A Case History: Evaluating Well Completions in the Eagle Ford Shale Using a Data-Driven Approach

2015 ◽  
Author(s):  
Amir M. Nejad ◽  
Stanislav Sheludko ◽  
Robert F. Shelley ◽  
Trey Hodgson ◽  
Riley McFall
Keyword(s):  
Neural Network ◽  
Neural Network Model ◽  
Oil And Gas ◽  
Gas Production ◽  
Data Driven ◽  
Eagle Ford Shale ◽  
Eagle Ford ◽  
Oil And Gas Production ◽  
Treatment Designs ◽  
Different Parts

Abstract Unconventional shale resources are key hydrocarbon sources, gaining importance and popularity as hydrocarbon reservoirs both in the United States and internationally. Horizontal wellbores and multiple transverse hydraulic fracturing are instrumental factors for economical production from shale assets. Hydraulic fracturing typically represents a major component of total well completion costs, and many efforts have been made to study and investigate different strategies to improve well production and reduce costs. The focus of this paper is completion effectiveness evaluation in different parts of the Eagle Ford Shale Formation, and our objective is to identify appropriate completion strategies in the field. A data-driven neural network model is trained on the database comprised of multiple operators' well data. In this model, drilling and mud data are used as indicators for geology and reservoir-related parameters such as pressure, fluid saturation and permeability. Additionally, completion- and fracture-related parameters are also used as model inputs. Because wells are pressure managed differently, normalized oil and gas production is used as a model output. Thousands of neural networks are trained using genetic algorithm in order to fully evaluate hidden correlations within the database. This results in selection of a neural network that is able to understand reservoir, completion and frac differences between wells and identify how to improve future completion/stimulation designs. The final neural network model is successfully developed and tested on two separate data sets located in different parts of the Eagle Ford Shale oil window. Further, an additional test data set comprised of eight wells from a third field location is used to validate the predictive usefulness of the data-driven model. Under-producing wells were also identified by the model and new fracture designs were recommended to improve well productivity. This paper will be useful for understanding the effects of completion and fracture treatment designs on well productivity in the Eagle Ford. This information will help operators select more effective treatment designs, which can reduce operational costs associated with completion/fracturing and can improve oil and gas production.

QUANTIFYING FRESH WATER AND PROPPANT REQUIREMENTS FOR OIL AND GAS PRODUCTION FROM THE EAGLE FORD GROUP, GULF COAST, TEXAS

2018 ◽  
Author(s):  
Nicholas J. Gianoutsos ◽  
◽  
Seth S. Haines ◽  
Brian A. Varela ◽  
Katherine J. Whidden
Keyword(s):  
Fresh Water ◽  
Oil And Gas ◽  
Gulf Coast ◽  
Gas Production ◽  
Eagle Ford ◽  
Oil And Gas Production

scholarly journals Experimental Investigation of Inhibitive Drilling Fluids Performance: Case Studies from United States Shale Basins

Energies ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 5142
Author(s):  
Nabe Konate ◽  
Saeed Salehi
Keyword(s):  
Oil And Gas ◽  
Drilling Fluid ◽  
Gas Production ◽  
Drilling Fluids ◽  
Eagle Ford Shale ◽  
Oil And Gas Production ◽  
Shale Formations ◽  
Drilling Performance ◽  
Marine Shale ◽  
Fluid Systems

Shale formations are attractive prospects due to their potential in oil and gas production. Some of the largest shale formations in the mainland US, such as the Tuscaloosa Marine Shale (TMS), have reserves estimated to be around 7 billion barrels. Despite their huge potential, shale formations present major concerns for drilling operators. These prospects have unique challenges because of all their alteration and incompatibility issues with drilling and completion fluids. Most shale formations undergo numerous chemical and physical alterations, making their interaction with the drilling and completion fluid systems very complex to understand. In this study, a high-pressure, high-temperature (HPHT) drilling simulator was used to mimic real time drilling operations to investigate the performance of inhibitive drilling fluid systems in two major shale formations (Eagle Ford Shale and Tuscaloosa Marine Shale). A series of drilling experiments using the drilling simulator and clay swelling tests were conducted to evaluate the drilling performance of the KCl drilling fluid and cesium formate brine systems and their effectiveness in minimizing drilling concerns. Cylindrical cores were used to mimic vertical wellbores. It was found that the inhibitive muds systems (KCl and cesium formate) provided improved drilling performance compared to conventional fluid systems. Among the inhibitive systems, the cesium formate brine showed the best drilling performances due to its low swelling rate and improved drilling performance.

