Abeeb Adebowale Awotunde
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Abeeb Adebowale Awotunde has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad S. Jamal
Department of Petroleum Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia
9 shared publications - Menhal A. Al-Ismael
Saudi Aramco, Dhahran, Saudi Arabia
4 shared publications Roland N. Horne
Stanford University
4 shared publicationsHasan Y. Al-Yousef
King Fahd Univ Petr & Minerals, Coll Petr Engn & Geosci, Dhahran, Saudi Arabia
3 shared publicationsShirish Patil
King Fahd Univ Petr & Minerals, Coll Petr Engn & Geosci, Dhahran, Saudi Arabia
3 shared publicationsFaisal A. Fairag
King Fahd University of Petroleum & Minerals
2 shared publications
Latest Publications
- 13 June 2026
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51  (20) , 22987-23016
The Dhahran Probability Density Function for Improved Parameter Estimation
- 13 June 2026
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51  (20) , 22987-23016
The Dhahran Probability Density Function for Improved Parameter Estimation
- 26 November 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31  (01) , 621-642
Transformer-Based Generative Model for Automated Field Development Planning and Optimization in Hydrocarbon Reservoirs
Summary: As global demand for energy is increasing, exploration and new discoveries of oil and gas reservoirs continue, with optimal field development becoming more critical. Field development planning requires a comprehensive understanding of the reservoir, which usually involves developing computer-based simulation models and using time-intensive optimization techniques. Recent progress in generative artificial intelligence (AI) indicates potential to support field development optimization (FDO). With this research, we investigate the application of generative AI in FDO by developing a transformer-based generative model for generating optimal future wells that maximize the net present value (NPV). A new transformer architecture is developed, and the corresponding model is trained and applied to generate two outputs: (i) a probability map, providing spatial scores that guide the optimization of well types and locations, and (ii) a well control map that specifies the optimal operating settings at each location. The architecture includes an encoder module, which captures complex patterns and dependencies within the numerical simulation data to support well placement decisions. It also includes an embedding layer that converts raw data into dense vectors and encoding layers that add spatial and temporal context to improve model understanding of reservoir dynamics. The proposed approach was evaluated using the PUNQ-S3 benchmark reservoir simulation model using various input scenarios with different numbers and configurations of existing wells. The results demonstrate promising performance, providing instant predictions that closely align with the outcomes of the differential evolution (DE) optimization algorithm coupled with high-fidelity numerical simulation outputs, which demonstrate a strong understanding of the reservoir system behavior.
- 26 November 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31  (01) , 621-642
Transformer-Based Generative Model for Automated Field Development Planning and Optimization in Hydrocarbon Reservoirs
Summary: As global demand for energy is increasing, exploration and new discoveries of oil and gas reservoirs continue, with optimal field development becoming more critical. Field development planning requires a comprehensive understanding of the reservoir, which usually involves developing computer-based simulation models and using time-intensive optimization techniques. Recent progress in generative artificial intelligence (AI) indicates potential to support field development optimization (FDO). With this research, we investigate the application of generative AI in FDO by developing a transformer-based generative model for generating optimal future wells that maximize the net present value (NPV). A new transformer architecture is developed, and the corresponding model is trained and applied to generate two outputs: (i) a probability map, providing spatial scores that guide the optimization of well types and locations, and (ii) a well control map that specifies the optimal operating settings at each location. The architecture includes an encoder module, which captures complex patterns and dependencies within the numerical simulation data to support well placement decisions. It also includes an embedding layer that converts raw data into dense vectors and encoding layers that add spatial and temporal context to improve model understanding of reservoir dynamics. The proposed approach was evaluated using the PUNQ-S3 benchmark reservoir simulation model using various input scenarios with different numbers and configurations of existing wells. The results demonstrate promising performance, providing instant predictions that closely align with the outcomes of the differential evolution (DE) optimization algorithm coupled with high-fidelity numerical simulation outputs, which demonstrate a strong understanding of the reservoir system behavior.
