discussed. The Feedforward neural networks are used to describe the unknown nonlinear dynamics of the real system. The backpropagation algorithm is used, offline, to train the neural networks model. The optimal control actions are computed by solving a nonconvex optimization problem with the gradient method. In gradient method, the steepest descent is a sensible factor for convergence. Then, an adaptive variable control rate based on Lyapunov function candidate and asymptotic convergence of the predictive controller are proposed. The stability of the closed loop system based on the neural model is proved. In order to demonstrate the robustness of the proposed predictive controller under set-point and load disturbance, a simulation example is considered. A comparison of the control performance achieved with a Levenberg-Marquardt method is also provided to illustrate the effectiveness of the proposed controller.

Analysis of Generalization for a New Kind of Neural Network

2013 ◽  
Vol 760-762 ◽  
pp. 2023-2027
Author(s):  
Dai Yuan Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Feedforward Neural Networks ◽  
Weight Functions ◽  
Good Property ◽  
High Learning ◽  
B Spline ◽  
Learning Speed ◽  
The Neural Networks ◽  
Approach Zero

To describe the performance of a new kind of approximation algorithm using B-Spline weight functions on feedforward neural networks, the analysis of generalization is proposed in this paper. The neural networks architecture is very simple and the number of weight functions is independent of the number of patterns. Three important theorems are proved, which mean that, by increasing the density of the knots, the upper bound of the networks error can be made to approach zero. The results show that the new algorithm has good property of generalization and high learning speed.

Neural Networks Predictive Controller Using an Adaptive Control Rate

2014 ◽  
Vol 3 (3) ◽  
pp. 127-147 ◽  
Author(s):  
Ahmed Mnasser ◽  
Faouzi Bouani ◽  
Mekki Ksouri
Keyword(s):  
Neural Networks ◽  
Gradient Method ◽  
Feedforward Neural Networks ◽  
Neural Model ◽  
Closed Loop System ◽  
Variable Control ◽  
Predictive Controller ◽  
The Neural Networks ◽  
The Stability ◽  
Unknown Nonlinear Dynamics

A model predictive control design for nonlinear systems based on artificial neural networks is discussed. The Feedforward neural networks are used to describe the unknown nonlinear dynamics of the real system. The backpropagation algorithm is used, offline, to train the neural networks model. The optimal control actions are computed by solving a nonconvex optimization problem with the gradient method. In gradient method, the steepest descent is a sensible factor for convergence. Then, an adaptive variable control rate based on Lyapunov function candidate and asymptotic convergence of the predictive controller are proposed. The stability of the closed loop system based on the neural model is proved. In order to demonstrate the robustness of the proposed predictive controller under set-point and load disturbance, a simulation example is considered. A comparison of the control performance achieved with a Levenberg-Marquardt method is also provided to illustrate the effectiveness of the proposed controller.

Sign in / Sign up

Export Citation Format

Share Document