Menhal A. Al-Ismael
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Menhal A. Al-Ismael has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Abeeb Adebowale Awotunde
Department of Petroleum Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia
4 shared publications Mohammad S. Jamal
Department of Petroleum Engineering, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia
1 shared publication
Latest Publications
- 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
- 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.