A Neurosimulation Tool for Predicting Performance in Enhanced Coalbed Methane 
and CO2 Sequestration Projects

Görücü, Fatma; Ertekin, Turgay; Bromhal, Grant; Smith, Duane H.; Sams, W.; Jikich, Sinisha A.

doi:10.2523/97164-ms

Cited by 3 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…for gas-condensate reservoir exploitation. Odusote et al 5 presented a screening tool-box for recovery of coalbed methane by CO 2 injection, and Gorucu et al 6 characterized carbon dioxide sequestration and coalbed methane projects.…”

Section: Application Of Neuro-simulationmentioning

confidence: 99%

A New Screening Tool for Improved Oil Recovery Methods Using Artificial Neural Networks

Parada

Ertekin

2012

SPE Western Regional Meeting

View full text Add to dashboard Cite

In more recent years, improved oil recovery (IOR) techniques are applied to reservoirs even before their natural energy drive is exhausted by primary depletion. Screening criteria for IOR methods are used to select the appropriate recovery technique in view of the reservoir characteristics. However, further reservoir appraisal is necessary after the applicable recovery technique is identified. The methodology proposed in this paper allows the preliminary evaluation of reservoir performance in parallel with the IOR screening process.In this study, artificial neural network (ANN) methodology is used to build a high-performance neuro-simulation tool for screening IOR methods such as waterflooding, steam injection and miscible injection of CO 2 and N 2 . This innovative tool integrates the field development plan into the screening method. The reservoir characteristics are evaluated together with a proposed production scenario to assess the most suitable recovery process and, at the same time, the reservoir performance is forecasted by providing the estimated oil production curve.The screening toolbox consists of proxy models that implement a multilayer cascade feedforward back propagation artificial network algorithm. The proxy models work for a diverse range of reservoir fluids and rock properties. The field development plan is featured in the tool by different well patterns, well spacing and well operating conditions. The ANN screening tool predicts oil production rate, cumulative oil production and estimated production time. The tool also provides the flexibility to compare the hydrocarbon production for different sets of inputs, which facilitates comparison of various depletion strategies in the screening process as well.The results of this study show that the networks are able to recognize the strong correlation between the displacement mechanism and the reservoir characteristics as they effectively forecast hydrocarbon production for different reservoirs. The tool presents a new means to design an efficient and feasible IOR project by using artificial intelligence. The proposed tool facilitates the appraisal of diverse field development strategies for oil reservoirs and allows comparison of reservoir performance under diverse production schemes.

show abstract

Section: Application Of Neuro-simulationmentioning

confidence: 99%

A New Screening Tool for Improved Oil Recovery Methods Using Artificial Neural Networks

Parada

Ertekin

2012

SPE Western Regional Meeting

View full text Add to dashboard Cite

show abstract

“…In recent years the attention given to the use of unmineable coal seams for sequestration purposes has progressively increased because the simultaneous recovery of natural gas helps to decrease the cost of the CO 2 sequestration project. [4] This paper shows the application of ANN methodology to predict the methane recovered after the sequestration of certain amount of CO 2 . ANN methodology is highly dependent on the input parameters, so after reading different articles in the literature, a total of 6 system properties and design parameters are included in the artificial neural network (ANN) architecture as the input.…”

Section: Introductionmentioning

confidence: 99%

“…CH 4 saturation change during CO 2 injection RBF Developed BP model (from MATLAB TM Software) Developed RBF model (from MATLAB TM Software) Predicted CH4 recovered with the BP model versus the simulation data (Training) Predicted CH 4 recovered with the BP model versus the simulation data (Validation) Predicted CH 4 recovered with the BP model versus the simulation data (Testing) Predicted CO 2 injected with the BP model versus the simulation data (Training) Predicted CO 2 injected with the BP model versus the simulation data (Validation) Predicted CO 2 injected with the BP model versus the simulation data (Testing) Predicted CH 4 recovered with the RBF model versus the simulation data Predicted CO 2 injected with the RBF model versus the simulation data…”

mentioning

confidence: 99%

Implementing Simulation and Artificial Intelligence Tools To Optimize the Performance of the CO2 Sequestration in Coalbed Methane Reservoirs