- 4 August 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50  (24) , 21381-21402
Enhancing Large Language Models with In-Context Learning for Reservoir Management Tasks
- 4 August 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50  (24) , 21381-21402
Enhancing Large Language Models with In-Context Learning for Reservoir Management Tasks
- 3 December 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50  (7) , 5279-5301
A Comprehensive Review of Advancements in AI-Based Techniques for Field Development Optimization
- 3 December 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50  (7) , 5279-5301
A Comprehensive Review of Advancements in AI-Based Techniques for Field Development Optimization
- 18 June 2024
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 240
Leakage risk assessment on sealing efficiency of caprock during CO2 huff-n-puff for safe sequestration
- 18 June 2024
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 240
Leakage risk assessment on sealing efficiency of caprock during CO2 huff-n-puff for safe sequestration
- 14 June 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50  (7) , 4703-4720
Temperature Distribution and Pressure Transient Analysis in Heavy Oil Reservoirs Undergoing Microwave Heating
- 14 June 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50  (7) , 4703-4720
Temperature Distribution and Pressure Transient Analysis in Heavy Oil Reservoirs Undergoing Microwave Heating
- 13 December 2022
- Published by Elsevier in Computers & Geosciences
- Vol. 171
Interwell simulation model for the advection dispersion equation
- 13 December 2022
- Published by Elsevier in Computers & Geosciences
- Vol. 171
Interwell simulation model for the advection dispersion equation
- 9 November 2022
- Published by Society of Petroleum Engineers (SPE) in SPE Reservoir Evaluation & Engineering
- Vol. 26  (02) , 214-227
Robust and Efficient Identification of Hydraulic Flow Units using Differential Evolution Optimization and Two-Stage Clustering Techniques
Summary: One essential process in reservoir characterization is the identification of hydraulic flow units (HFUs). It plays a critical role in determining hydrocarbon reserves and improving reservoir productivity. Flow zone indicator (FZI), determined from core data, is widely used to identify HFUs. One of the challenges in the FZI technique is that the number of HFUs is identified using qualitative methods and subjective estimation. This work proposes robust methods to identify the optimal HFUs using differential evolution (DE) and two-stage clustering. The first method tested in this work enumerates through a large number of HFUs scenarios using 10 clustering algorithms and different input parameters (number of clusters, minimum number of samples, etc.). The scenario with the largest average correlation coefficient is selected as optimum. The second method uses the DE algorithm to maximize the average correlation coefficient and hence obtain the optimal HFUs. The third method consists of two stages. The first stage uses the OPTICS clustering algorithm to determine the number of HFUs, while the second stage generates the desired clusters using the Gaussian mixture algorithm. Both iterative evaluation and DE optimization methods achieved the same clustering results. However, DE optimization resulted in 85% reduction in runtime due to the robust search capability of the DE algorithm which leads to the solution more efficiently. Furthermore, another significant reduction in runtime was achieved using the two-stage clustering method which yielded very close results. The proposed methods in this work provide unique and potential opportunity to improve the use of FZI data analysis to identify HFUs. This work uses the power of clustering and stochastic algorithms to support a critical process in reservoir characterization.
- 9 November 2022
- Published by Society of Petroleum Engineers (SPE) in SPE Reservoir Evaluation & Engineering
- Vol. 26  (02) , 214-227
Robust and Efficient Identification of Hydraulic Flow Units using Differential Evolution Optimization and Two-Stage Clustering Techniques
Summary: One essential process in reservoir characterization is the identification of hydraulic flow units (HFUs). It plays a critical role in determining hydrocarbon reserves and improving reservoir productivity. Flow zone indicator (FZI), determined from core data, is widely used to identify HFUs. One of the challenges in the FZI technique is that the number of HFUs is identified using qualitative methods and subjective estimation. This work proposes robust methods to identify the optimal HFUs using differential evolution (DE) and two-stage clustering. The first method tested in this work enumerates through a large number of HFUs scenarios using 10 clustering algorithms and different input parameters (number of clusters, minimum number of samples, etc.). The scenario with the largest average correlation coefficient is selected as optimum. The second method uses the DE algorithm to maximize the average correlation coefficient and hence obtain the optimal HFUs. The third method consists of two stages. The first stage uses the OPTICS clustering algorithm to determine the number of HFUs, while the second stage generates the desired clusters using the Gaussian mixture algorithm. Both iterative evaluation and DE optimization methods achieved the same clustering results. However, DE optimization resulted in 85% reduction in runtime due to the robust search capability of the DE algorithm which leads to the solution more efficiently. Furthermore, another significant reduction in runtime was achieved using the two-stage clustering method which yielded very close results. The proposed methods in this work provide unique and potential opportunity to improve the use of FZI data analysis to identify HFUs. This work uses the power of clustering and stochastic algorithms to support a critical process in reservoir characterization.
