Quang Minh Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Quang Minh Nguyen has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Mustafa Onur
The University of Tulsa, Tulsa, USA
11 shared publications - Faruk Omer Alpak
Shell International Exploration and Production Inc., Houston, Texas, USA
4 shared publications - Ahmed Adeyemi
University of Tulsa, Tulsa, Oklahoma, USA
2 shared publications - Imaobong Tom
The University of Tulsa, Tulsa, USA
2 shared publications - Omer Lutfu Toktas
University of Tulsa, Tulsa, Oklahoma, USA
2 shared publications Usman Abdulkareem
University of Tulsa, Tulsa, Oklahoma, USA
2 shared publications
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.
- 16 December 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (02) , 1119-1140
Application of Embed-to-Control Observe Deep-Learning-Based Reservoir Surrogate in CO2 Storage Monitoring and Multiobjective Optimization
Summary: The focus of this paper is on the use of a data-driven method for predicting reservoir performance in a carbon dioxide (CO2) storage application. The aim is to forecast state variables and well outputs for a compositional fluid system, as well as to perform multiobjective optimization under geological uncertainty, all by using a deep learning (DL)-based surrogate model. The surrogate model used in this work is based on the multimodel embed-to-control observe (E2CO) architecture, consisting of four blocks of neural networks (NNs), which are encoder, transition, transition output, and decoder. Our previous studies published by Nguyen et al. 2023bNguyen et al. 2023c,47 considered bi-objective optimization under geological uncertainty of CO2 storage, but using a high-fidelity simulator (HFS). Also, the previous multimodel E2CO proxy models published in our studies by Nguyen and Onur 2024aNguyen and Onur 2024b and 49 and Nguyen et al. (2024) are valid for single-objective reservoir production optimization using the E2CO proxy built on the training samples from two-phase black oil reservoir models. This is the first study for implementing E2CO, trained by samples from a compositional model based on SPE10 for a bi-objective optimization problem of CO2 storage. In this study, we combine the surrogate model with the stochastic-gradient-based line-search sequential quadratic programming (LS-SQP) framework and implement the lexicographic method to handle robust multiobjective optimization with the nonlinear state constraints. Five realizations of the SPE10 sector model, consisting of different channelized heterogeneous distributions with eight vertical wells, are used to demonstrate the prediction and optimization performances of the proposed framework. The framework fully leverages various results and insights from previous studies, allowing us to achieve excellent optimization (with nonlinear state constraint) results at very affordable computational expenses, while still maintaining good agreement with the results from the HFS.
- 16 December 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (02) , 1119-1140
Application of Embed-to-Control Observe Deep-Learning-Based Reservoir Surrogate in CO2 Storage Monitoring and Multiobjective Optimization
Summary: The focus of this paper is on the use of a data-driven method for predicting reservoir performance in a carbon dioxide (CO2) storage application. The aim is to forecast state variables and well outputs for a compositional fluid system, as well as to perform multiobjective optimization under geological uncertainty, all by using a deep learning (DL)-based surrogate model. The surrogate model used in this work is based on the multimodel embed-to-control observe (E2CO) architecture, consisting of four blocks of neural networks (NNs), which are encoder, transition, transition output, and decoder. Our previous studies published by Nguyen et al. 2023bNguyen et al. 2023c,47 considered bi-objective optimization under geological uncertainty of CO2 storage, but using a high-fidelity simulator (HFS). Also, the previous multimodel E2CO proxy models published in our studies by Nguyen and Onur 2024aNguyen and Onur 2024b and 49 and Nguyen et al. (2024) are valid for single-objective reservoir production optimization using the E2CO proxy built on the training samples from two-phase black oil reservoir models. This is the first study for implementing E2CO, trained by samples from a compositional model based on SPE10 for a bi-objective optimization problem of CO2 storage. In this study, we combine the surrogate model with the stochastic-gradient-based line-search sequential quadratic programming (LS-SQP) framework and implement the lexicographic method to handle robust multiobjective optimization with the nonlinear state constraints. Five realizations of the SPE10 sector model, consisting of different channelized heterogeneous distributions with eight vertical wells, are used to demonstrate the prediction and optimization performances of the proposed framework. The framework fully leverages various results and insights from previous studies, allowing us to achieve excellent optimization (with nonlinear state constraint) results at very affordable computational expenses, while still maintaining good agreement with the results from the HFS.