Mohammadpoor

Firouz

Torabi

2012

Carbon Management Technology Conference

View full text Add to dashboard Cite

CO 2 capture and sequestration is inevitable. The concentration of the CO 2 in the atmosphere is increasing continuously which will cause global warming among other consequences. Among storage options, the underground storage in depleted oil and gas reservoirs and unminable coals are considered the most economical storage options. On the other hand, natural gas consumption, which is considered to be a clean fuel, has increased significantly during the past years. Therefore seeking for new unconventional energy resources, especially gas seems to be inevitable. This goal is followed not only because of economical benefits but also because of environmental issues we are encountering these days. The purpose of this study is to develop an Artificial Neural network (ANN) tool to predict the important performance indicators such as methane recovered and CO 2 injected, which are critical in CO2 storage projects in coal seams. We have combined the simulation method with artificial intelligence tools to predict the complex behavior of coal bed methane (CBM) reservoirs.In the first step a simulation is done using CMG software. A dual porosity model, which accounts for the optimum conditions during CO 2 sequestration and consequently the optimum methane recovery from coal bed reservoirs was developed. Then the data extracted from the simulated CBM reservoir was employed to train the ANN model. Different parameters related to the coal seam such as porosity, permeability, initial pressure, thickness, temperature and initial water saturation are considered as the input for the network. The outputs are the CO 2 injected and the recovered methane, which show the performance of the CO 2 injection project. The Back-Propagation learning algorithm was used and different transfer functions and numbers of hidden layers were tried to find the best model with the least error. The tested neural network predictions were plotted versus the real data available and also different error analyses were carried out to prove the accuracy of the model. The R-Squared for the predicted values for the CO 2 injected and the recovered methane were 0.92 and 0.94; the average percent arithmetic deviations were 4.8% and 4.5% respectively.

show abstract

Application of Machine Learning and Artificial Intelligence in Proxy Modeling for Fluid Flow in Porous Media

Amini

Mohaghegh

2019

Fluids

View full text Add to dashboard Cite

Reservoir simulation models are the major tools for studying fluid flow behavior in hydrocarbon reservoirs. These models are constructed based on geological models, which are developed by integrating data from geology, geophysics, and petro-physics. As the complexity of a reservoir simulation model increases, so does the computation time. Therefore, to perform any comprehensive study which involves thousands of simulation runs, a very long period of time is required. Several efforts have been made to develop proxy models that can be used as a substitute for complex reservoir simulation models. These proxy models aim at generating the outputs of the numerical fluid flow models in a very short period of time. This research is focused on developing a proxy fluid flow model using artificial intelligence and machine learning techniques. In this work, the proxy model is developed for a real case CO2 sequestration project in which the objective is to evaluate the dynamic reservoir parameters (pressure, saturation, and CO2 mole fraction) under various CO2 injection scenarios. The data-driven model that is developed is able to generate pressure, saturation, and CO2 mole fraction throughout the reservoir with significantly less computational effort and considerably shorter period of time compared to the numerical reservoir simulation model.

show abstract

A Neurosimulation Tool for Predicting Performance in Enhanced Coalbed Methane and CO2 Sequestration Projects

Cited by 3 publications

References 4 publications

A New Screening Tool for Improved Oil Recovery Methods Using Artificial Neural Networks

A New Screening Tool for Improved Oil Recovery Methods Using Artificial Neural Networks

Implementing Simulation and Artificial Intelligence Tools To Optimize the Performance of the CO2 Sequestration in Coalbed Methane Reservoirs

Application of Machine Learning and Artificial Intelligence in Proxy Modeling for Fluid Flow in Porous Media

Contact Info

Product

Resources

About