- 1 November 2022
- Published by American Society of Civil Engineers (ASCE) in Journal of Water Resources Planning and Management
- Vol. 148  (11) , 04022053
Management of Saltwater Intrusion in Coastal Karstic Aquifers under Geological Uncertainties Associated with Shapes and Locations of Cave Networks
Stochastic optimization is an important tool employed to manage salt intrusion and increased freshwater production in coastal aquifers by estimating the optimum well locations and well operation parameters. In karst aquifers, the shape and location of the caves in the aquifers are often uncertain parameters. Thus, it becomes necessary to take into consideration the uncertainties when optimizing water production from such aquifers. The uncertainty associated with the parameterization of aquifers is often handled by creating several equiprobable realizations of aquifers through stochastic simulations. These realizations jointly describe the uncertainty in the aquifer model and as such are used as a means to manage uncertainty when performing optimization and simulation studies of such aquifers. However, owing to the large number of stochastic realizations often created to describe the uncertainty in an aquifer model, performing optimization under uncertainty becomes computationally expensive. In this paper, we propose a freshwater production optimization strategy that uses two separate clustering strategies to identify a small set of realizations (from the total ensemble of aquifer model realizations) upon which the optimization study can be conducted. In this study, a clustering strategy is adopted to reduce the computational expense associated with conducting the optimization study. The algorithm was used as the clustering algorithm, and a modified form of the Darcy model with optimized permeability distribution (DMOPD) was selected as the forward model that describes the flow of fluid in the aquifer. Furthermore, the DMOPD was connected to an advection-dispersion-adsorption equation that describes the transport of salt with the fluid phase. A synthetic aquifer example was used to illustrate the optimization strategy and the results obtained show that the clustering algorithm proves to be a useful tool in selecting representative samples for the optimization case study. Also, the optimization algorithm was found to be a viable tool to limit saltwater intrusion in karstic aquifers while maximizing freshwater recovery.- 1 November 2022
- Published by American Society of Civil Engineers (ASCE) in Journal of Water Resources Planning and Management
- Vol. 148  (11) , 04022053
Management of Saltwater Intrusion in Coastal Karstic Aquifers under Geological Uncertainties Associated with Shapes and Locations of Cave Networks
Stochastic optimization is an important tool employed to manage salt intrusion and increased freshwater production in coastal aquifers by estimating the optimum well locations and well operation parameters. In karst aquifers, the shape and location of the caves in the aquifers are often uncertain parameters. Thus, it becomes necessary to take into consideration the uncertainties when optimizing water production from such aquifers. The uncertainty associated with the parameterization of aquifers is often handled by creating several equiprobable realizations of aquifers through stochastic simulations. These realizations jointly describe the uncertainty in the aquifer model and as such are used as a means to manage uncertainty when performing optimization and simulation studies of such aquifers. However, owing to the large number of stochastic realizations often created to describe the uncertainty in an aquifer model, performing optimization under uncertainty becomes computationally expensive. In this paper, we propose a freshwater production optimization strategy that uses two separate clustering strategies to identify a small set of realizations (from the total ensemble of aquifer model realizations) upon which the optimization study can be conducted. In this study, a clustering strategy is adopted to reduce the computational expense associated with conducting the optimization study. The algorithm was used as the clustering algorithm, and a modified form of the Darcy model with optimized permeability distribution (DMOPD) was selected as the forward model that describes the flow of fluid in the aquifer. Furthermore, the DMOPD was connected to an advection-dispersion-adsorption equation that describes the transport of salt with the fluid phase. A synthetic aquifer example was used to illustrate the optimization strategy and the results obtained show that the clustering algorithm proves to be a useful tool in selecting representative samples for the optimization case study. Also, the optimization algorithm was found to be a viable tool to limit saltwater intrusion in karstic aquifers while maximizing freshwater recovery.- 2 February 2022
- Published by Elsevier in Journal of Petroleum Science and Engineering
- Vol. 212
Triple mesh methods and their application to two-phase flow in porous media
- 2 February 2022
- Published by Elsevier in Journal of Petroleum Science and Engineering
- Vol. 212
Triple mesh methods and their application to two-phase flow in porous media