- 15 December 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (02) , 1266-1283
Embed-to-Control-Based Deep Learning Surrogate for Robust Nonlinearly Constrained Life Cycle Production Optimization: A Realistic Deepwater Application
Summary: This paper presents a realistic deepwater application of a deep learning (DL)-based reservoir surrogate model in forecasting reservoir performance (via the prediction of state variables and well outputs) and nonlinearly constrained production optimization under geological uncertainty by utilizing an efficient gradient-based method. The reservoir surrogate model is based on the multimodel embed-to-control observe (E2CO) architecture, consisting of four blocks of neural networks (NNs): encoder, transition, transition output, and decoder. In this work, the surrogate model is coupled with the powerful stochastic-gradient-based line-search sequential quadratic programming (LS-SQP) workflow to handle robust production optimization in the presence of nonlinear state constraints. This is the first time the E2CO-based production optimization method driven by a novel nonlinear optimization is applied to a reservoir model with very realistic characteristics of a deepwater reservoir (not a toy reservoir model) in terms of structural architecture and flow property distribution in an efficient data-driven manner using the multimodel E2CO DL surrogate as detailed by Nguyen and Onur (2025). Five realizations of the synthetic realistic Reservoir X model with different channelized heterogeneous permeability distributions under waterflooding are used for showcasing the prediction and optimization performances of the DL-based framework. The results from this framework are directly and quantitatively compared with those simulated using a commercial high-fidelity reservoir simulator (HFS).
- 15 December 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (02) , 1266-1283
Embed-to-Control-Based Deep Learning Surrogate for Robust Nonlinearly Constrained Life Cycle Production Optimization: A Realistic Deepwater Application
Summary: This paper presents a realistic deepwater application of a deep learning (DL)-based reservoir surrogate model in forecasting reservoir performance (via the prediction of state variables and well outputs) and nonlinearly constrained production optimization under geological uncertainty by utilizing an efficient gradient-based method. The reservoir surrogate model is based on the multimodel embed-to-control observe (E2CO) architecture, consisting of four blocks of neural networks (NNs): encoder, transition, transition output, and decoder. In this work, the surrogate model is coupled with the powerful stochastic-gradient-based line-search sequential quadratic programming (LS-SQP) workflow to handle robust production optimization in the presence of nonlinear state constraints. This is the first time the E2CO-based production optimization method driven by a novel nonlinear optimization is applied to a reservoir model with very realistic characteristics of a deepwater reservoir (not a toy reservoir model) in terms of structural architecture and flow property distribution in an efficient data-driven manner using the multimodel E2CO DL surrogate as detailed by Nguyen and Onur (2025). Five realizations of the synthetic realistic Reservoir X model with different channelized heterogeneous permeability distributions under waterflooding are used for showcasing the prediction and optimization performances of the DL-based framework. The results from this framework are directly and quantitatively compared with those simulated using a commercial high-fidelity reservoir simulator (HFS).
- 15 October 2025
- Published by Springer Nature in Computational Geosciences
- Vol. 29 (5) , 1-30
Nonlinearly constrained well placement optimization for geologic CO$_{2}$ storage using Iterative Latin Hypercube Sampling- 15 October 2025
- Published by Springer Nature in Computational Geosciences
- Vol. 29 (5) , 1-30
Nonlinearly constrained well placement optimization for geologic CO$_{2}$ storage using Iterative Latin Hypercube Sampling- 28 August 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (11) , 7023-7036
Nonlinearly Constrained Life-Cycle Production Optimization Under Geological Uncertainty: A Realistic Application
Summary: This study presents a realistic application of our previously developed nonlinearly constrained stochastic gradient-based optimization framework that can efficiently solve nonlinearly constrained robust production optimization problems. We apply the optimization framework to a synthetic, yet realistic, field optimization problem using multiple history-matched realizations of the geologic model. For the synthetic realistic field example, the reservoir is assumed to undergo production for several years. Well controls (bottomhole pressures, or BHPs, for producers and water injection rates for injectors) on a sequence of control steps (time intervals) are optimized during the forecast period by maximizing the expected value of the net present value (NPV, or ensemble average) over multiple realizations of subsurface description for the subsequent 10 years of production under a waterflooding scenario subject to nonlinear constraints. The optimization framework is based on our in-house nonlinear optimizer employing sequential quadratic programming (SQP) coupled with stochastic simplex approximated gradients (StoSAG). It incorporates the line-search procedure within SQP and is referred to as line-search sequential quadratic programming (LS-SQP). We couple LS-SQP with two different constraint handling schemes: the expected value constraint scheme and the minimum-maximum (min-max) constraint scheme. Both bound constraints on well controls and nonlinear constraints on field liquid production rate (FLPR), field water injection rate FWIR, and/or individual producer water production rates are considered. We consider several different history-matched geological realizations of the realistic field example with several injectors and producers. A black-oil commercial reservoir simulator is utilized in the optimization workflow to assess the objective function with imposed constraints. Results show that the framework LS-SQP algorithm with StoSAG can effectively handle the nonlinear constraints in a robust life cycle production optimization problem. Moreover, our results show that the LS-SQP framework with any of the two different constraint-handling schemes considered effectively handles the nonlinear constraints in a life cycle robust production optimization problem. However, the expected value constraint scheme results in a higher optimal NPV than the min-max constraint scheme, but at the cost of possible constraint violation for some individual geological realizations. Application results demonstrate that our nonlinearly constrained stochastic gradient-based robust optimization framework has great potential to be a rapid approximate capability for performing life cycle production optimization under subsurface uncertainty with bound and nonlinear constraints.
