Ahmed Adeyemi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ahmed Adeyemi has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Mustafa Onur
The University of Tulsa, Tulsa, USA
4 shared publications - Quang Minh Nguyen
University of Tulsa, Tulsa, Oklahoma, USA
2 shared publications Usman Abdulkareem
University of Tulsa, Tulsa, Oklahoma, USA
1 shared publication
Latest Publications
- 1 June 2026
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (08) , 1-23
Deep-Learning-Based History-Matching Framework Using an Embed-to-Control Observe Reservoir Surrogate
Summary: With this study, we investigate a deep learning (DL)–based reduced-order model (ROM) for reservoir history matching (HM) using the embed-to-control (E2C) and observe (E2CO) framework. E2CO combines an autoencoder for dimensionality reduction, a linear transition network for latent-state evolution, and a transition output network for predicting well responses. The framework is implemented with proper orthogonal decomposition and trajectory piecewise linearization (POD-TPWL), enabling efficient projection of high-dimensional model parameters into a reduced space. The model is trained in both high-dimensional (m-space) and reduced (β-space) parameter spaces, and their training cost and predictive performance are compared. The trained E2CO proxy is integrated with the ensemble smoother with multiple data assimilation (ES-MDA) to calibrate heterogeneous permeability fields using noisy production data [oil and water rates and injection-bottomhole pressures (BHPs)] from the 3D SPE10 benchmark model. Results demonstrate that the proposed approach provides accurate predictions of reservoir states and well outputs while significantly reducing computational costs compared with a high-fidelity simulator. To the best of our knowledge, this is the first study in petroleum engineering to combine a conventional ROM framework with a DL-based proxy for ES-MDA-based HM. The findings highlight the importance of efficient preprocessing and dimensionality reduction in machine learning (ML) workflows, offering practical guidance for integrating ML-based proxies with conventional HM methodologies.
- 1 June 2026
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (08) , 1-23
Deep-Learning-Based History-Matching Framework Using an Embed-to-Control Observe Reservoir Surrogate
Summary: With this study, we investigate a deep learning (DL)–based reduced-order model (ROM) for reservoir history matching (HM) using the embed-to-control (E2C) and observe (E2CO) framework. E2CO combines an autoencoder for dimensionality reduction, a linear transition network for latent-state evolution, and a transition output network for predicting well responses. The framework is implemented with proper orthogonal decomposition and trajectory piecewise linearization (POD-TPWL), enabling efficient projection of high-dimensional model parameters into a reduced space. The model is trained in both high-dimensional (m-space) and reduced (β-space) parameter spaces, and their training cost and predictive performance are compared. The trained E2CO proxy is integrated with the ensemble smoother with multiple data assimilation (ES-MDA) to calibrate heterogeneous permeability fields using noisy production data [oil and water rates and injection-bottomhole pressures (BHPs)] from the 3D SPE10 benchmark model. Results demonstrate that the proposed approach provides accurate predictions of reservoir states and well outputs while significantly reducing computational costs compared with a high-fidelity simulator. To the best of our knowledge, this is the first study in petroleum engineering to combine a conventional ROM framework with a DL-based proxy for ES-MDA-based HM. The findings highlight the importance of efficient preprocessing and dimensionality reduction in machine learning (ML) workflows, offering practical guidance for integrating ML-based proxies with conventional HM methodologies.
- 10 April 2026
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 263
E2CO-lite: A scalable deep-learning surrogate for efficient nonlinearly constrained robust production optimization
- 10 April 2026
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 263
E2CO-lite: A scalable deep-learning surrogate for efficient nonlinearly constrained robust production optimization
- 24 September 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (11) , 6603-6621
Accelerated Deep Reinforcement Learning in Subsurface Reservoir Production Optimization
Summary: Constrained production optimization in subsurface reservoirs under geological uncertainty presents major computational and methodological challenges. High-fidelity simulations are too slow for training reinforcement learning (RL) agents or running iterative gradient-based optimizations. Ensuring constraint satisfaction amid uncertain reservoir dynamics requires carefully designed strategies. In this study, we introduce a hybrid optimization framework that integrates a scalable multimodel embed-to-control and observe (E2CO-lite) surrogate, deep reinforcement learning (DRL) with adaptive constraint-aware reward shaping, and sequential quadratic programming (SQP) with stochastic gradients (StoSAG). The E2CO-lite surrogate accelerates simulation while preserving geological realism, enabling efficient DRL training across clustered realizations. The trained DRL agent provides generalizable control strategies to warm-start SQP, combining DRL’s exploratory strength with SQP’s constraint-handling rigor. We validate the framework on the Brugge benchmark reservoir. Proxy-based DRL training achieves more than 50X speedup compared with full-physics simulation. The DRL-SQP hybrid improves convergence and optimization outcomes over SQP with naïve initialization. The results show that DRL-assisted initialization achieves higher net present value (NPV) while satisfying constraints. Final control strategies tested on the true Brugge model confirm the method’s scalability, efficiency, and practical relevance for subsurface reservoir optimization under uncertainty.
