Production History Matching and Forecasting of Shale Assets Using Pattern Recognition

Esmaili, Soodabeh

doi:10.33915/etd.3651

Cited by 5 publications

(4 citation statements)

References 27 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The smart proxy model is extended to another reservoir simulation application, namely history matching. Soodabeh used the smart proxy technique to predict the future well/reservoir performance and to analyze the behavior of the newly drilled wells in a shale reservoir[49]. She performed a history match for every single well with very high accuracy.…”

mentioning

confidence: 99%

A data-driven smart proxy model for a comprehensive reservoir simulation

Alenezi

Mohaghegh

2016

2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT)

View full text Add to dashboard Cite

The preferred common tool to estimate the performance of oil and gas fields under different production scenarios is numerical reservoir simulation. A comprehensive numerical reservoir model has tens of millions of grid blocks. The massive potential of existing numerical reservoir simulation models have gone unrealized because they are computationally expensive and time-consuming. Therefore, an effective alternative tool is required for fast and reliable decision making. To reduce the required computational time, proxy models have been developed. Traditional proxy models are either statistical or reduced-order models (ROM). They were developed to substitute complex numerical simulation with producing a representation of the system at a lower computational cost. However, there are shortcomings associated with these approaches when applied to complex systems. In this study, a novel proxy-model approach is presented in order to overcome the computational size and the traditional proxy-model challenges. The smart proxy model presented is based on artificial intelligence and data-mining techniques. The objective of this study was to develop two types of smart proxy models at each grid block. The first smart proxy model was generated to identify dynamic reservoir properties (pressure and saturations). The other proxy model was created to determine the production profile of a well. The two smart proxy models can be coupled in order to examine field production performance under different operational and geological realization. The field of study in this work is the SACROC unit. It is a depleted oil field located in Scurry County, Texas. The production history of this field began back in the late 1940s. Based on the long period of production and the different drive mechanisms employed throughout the fields exploitation, its performance history was divided into three phases in this study. Each phase was investigated and smart proxy models were applied to each. ful children, Jana, Naif and Reelam, who provide unending inspiration. Finally, I extend my thanks and gratitude to Saudi Aramco for giving me the opportunity and financial support to pursue a PhD degree.

show abstract

mentioning

confidence: 99%

A data-driven smart proxy model for a comprehensive reservoir simulation

Alenezi

Mohaghegh

2016

2016 4th Saudi International Conference on Information Technology (Big Data Analysis) (KACSTIT)

View full text Add to dashboard Cite

show abstract

“…Reservoir characteristics of each layer including matrix porosity, matrix permeability, pay thickness, net to gross (NTG), initial water saturation and total organic content (TOC) of each well was given by the operator. In order to have consistent values for each well an average of reservoir properties based on well completion zone was calculated (Esmaili, 2013).…”

Section: Methodsmentioning

confidence: 99%

“…For the most of gas and oil wells, the production analysis should be applied. The diffusivity equation which is a combination of continuity equation, flux equation (Darcy's Law) and an equation of state are the origin of all these analyses methods [Esmaili, 2013]. Production analysis for shale have been developed over the last 50 years based on models for gas production from coal beds and applied initially to low pressure fractured reservoirs [Walton, 2012].…”