- 28 August 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (11) , 7023-7036
Nonlinearly Constrained Life-Cycle Production Optimization Under Geological Uncertainty: A Realistic Application
Summary: This study presents a realistic application of our previously developed nonlinearly constrained stochastic gradient-based optimization framework that can efficiently solve nonlinearly constrained robust production optimization problems. We apply the optimization framework to a synthetic, yet realistic, field optimization problem using multiple history-matched realizations of the geologic model. For the synthetic realistic field example, the reservoir is assumed to undergo production for several years. Well controls (bottomhole pressures, or BHPs, for producers and water injection rates for injectors) on a sequence of control steps (time intervals) are optimized during the forecast period by maximizing the expected value of the net present value (NPV, or ensemble average) over multiple realizations of subsurface description for the subsequent 10 years of production under a waterflooding scenario subject to nonlinear constraints. The optimization framework is based on our in-house nonlinear optimizer employing sequential quadratic programming (SQP) coupled with stochastic simplex approximated gradients (StoSAG). It incorporates the line-search procedure within SQP and is referred to as line-search sequential quadratic programming (LS-SQP). We couple LS-SQP with two different constraint handling schemes: the expected value constraint scheme and the minimum-maximum (min-max) constraint scheme. Both bound constraints on well controls and nonlinear constraints on field liquid production rate (FLPR), field water injection rate FWIR, and/or individual producer water production rates are considered. We consider several different history-matched geological realizations of the realistic field example with several injectors and producers. A black-oil commercial reservoir simulator is utilized in the optimization workflow to assess the objective function with imposed constraints. Results show that the framework LS-SQP algorithm with StoSAG can effectively handle the nonlinear constraints in a robust life cycle production optimization problem. Moreover, our results show that the LS-SQP framework with any of the two different constraint-handling schemes considered effectively handles the nonlinear constraints in a life cycle robust production optimization problem. However, the expected value constraint scheme results in a higher optimal NPV than the min-max constraint scheme, but at the cost of possible constraint violation for some individual geological realizations. Application results demonstrate that our nonlinearly constrained stochastic gradient-based robust optimization framework has great potential to be a rapid approximate capability for performing life cycle production optimization under subsurface uncertainty with bound and nonlinear constraints.
- 9 May 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (07) , 3931-3949
A Deep-Learning-Based Reservoir Surrogate for Performance Forecast and Nonlinearly Constrained Life-Cycle Production Optimization Under Geological Uncertainty
Summary: In this study, we present an efficient gradient-based production optimization method that uses a deep-learning (DL)-based proxy model for the prediction of state variables (such as pressures and saturations) and well outputs [such as bottomhole pressures (BHPs) and injection rates] to solve nonlinearly constrained optimization with geological uncertainty. In our study, geological uncertainty is assumed to exist only due to uncertainty in the absolute permeability. The surrogate model is the embed-to-control observe (E2CO) DL proxy model, consisting of four blocks of neural networks (NNs)—encoder, transition, transition output, and decoder. The use of a transition output block in E2CO networks provides the capability of predicting reservoir system output directly from the input state variables without using any explicit well model equations. The proxy model is coupled with a powerful stochastic-gradient-based line search sequential quadratic programming (LS-SQP) workflow to handle robust production optimization in the presence of nonlinear state constraints. A portion of the SPE10 benchmark reservoir model with channelized heterogeneous permeability under waterflooding is used for demonstrating the prediction and optimization performances of the proposed E2CO-based framework. The results from the novel framework presented in this work are directly and quantitatively compared with the ones simulated using a commercial high-fidelity reservoir simulator (HFS).
