Artificial Intelligence Assisted History Matching -- Proof of Concept

Shahkarami, Alireza

doi:10.33915/etd.3342

Cited by 3 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section intends to present the results for one of the wells (well # 20) for different steps of developing and applying the SRM. The results for all wells can be found in somewhere else (Shahkarami 2012). Figure 9 displays the results after the training process; the chart portrays the oil rate profile for 30 years of production comparing SRM results with the simulator outputs.…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence (AI) Assisted History Matching

Shahkarami

Mohaghegh

Gholami

et al. 2014

SPE Western North American and Rocky Mountain Joint Meeting

Self Cite

View full text Add to dashboard Cite

History matching is the process of adjusting uncertain reservoir parameters until an acceptable match with the measured production data is obtained. Complexity and insufficient knowledge of reservoir characteristics makes this process timeconsuming with high computational cost. In the recent years, many efforts mainly referred as assisted history matching have attempted to make this process faster; nevertheless, the degree of success of these techniques continues to be a subject for debate.This study aims to examine the application of a unique pattern recognition technology to improve the time and efforts required for completing a successful history matching project. The pattern recognition capabilities of Artificial Intelligence and Data Mining (AI&DM) are used to develop Surrogate Reservoir Model (SRM) for utilization as the engine to drive the history matching process. SRM is an intelligent prototype of the full-field reservoir simulation model that runs in fractions of a second. SRM is built using a handful of geological realizations.In this study, a synthetic reservoir model of a heterogeneous oilfield with 24 production wells and 30 years of production history was used as the ground truth (the subject and the goal of the history match). An SRM was created to accurately represent this reservoir model. The history matching process for this field was performed using the SRM and by tuning static data (Permeability). The result of this study demonstrates the capabilities of SRM for fast track and accurate reproduction of the numerical model results. Speed and accuracy make SRM a fast and effective tool for assisted history matching.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence (AI) Assisted History Matching

Shahkarami

Mohaghegh

Gholami

et al. 2014

SPE Western North American and Rocky Mountain Joint Meeting

Self Cite

View full text Add to dashboard Cite

show abstract

“…History matching can be done manually where an experienced professional tunes the parameters of interest to find a matching model. However, manual history matching can be time consuming and prone to human bias and error [16,17]. History matching can also be done with the help of computers, which is known as assisted or automatic history matching.…”

Section: Literature Reviewmentioning

confidence: 99%

Parallel Automatic History Matching Algorithm Using Reinforcement Learning

Alomar¹,

Williams²

2023

Energies

View full text Add to dashboard Cite

Reformulating the history matching problem from a least-square mathematical optimization problem into a Markov Decision Process introduces a method in which reinforcement learning can be utilized to solve the problem. This method provides a mechanism where an artificial deep neural network agent can interact with the reservoir simulator and find multiple different solutions to the problem. Such a formulation allows for solving the problem in parallel by launching multiple concurrent environments enabling the agent to learn simultaneously from all the environments at once, achieving significant speed up.

show abstract

“…The basic procedure is to begin with an initial parameter guess and improve it by incorporating field data in an automatic loop. The match will be evaluated between the measured and estimated data by using an objective function as mention earlier (Shahkarami, 2012).…”

Section: 4 a U T O M At E D A N D M A N U A L H I S T O Ry M At Cmentioning

confidence: 99%

“…where different combinations of modified reservoir parameters can give almost the same behavior of the actual reservoir history data (Shahkarami, 2012).…”

Section: 4 1 Introductionmentioning

confidence: 99%

Performance of the Horizontal Wells in a Naturally Fractured Carbonate Reservoir

Al-Bayati¹

View full text Add to dashboard Cite

About 60 percent of the world's proven oil reserves and 40 percent of gas reserves are trapped in carbonate reservoirs. Recovery rates are relatively low in carbonate reservoirs, and it is extremely challenging to predict due to the heterogeneous nature of these reservoirs. The majority of carbonate reservoirs contain fractures which may vary in size from millimeters to kilometers. A typical example of this type of reservoirs is oil and gas fields in the northern Iraq. These fields are almost all developed by vertical wells. This study will investigate the use of horizontal wells to enhance the productivity in one of these reservoirs. CMG software is used to simulate the Upper Qamchuqa reservoir of the Khabbaz oil field northeastern of Iraq. The Upper Qamchuqa reservoir is a subsurface anticline with a major normal fault on the eastern flank. Moreover, it mainly consists of dolomite, dolomitic limestone, limestone and marly limestone. The simulation model was validated by the history matching the production rates. Subsequently, horizontal wells were added to the model, and the optimum placement and lateral length investigated. Furthermore, the reservoir parameters that have a significant influence on the history matching and the predicted horizontal wells' performance were identified for future development of the field. The results of this study can provide a guideline for reducing the operating costs and increasing the productivity of similar naturally fractured reservoirs in the area. iii DEDICATION This thesis is dedicated to my wonderful family and special relatives for their tremendous support, love, and encouragement throughout my life.

show abstract

Artificial Intelligence Assisted History Matching -- Proof of Concept

Cited by 3 publications

References 46 publications

Artificial Intelligence (AI) Assisted History Matching

Artificial Intelligence (AI) Assisted History Matching

Parallel Automatic History Matching Algorithm Using Reinforcement Learning

Performance of the Horizontal Wells in a Naturally Fractured Carbonate Reservoir

Contact Info

Product

Resources

About