scholarly journals Improving the energy efficiency of oil production using identification and prediction of operating modes of production wells based on data analysis methods, machine learning and neural networks

2019 ◽  
Vol 124 ◽  
pp. 05031 ◽  
Author(s):  
A.M. Sagdatullin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Control System ◽  
Oil And Gas ◽  
Gas Production ◽  
Operating Conditions ◽  
Identification System ◽  
Oil And Gas Production ◽  
The Neural Network ◽  
And Control

Currently, there is a need to improve the systems and control of pumping equipment in the oil and gas production and oil and gas transport industries. Therefore, an adaptive neural network control system for an electric drive of a production well was developed. The task of expanding the functional capabilities of asynchronous electric motors control of the oil and gas production system using the methods of neural networks is solved. We have developed software modules of the well drive control system based on the neural network, an identification system, and a scheme to adapt the control processes to changing load parameters, that is, to dynamic load, to implement the entire system for real-time control of the highspeed process. In this paper, based on a model of an identification block that includes a multilayered neural network of direct propagation, the control of the well system was implemented. The neural network of the proposed system was trained on the basis of the error back-propagation algorithm, and the identification unit works as a forecaster of system operation modes based on the error prediction. In the initial stage of the model adaptation, some fluctuations of the torque are observed at the output of the neural network, which is associated with new operating conditions and underestimated level of learning. However, the identification object and control system is able to maintain an error at minimum values and adapt the control system to a new conditions, which confirms the reliability of the proposed scheme.

Using Neural Network Predictive Control for Riser-Slugging Suppression

2009 ◽  
Vol 4 (4) ◽  
Author(s):  
Reza Eslamloueyan ◽  
Elham Hosseinzadeh
Keyword(s):  
Neural Network ◽  
Control System ◽  
Predictive Control ◽  
Oil And Gas ◽  
Neural Model ◽  
Nonlinear Process ◽  
Economic Benefits ◽  
Gas Production ◽  
Ann Model ◽  
Oil And Gas Production

Riser-slugging is a flow regime that can occur in multiphase pipeline-riser systems, and is characterized by severe flow and pressure oscillations. Reducing undesired slugging effects can have great economic benefits. Recently, control methods have been proposed to conquer slugging flow problems in pipeline risers. The advantages of using a control system are that it can be installed on existing oil and gas production facilities with no need for expensive equipment and no significant pressure drop is imposed to the system.In this work, a predictive control system based on Neural Network (NN) model of process is developed for handling and suppressing riser-slugging. An ANN model of the plant is used to predict future response of the nonlinear process. Storkaas dynamic model (Storkaas and Skogestad,2002) is employed for the process simulation. Comparing the results of this research to that of others, indicates that the proposed neural model predictive controller makes a significant improvement in the setpoint tracking especially for higher step change in the setpoint value.

scholarly journals Comparing Permitted Emissions to Atmospheric Observations of Hydrocarbons in the Eagle Ford Shale Suggests Permit Violations

Energies ◽  
2021 ◽  
Vol 14 (3) ◽  
pp. 780
Author(s):  
Joel Holliman ◽  
Gunnar W. Schade
Keyword(s):  
Oil And Gas ◽  
Gas Production ◽  
Eagle Ford Shale ◽  
Oil And Gas Development ◽  
Eagle Ford ◽  
South Central ◽  
Atmospheric Observations ◽  
Abandoned Wells ◽  
Oil And Gas Operations ◽  
Using Data

