Benchmarking of Ultimate Recovery Factor Across Kuwait: Unlocking Additional Potential

Al-Ghanemi, Mohammad; Dhote, Prashant; Bora, Anup; Al-Bahar, Mohammad; Walker, Jake; Dharnidharan, Bala; Hornbrook, John W.

doi:10.2118/203422-ms

Day 2 Tue, November 10, 2020 2020

DOI: 10.2118/203422-ms

|View full text |Cite

Benchmarking of Ultimate Recovery Factor Across Kuwait: Unlocking Additional Potential

Mohammad Al-Ghanemi

Prashant Dhote

Anup Bora

et al.

Abstract: A countrywide benchmarking of ultimate recovery factor (URF) for oil reservoirs in Kuwait is presented in this study. The results of this study have been useful to support identification of long-term opportunities and have influenced the creation of conceptual development plans for some of the newly discovered prospects of the company. The Kuwait Oil Company (KOC) has a diverse inventory of petroleum reservoirs having a wide range of geologic age, depth, reservoir complexity, and development mat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2023

Publication Types

Select...

Other2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Development of a Machine Learning Technique in Conjunction with Reservoir Complexity Index to Predict Recovery Factor Using Data from 18,000 Reservoirs

Pooladi‐Darvish

Tabatabaie

Cadena

2022

Day 3 Wed, November 02, 2022

View full text Add to dashboard Cite

With increased popularity and success of Machine-Learning (ML) Techniques, there is continued interest in developing new tools while exploring the boundaries of the technique. Here we use ML techniques to identify reservoir engineering, geological and development features that influence the ultimate recovery factor in a group of reservoirs, and to develop a model that provides the relation between recovery factor (RF) and these influencing features. Furthermore, we use techniques that allow opening the "black-box model" to decipher the relation between the model output and the individual features. The overall process included: (i) Creating a subset of reservoirs from the main database that included high quality reliable data, (ii) using SME (Subject Matter Expert) knowledge to develop a list of expected influential attributes, (iii) investigating the quality and the quantity of the data within each attribute and imputing when necessary, (iv) utilizing data analysis tools to reduce the number of input variables, and (v) examining the success of the model in modelling the test data. A Reservoir Complexity Index (RCI) factor was calculated using the 6 attributes identified and input into the ML model. For a dataset of approximately 18,000 reservoirs with high confidence in the recovery factor, a model was developed with 6 numerical features. The model exhibited an accuracy of ±5% for 50% of the data (between P25 and P75) and ±10% for 80% of the data (between P10 and P90). Contrary to our expectations, inclusion of the categorical features available in the reservoirs’ database did not improve the accuracy of the model. While this work falls within a growing category of similar work, its novelty is in demonstrating the strength of XGBoost in modelling and of SHapley Additive exPlanations (SHAP) in deciphering the relative contributions for each attribute of the model. Furthermore, we provided multiple examples to demonstrate and explore both the value and the limitations, and failure of application, of the ML techniques in this kind of work. This learning is important for a cautious but robust adaptation and acceptance of ML techniques.

show abstract

Development of a Machine Learning Technique in Conjunction with Reservoir Complexity Index to Predict Recovery Factor Using Data from 18,000 Reservoirs

Pooladi‐Darvish

Tabatabaie

Cadena

2022

Day 3 Wed, November 02, 2022

View full text Add to dashboard Cite

show abstract

Hybrid Workflows- A History of Tomorrow

Moradi,

Ask,

Alessio

2023

Day 2 Wed, September 06, 2023

View full text Add to dashboard Cite

This study provides an overview of the evolution of technology in the reservoir modeling field, discussing past, present, and future advancements. It explores how technologies such as central and graphics processing units have enabled engineers to increase the number of simulation grids from 500,000 to 1 trillion cells over the last 20 years. The paper also examines data-driven workflows that have accelerated the reservoir modeling process to a few weeks, highlighting their limitations. To address these limitations, the study introduces hybrid physics-guided data-driven models as a modern digital tool for mapping potential remaining oil in brownfields. These hybrid workflows combine the strengths of both physics-guided and data-driven models, overcoming the weaknesses of each approach. Two case studies, located in the North Sea and the Middle East, are reviewed to demonstrate the effectiveness of these hybrid workflows. The comparison of the water saturation map generated by the hybrid workflow with the contact movement calculated from 4D seismic data in the North Sea field shows a strong correlation, indicating a reliable match between the two maps. In the Middle East case study, the performance of four infill wells calculated by the hybrid workflow is evaluated against the actual outcomes of post-drilling activities. The results show that, except for one of wells, the actual outcomes align with the predicted trends, falling within the P10-P90 band. The paper emphasizes the novelty and benefits of using hybrid workflows, as they enable the generation of potential remaining oil maps in a few days—a task that is challenging with conventional numerical simulation workflows. These hybrid workflows offer significant time and cost savings while maintaining high fidelity. The advanced technologies discussed in this study facilitate the implementation of practical digitalization strategies across all disciplines in the industry, ushering in a new era of data-driven innovation.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Benchmarking of Ultimate Recovery Factor Across Kuwait: Unlocking Additional Potential

Cited by 2 publications

References 4 publications

Development of a Machine Learning Technique in Conjunction with Reservoir Complexity Index to Predict Recovery Factor Using Data from 18,000 Reservoirs

Development of a Machine Learning Technique in Conjunction with Reservoir Complexity Index to Predict Recovery Factor Using Data from 18,000 Reservoirs

Hybrid Workflows- A History of Tomorrow

Contact Info

Product

Resources

About