Prescriptive Analytics for Completion Optimization in Unconventional Resources

Shirangi, Mehrdad G.; Oruganti, Yagna Deepika; Wilson, Thomas A.; Furlong, Edward T.; Winter, E. L.; Martin, Joel W.; Yancy, Robert

doi:10.2118/195311-ms

Cited by 5 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several directions to investigate in future. Application of CLFD optimization to geothermal reservoir, groundwater remediation (Bayer et al, 2008;Ghorbanidehno et al, 2017), and CO 2 -EOR problems, and unconventional resources (Shirangi et al, 2019) should also be investigated. In this work, a fixed project life was specified in the optimization step of CLFD and the expected NPV was optimized.…”

Section: Discussionmentioning

confidence: 99%

Closed-loop field development with multipoint geostatistics and statistical performance assessment

Shirangi

2019

Journal of Computational Physics

View full text Add to dashboard Cite

Closed-loop field development (CLFD) optimization is a comprehensive framework for optimal development of subsurface resources. CLFD involves three major steps: 1) optimization of full development plan based on current set of models, 2) drilling new wells and collecting new spatial and temporal (production) data, 3) model calibration based on all data. This process is repeated until the optimal number of wells is drilled. This work introduces a new CLFD implementation for complex systems described by multipoint geostatistics (MPS). Model calibration is accomplished in two steps: conditioning to spatial data by a geostatistical simulation method, and conditioning to production data by optimization-based PCA. A statistical procedure (TruMAP) is presented to assess the performance of CLFD. For performance assessment by TruMAP, the methodology is applied to an oil reservoir example for 25 different true-model cases. Application of a single-step of CLFD, improved the true NPV in 64%-80% of cases. The full CLFD procedure (with three steps) improved the true NPV in 96% of cases, with an average improvement of 37%. These results indicate the effectiveness of performing multiple steps of closed-loop optimization. This massive computational experiment involved about 9.5 million reservoir simulation runs that took about 320,000 CPU hours.

show abstract

Section: Discussionmentioning

confidence: 99%

Closed-loop field development with multipoint geostatistics and statistical performance assessment

Shirangi

2019

Journal of Computational Physics

View full text Add to dashboard Cite

show abstract

Completion Design Optimization for Unconventional Wells Using Large Scale Computational Science

Cotrell

Hoeink

Odusina

et al. 2019

Day 2 Wed, October 23, 2019

View full text Add to dashboard Cite

In the current state of the oil and gas industry, unconventional resources are a significant source of the total production output. Unconventional wells remain profitable at various price points, because initial stimulation treatments can be tailored to changing market conditions, reflecting completion costs and (estimated) hydrocarbon prices. The same holds true for re-stimulation of already producing wells. Stimulation treatment "opens" up the subsurface to ultimately allow for better drainage of the reservoir hydrocarbons. The primary stimulation treatment currently in use is hydraulic fracturing, in which the wellbore is broken up into multiple stages, and highly pressurized fluid (oftentimes water) is pumped into each stage of the wellbore. This causes fractures to propagate away from the wellbore, which in turn enhances the local reservoir permeability and allows for economical production. Historically, the number of stages, and clusters per stage, for hydraulic stimulation has been based on wellbore horizontal length (e.g., 200 ft or 400 ft), or much valued previous experience in the same or similar area, as well as other investment considerations. Over time, a strong tendency has developed to place stages and clusters closer together to improve production. However, it is reasonable to assume that there will be a point beyond which adding another stage becomes more expensive than what is gained by increased production revenue from the greater stage count (i.e., less profitable depending on the time of investment). This scenario frames a classic optimization problem which is solved using Monte Carlo methods. Results show that optimal stimulation treatment configurations are robust for many objective functions related to the fracturing process (e.g., propped length and propped height). However, we find that objective functions related to production, production revenue, and profit often provide different optimum treatment configurations, and that those optima shift with respect to the considered timeframe. Because business decisions will ultimately be based on profit decisions over a given time span, we propose utilizing the appropriate objective function together with an integrated modeling approach such as presented here.

show abstract

Data Driven Workflow to Optimize Eagle Ford Unconventional Asset Development Plan Based on Multidisciplinary Data

Abdelfattah

Nasir

Yang

et al. 2021

SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

Unconventional reservoir development is a multidisciplinary challenge due to complicated physical system, including but not limited to complicated flow mechanism, multiple porosity system, heterogeneous subsurface rock and minerals, well interference, and fluid-rock interaction. With enough well data, physics-based models can be supplemented with data driven methods to describe a reservoir system and accurately predict well performance. This study uses a data driven approach to tackle the field development problem in the Eagle Ford Shale. A large amount of data spanning major oil and gas disciplines was collected and interrogated from around 300 wells in the area of interest. The data driven workflow consists of: Descriptive model to regress on existing wells with the selected well features and provide insight on feature importance, Predictive model to forecast well performance, and Subject matter expert driven prescriptive model to optimize future well design for well economics improvement. To evaluate initial well economics, 365 consecutive days of production oil per CAPEX dollar spent (bbl/$) was setup as the objective function. After a careful model selection, Random Forest (RF) shows the best accuracy with the given dataset, and Differential Evolution (DE) was used for optimization. Using recursive feature elimination (RFE), the final master dataset was reduced to 50 parameters to feed into the machine learning model. After hyperparameter tuning, reasonable regression accuracy was achieved by the Random Forest algorithm, where correlation coefficient (R2) for the training and test dataset was 0.83, and mean absolute error percentage (MAEP) was less than 20%. The model also reveals that the well performance is highly dependent on a good combination of variables spanning geology, drilling, completions, production and reservoir. Completion year has one of the highest feature importance, indicating the improvement of operation and design efficiency and the fluctuation of service cost. Moreover, lateral rate of penetration (ROP) was always amongst the top two important parameters most likely because it impacts the drilling cost significantly. With subject matter experts’ (SME) input, optimization using the regression model was performed in an iterative manner with the chosen parameters and using reasonable upper and lower bounds. Compared to the best existing wells in the vicinity, the optimized well design shows a potential improvement on bbl/$ by approximately 38%. This paper introduces an integrated data driven solution to optimize unconventional development strategy. Comparing to conventional analytical and numerical methods, machine learning model is able to handle large multidimensional dataset and provide actionable recommendations with a much faster turnaround. In the course of field development, the model accuracy can be dynamically improved by including more data collected from new wells.

show abstract

Prescriptive Analytics for Completion Optimization in Unconventional Resources

Cited by 5 publications

References 23 publications

Closed-loop field development with multipoint geostatistics and statistical performance assessment

Closed-loop field development with multipoint geostatistics and statistical performance assessment

Completion Design Optimization for Unconventional Wells Using Large Scale Computational Science

Data Driven Workflow to Optimize Eagle Ford Unconventional Asset Development Plan Based on Multidisciplinary Data

Contact Info

Product

Resources

About