Section: Literature Reviewmentioning

confidence: 99%

Estimating Ultimate Recovery in Shale Wells Based on Facts

Javadi¹

View full text Add to dashboard Cite

Estimating Ultimate Recovery for Shale Based on Facts Faegheh Javadi Natural gas, as one of the nation's major energy sources plays a vital role in the US energy mix. In recent years, the production from Shale has focused much attention on this source of hydrocarbon. As an essential step for the production planning, natural gas professionals estimate production and ultimate recovery (EUR) throughout the life of wells. The fluid production rate (q) usually varies as a function of rock properties, well, and completion design parameters. The variation associated with these parameters is a source of uncertainty in estimating the long term production for unconventional reservoirs. A number of methodologies have been suggested to estimate the long term production of shale wells. Decline curve analysis is the most widely used methodology in the estimation of the future production profile (Arps, 1945). However, its results have been determined to be over optimistic (Fanchi et al. 2013 and Dinh et al. 2014). Discrepancies between actual and estimated production values by Arps decline curves have been observed. This is dominant in low permeability reservoirs characterized by production over-estimation that is a consequence of large values of hyperbolic component (b-values higher than 1). A combination of Arps hyperbolic (in early time) and exponential decline (in later time) is employed to overcome this deficiency (production over estimation). This combination of Arps declines curves are referred to as Combined Decline Curves (CDC). The resulting estimation of EUR is quite conservative such that it provides lower EUR values than Power Law Exponential and the Stretched Exponential Decline Curve. The major objective of this research is to condition the results of the CDC-EUR of shale wells to rock properties, well characteristics, and completion design parameters in a given shale asset. The first step of this study is CDC-EUR estimation using Arps combined decline curves. In order to have a more accurate (conservative) estimation, the hyperbolic curve will be switched to exponential decline during later time in the well's life. Then, artificial intelligence will be employed to condition the CDC-EUR to rock properties, well characteristics, and completion design parameters. The major rock properties that will be studied in this research as input parameters include porosity, total organic carbon, net thickness, and water saturation. Moreover, the effect of several design parameters, such as well trajectories, completion, and hydraulic fracturing variables on CDC-EUR will be investigated. This model will help natural gas professionals to have a better understanding of the effect of rock properties and design parameters on future gas production of shale.

show abstract

“…In the study performed by Esmaili (Esmaili 2013) an AI-based model was developed for a Marcellus Shale asset which includes 135 horizontal wells from 43 pads. The full field AI-based shale model was used to predict the well/reservoir performance and also forecast the behavior of the new wells.…”

Section: Application Of Neural Network In Petroleum Engineeringmentioning

confidence: 99%

Developing a Grid-Based Surrogate Reservoir Model Using Artificial Intelligence

Amini¹

View full text Add to dashboard Cite

Developing A Grid-Based Surrogate Reservoir Model Using Artificial Intelligence Shohreh Amini Reservoir simulation models are the major tools for studying fluid flow behavior in hydrocarbon reservoirs. They are now being used extensively in performing any kind of studies related to fluid production/injection in hydrocarbon bearing formations. Reservoir simulation models are constructed based on geological models, which are developed by integrating data from geology, geophysics, and petro-physics. This data comes from observation, measurements, and interpretations. Integration of maximum data from geology, geophysics, and petro-physics, contributes to building geologically complex and more realistic models. 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 (such as uncertainty analysis), a massive amount of time is needed to complete all the required simulation runs. On many occasions, the sheer number of required simulation runs, makes the accomplishment of a project's objectives impractical. In order to address this problem, several efforts have been made to develop proxy models which can be used as a substitute for complex reservoir simulation models. These proxy models aim to reproduce the outputs of the reservoir models in a very short amount of time. In this study, a Grid-Based Surrogate Reservoir Model (SRM) is developed to be used as a proxy model for a complex reservoir simulation model. SRM is a customized model based on Artificial Intelligent (AI) and Data Mining (DM) techniques and consists of several neural networks, which are trained, calibrated, and validated before being used online. In this research, a numerical reservoir simulation model is developed and history matched for a CO2 sequestration project, which was performed in Otway basin, Australia where CO2 is injected into a depleted gas reservoir through one injection well. In order to develop SRM, a handful of appropriate simulation scenarios for different operational constraints and/or geological realizations are designed and run. A comprehensive spatio-temporal data set is generated by integrating data from the conducted simulation runs and it is used to train, calibrate, and verify several neural networks which are further combined to make the surrogate model. This model is able to generate pressure, saturation, and CO2 mole fraction at each grid block of the reservoir with a significantly less computational effort compared to the numerical reservoir simulation model.

show abstract

Production History Matching and Forecasting of Shale Assets Using Pattern Recognition

Cited by 5 publications

References 27 publications

A data-driven smart proxy model for a comprehensive reservoir simulation

A data-driven smart proxy model for a comprehensive reservoir simulation

Estimating Ultimate Recovery in Shale Wells Based on Facts

Developing a Grid-Based Surrogate Reservoir Model Using Artificial Intelligence

Contact Info

Product

Resources

About