- 9 May 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (07) , 3931-3949
A Deep-Learning-Based Reservoir Surrogate for Performance Forecast and Nonlinearly Constrained Life-Cycle Production Optimization Under Geological Uncertainty
Summary: In this study, we present an efficient gradient-based production optimization method that uses a deep-learning (DL)-based proxy model for the prediction of state variables (such as pressures and saturations) and well outputs [such as bottomhole pressures (BHPs) and injection rates] to solve nonlinearly constrained optimization with geological uncertainty. In our study, geological uncertainty is assumed to exist only due to uncertainty in the absolute permeability. The surrogate model is the embed-to-control observe (E2CO) DL proxy model, consisting of four blocks of neural networks (NNs)—encoder, transition, transition output, and decoder. The use of a transition output block in E2CO networks provides the capability of predicting reservoir system output directly from the input state variables without using any explicit well model equations. The proxy model is coupled with a powerful stochastic-gradient-based line search sequential quadratic programming (LS-SQP) workflow to handle robust production optimization in the presence of nonlinear state constraints. A portion of the SPE10 benchmark reservoir model with channelized heterogeneous permeability under waterflooding is used for demonstrating the prediction and optimization performances of the proposed E2CO-based framework. The results from the novel framework presented in this work are directly and quantitatively compared with the ones simulated using a commercial high-fidelity reservoir simulator (HFS).
- 9 January 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (03) , 1413-1431
Comparison of Constrained Life Cycle Production Optimization Algorithms Based on Stochastic Simplex Approximate Gradients
Summary: This study focuses on the optimization of net present value (NPV) with respect to well controls, such as injection rates and producing bottomhole pressures (BHPs), subject to the nonlinear constraints of field liquid production rate (FLPR) and water rate for producers (WWPR). The core challenge is to maximize NPV while adhering to both linear and nonlinear constraints, crucial for effective reservoir management. The research presents a detailed comparison of three sequential quadratic programming (SQP)-based optimizers—the Tulsa University nonlinearly constrained production optimizer (TU-NLCPO), our in-house nonlinear production optimizer, and two publicly available optimizers, namely sequential least squares programming optimizer (SLSQP), and sparse nonlinear optimizer (SNOPT)—highlighting their application in constrained life cycle production optimization, a key aspect of closed-loop reservoir management. These optimizers are evaluated based on their ability to handle optimization variables, such as BHPs and well injection rates, over fixed control steps. Stochastic simplex approximate gradient (StoSAG) is applied across the three algorithms for a fair comparison. This comparison is performed using the Brugge model for waterflooding, providing a rigorous real-world assessment of each optimizer’s performance. Our findings reveal that TU-NLCPO consistently achieves higher NPV compared with SLSQP and SNOPT, indicating its superior optimization capability. Additionally, TU-NLCPO and SLSQP are found to be robust against different initial guesses, demonstrating consistent NPV values, whereas SNOPT shows variability despite reasonable overall performance. Regarding optimization with nonlinear state constraints, the performances of three optimizers are highly dependent on the initial guesses. The study also explores the impact of varying the number of perturbations for stochastic gradient generation on optimizer performance, noting an improvement across all methods with more perturbations. In general, our results show that SNOPT requires more accurate gradients, that is, more StoSAG perturbations required, than the other two optimizers, SLSQP often requires scaling of the objective function, while TU-NLCPO is more robust as compared with SLSQP and SNOPT to different initial guesses with nonlinear state constraints.