- 24 September 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (11) , 6603-6621
Accelerated Deep Reinforcement Learning in Subsurface Reservoir Production Optimization
Summary: Constrained production optimization in subsurface reservoirs under geological uncertainty presents major computational and methodological challenges. High-fidelity simulations are too slow for training reinforcement learning (RL) agents or running iterative gradient-based optimizations. Ensuring constraint satisfaction amid uncertain reservoir dynamics requires carefully designed strategies. In this study, we introduce a hybrid optimization framework that integrates a scalable multimodel embed-to-control and observe (E2CO-lite) surrogate, deep reinforcement learning (DRL) with adaptive constraint-aware reward shaping, and sequential quadratic programming (SQP) with stochastic gradients (StoSAG). The E2CO-lite surrogate accelerates simulation while preserving geological realism, enabling efficient DRL training across clustered realizations. The trained DRL agent provides generalizable control strategies to warm-start SQP, combining DRL’s exploratory strength with SQP’s constraint-handling rigor. We validate the framework on the Brugge benchmark reservoir. Proxy-based DRL training achieves more than 50X speedup compared with full-physics simulation. The DRL-SQP hybrid improves convergence and optimization outcomes over SQP with naïve initialization. The results show that DRL-assisted initialization achieves higher net present value (NPV) while satisfying constraints. Final control strategies tested on the true Brugge model confirm the method’s scalability, efficiency, and practical relevance for subsurface reservoir optimization under uncertainty.
- Open Access
- 29 August 2024
- Published by Springer Nature in Research Square
Streamlining Constrained Production Optimization Under Geological Uncertainty: An Integrated Framework Utilizing Automatically Differentiated Gradient from Deep-Learning-Based Reservoir Surrogates
Life-cycle production optimization in reservoir engineering poses computational challenges, especially under geological uncertainty and complex models. This study introduces a novel approach to enhance optimization accuracy and efficiency by integrating automatic gradient computation from a deep-learning-based reservoir surrogate into the optimization process. Departing from conventional techniques, we aim to leverage the inherent automatic differentiation (AD) capabilities of deep-learning platforms to compute gradients seamlessly within the optimization framework. Our method builds upon the Embed-to-control Observe (E2CO) deep-learning proxy model, featuring an architecture comprising encoder, transition, transition output, and decoder blocks. The transition output block enables direct prediction of reservoir system outputs from input state variables without using any explicit well-model equations. Coupled with a gradient-based line-search sequential quadratic programming (LSSQP) workflow, our approach, enhanced by the novel integration of automatic gradient computation from the deep-learning proxy, adeptly manages robust production optimization under nonlinear state constraints. Performance evaluations are conducted using a portion of the SPE10 benchmark reservoir model, demonstrating the efficacy of the proposed approach compared to conventional methods. Our findings reveal that the integration of automatic gradient computation from the deep-learning-based reservoir surrogate significantly enhances optimization efficiency. The trained and cross-validated multi-model E2CO surrogate accurately predicts state variables and well outputs under geological uncertainty. Utilizing the AD-based gradients derived from the deep-learning proxy for the gradient-based LSSQP workflow, our approach achieves optimal solutions comparable to the stochastic gradient approach and the direct optimization using high-fidelity reservoir simulators. Moreover, the proposed optimization workflow demonstrates superior time efficiency compared to conventional approaches directly coupled with reservoir simulators.
- 29 August 2024
- Published by Springer Nature in Research Square
Open AccessStreamlining Constrained Production Optimization Under Geological Uncertainty: An Integrated Framework Utilizing Automatically Differentiated Gradient from Deep-Learning-Based Reservoir Surrogates
Life-cycle production optimization in reservoir engineering poses computational challenges, especially under geological uncertainty and complex models. This study introduces a novel approach to enhance optimization accuracy and efficiency by integrating automatic gradient computation from a deep-learning-based reservoir surrogate into the optimization process. Departing from conventional techniques, we aim to leverage the inherent automatic differentiation (AD) capabilities of deep-learning platforms to compute gradients seamlessly within the optimization framework. Our method builds upon the Embed-to-control Observe (E2CO) deep-learning proxy model, featuring an architecture comprising encoder, transition, transition output, and decoder blocks. The transition output block enables direct prediction of reservoir system outputs from input state variables without using any explicit well-model equations. Coupled with a gradient-based line-search sequential quadratic programming (LSSQP) workflow, our approach, enhanced by the novel integration of automatic gradient computation from the deep-learning proxy, adeptly manages robust production optimization under nonlinear state constraints. Performance evaluations are conducted using a portion of the SPE10 benchmark reservoir model, demonstrating the efficacy of the proposed approach compared to conventional methods. Our findings reveal that the integration of automatic gradient computation from the deep-learning-based reservoir surrogate significantly enhances optimization efficiency. The trained and cross-validated multi-model E2CO surrogate accurately predicts state variables and well outputs under geological uncertainty. Utilizing the AD-based gradients derived from the deep-learning proxy for the gradient-based LSSQP workflow, our approach achieves optimal solutions comparable to the stochastic gradient approach and the direct optimization using high-fidelity reservoir simulators. Moreover, the proposed optimization workflow demonstrates superior time efficiency compared to conventional approaches directly coupled with reservoir simulators.