The recent decade’s rapid unconventional oil and gas development in the Eagle Ford of south-central Texas has caused increased hydrocarbon emissions, which we have previously analyzed using data from a Texas Commission on Environmental Quality air quality monitoring station located downwind of the shale area. Here, we expand our previous top-down emissions estimate and compare it to an estimated regional emissions maximum based on (i) individual facility permits for volatile organic compound (VOC) emissions, (ii) reported point source emissions of VOCs, (iii) traffic-related emissions, and (iv) upset emissions. This largely permit-based emissions estimate accounted, on average, for 86% of the median calculated emissions of C3-C6-hydrocarbons at the monitor. Since the measurement-based emissions encompass a smaller section of the shale than the calculated maximum permitted emissions, this strongly suggests that the actual emissions from oil and gas operations in this part of the Eagle Ford exceeded their permitted allowance. Possible explanations for the discrepancy include emissions from abandoned wells and high volumes of venting versus flaring. Using other recent observations, such as large fractions of unlit flares in the Permian shale basin, we suggest that the excessive venting of raw gas is a likely explanation. States such as Texas with significant oil gas production will need to require better accounting of emissions if they are to move towards a more sustainable energy economy.

scholarly journals A Novel Multi-Input AlexNet Prediction Model for Oil and Gas Production

2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Yang Wang ◽  
Yin Lv ◽  
Dali Guo ◽  
Shu Zhang ◽  
Shixiang Jiao
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Oil And Gas ◽  
Nearest Neighbor ◽  
Gas Production ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Oil And Gas Production ◽  
Network Support ◽  
Parameter Values

In the process of oilfield development, it is important to predict the oil and gas production. The predicted value of oil production is the amount of oil that may be obtained within a certain area over a certain period. Because of the current demand for oil and gas production prediction, a prediction model using a multi-input convolutional neural network based on AlexNet is proposed in this paper. The model predicts real oilfield data and achieves good results: increasing prediction accuracy by 17.5%, 20.8%, 11.6%, 8.9%, 6.9%, and 14.9% with respect to the backpropagation neural network, support vector machine, artificial neural network, radial basis function neural network, K-nearest neighbor, and decision tree methods, respectively. It addresses the uncertainty of oil and gas production caused by the change in parameter values during the process of petroleum exploitation and has far-reaching application significance.

ASSESSING WATER AND PROPPANT USE ASSOCIATED WITH OIL AND GAS PRODUCTION IN THE EAGLE FORD GROUP, TEXAS

2019 ◽  
Author(s):  
Nicholas J. Gianoutsos ◽  
◽  
Seth S. Haines ◽  
Brian A. Varela ◽  
K.J. Whidden
Keyword(s):  
Oil And Gas ◽  
Gas Production ◽  
Eagle Ford ◽  
Oil And Gas Production

Hybrid combination genetic algorithm and controlled gradient method to train a neural network

Geophysics ◽  
2016 ◽  
Vol 81 (4) ◽  
pp. IM35-IM43 ◽  
Author(s):  
Alexander Kobrunov ◽  
Ivan Priezzhev
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Gradient Method ◽  
Oil And Gas ◽  
Petroleum Industry ◽  
Gradient Methods ◽  
Gas Production ◽  
Production Rates ◽  
Oil And Gas Production ◽  
Area Of Interest

Multivariate predictive analysis is a widely used tool in the petroleum industry in situations in which the deterministic nature of the relationship between a variable that requires prediction and a variable that is used for the purposes of such prediction is unknown or very complex. For example, to perform a sweet-spot analysis, it is necessary to predict potential oil and gas production rates on a map, using various geologic and geophysical attribute maps (porosity, density, seismic attributes, gravity, magnetic, etc.) and the initial oil and gas production rates of several control or training wells located in the area of interest. We have developed a new technology that allows for building a stable nonlinear predictive operator by using the combination of a neural network, a genetic algorithm, and a controlled gradient method. The main idea behind the proposed technology is to combine stochastic and deterministic approaches during the construction of the predictive operator at the training stage. The proposed technology avoids many disadvantages of the genetic algorithm and gradients methods, such as a high level of dependency on the initial values; the phenomenon of over-fitting (overtraining), which results in creation of an operator with unstable predictability; and a low speed of decreasing error during iteration, and, as a result, a low level of prediction quality. However, the above-mentioned combination uses the advantages of both methods and allows for finding a solution significantly closer to a global minimum for the objective function, compared to simple gradient methods, such as back propagation. The combination of these methods together with Tikhonov regularization allows for building stable predictions in spatial or/and time coordinates.

Sign in / Sign up

Export Citation Format

Share Document