- 9 January 2025
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (03) , 1413-1431
Comparison of Constrained Life Cycle Production Optimization Algorithms Based on Stochastic Simplex Approximate Gradients
Summary: This study focuses on the optimization of net present value (NPV) with respect to well controls, such as injection rates and producing bottomhole pressures (BHPs), subject to the nonlinear constraints of field liquid production rate (FLPR) and water rate for producers (WWPR). The core challenge is to maximize NPV while adhering to both linear and nonlinear constraints, crucial for effective reservoir management. The research presents a detailed comparison of three sequential quadratic programming (SQP)-based optimizers—the Tulsa University nonlinearly constrained production optimizer (TU-NLCPO), our in-house nonlinear production optimizer, and two publicly available optimizers, namely sequential least squares programming optimizer (SLSQP), and sparse nonlinear optimizer (SNOPT)—highlighting their application in constrained life cycle production optimization, a key aspect of closed-loop reservoir management. These optimizers are evaluated based on their ability to handle optimization variables, such as BHPs and well injection rates, over fixed control steps. Stochastic simplex approximate gradient (StoSAG) is applied across the three algorithms for a fair comparison. This comparison is performed using the Brugge model for waterflooding, providing a rigorous real-world assessment of each optimizer’s performance. Our findings reveal that TU-NLCPO consistently achieves higher NPV compared with SLSQP and SNOPT, indicating its superior optimization capability. Additionally, TU-NLCPO and SLSQP are found to be robust against different initial guesses, demonstrating consistent NPV values, whereas SNOPT shows variability despite reasonable overall performance. Regarding optimization with nonlinear state constraints, the performances of three optimizers are highly dependent on the initial guesses. The study also explores the impact of varying the number of perturbations for stochastic gradient generation on optimizer performance, noting an improvement across all methods with more perturbations. In general, our results show that SNOPT requires more accurate gradients, that is, more StoSAG perturbations required, than the other two optimizers, SLSQP often requires scaling of the objective function, while TU-NLCPO is more robust as compared with SLSQP and SNOPT to different initial guesses with nonlinear state constraints.
- 2 December 2024
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (01) , 326-343
Performance Comparison of Gradient-Free Optimization Methods for Well Placement and Well Controls Optimization for Geologic CO2 Storage
Summary: In this study, we investigate the use of three different gradient-free population-based optimization methods—namely, iterative Latin hypercube sampling (ILHS), particle swarm optimization (PSO), and genetic algorithm (GA)—for the well placement and well controls optimization problem of CO2 underground storage in a 2D saline aquifer with bound constraints on the design variables. We also consider both simultaneous and sequential optimizations of well locations and well controls using these gradient-free methods. The optimization problem involves finding the optimal well types, well locations, or well controls for a CO2 injection problem in a synthetic saline aquifer compositional model built in a commercial simulator. The objective function formulated for the CO2 injection problem is the net present environmental value (NPEV) involving discrete design variables (well types and well locations) and continuous design variables (well controls). We observe that for simple well-location optimization problems involving one or two wells, all three algorithms obtained comparable results, given the same number of samples and number of iterations. However, for more complex cases such as the sequential or simultaneous optimization problems, when multiple wells that may include injectors and producers are present, we observe significant differences in the selection of the optimal well types and well locations among the three optimizers. In the simultaneous optimization of well types, well locations, and well controls, when both injectors and producers are bottomhole pressure (BHP) controlled, the results show that it is more optimal for at least one producer to be present, and for the injectors to be operated at the upper bound of the injector BHP, while the producers are operated at the lower bound of the producer BHP to maximize the NPEV.
- 2 December 2024
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 30 (01) , 326-343
Performance Comparison of Gradient-Free Optimization Methods for Well Placement and Well Controls Optimization for Geologic CO2 Storage
Summary: In this study, we investigate the use of three different gradient-free population-based optimization methods—namely, iterative Latin hypercube sampling (ILHS), particle swarm optimization (PSO), and genetic algorithm (GA)—for the well placement and well controls optimization problem of CO2 underground storage in a 2D saline aquifer with bound constraints on the design variables. We also consider both simultaneous and sequential optimizations of well locations and well controls using these gradient-free methods. The optimization problem involves finding the optimal well types, well locations, or well controls for a CO2 injection problem in a synthetic saline aquifer compositional model built in a commercial simulator. The objective function formulated for the CO2 injection problem is the net present environmental value (NPEV) involving discrete design variables (well types and well locations) and continuous design variables (well controls). We observe that for simple well-location optimization problems involving one or two wells, all three algorithms obtained comparable results, given the same number of samples and number of iterations. However, for more complex cases such as the sequential or simultaneous optimization problems, when multiple wells that may include injectors and producers are present, we observe significant differences in the selection of the optimal well types and well locations among the three optimizers. In the simultaneous optimization of well types, well locations, and well controls, when both injectors and producers are bottomhole pressure (BHP) controlled, the results show that it is more optimal for at least one producer to be present, and for the injectors to be operated at the upper bound of the injector BHP, while the producers are operated at the lower bound of the producer BHP to maximize the NPEV.
- 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.