Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization

In geoenergy science and engineering, well placement optimization is the process of determining optimal well locations and configurations to maximize economic value while considering geological, engineering, economic, and environmental constraints. This complex multi-million-dollar problem involves...

Full description

Saved in:
Bibliographic Details
Main Authors: Seoyoon Kwon, Minsoo Ji, Min Kim, Juliana Y. Leung, Baehyun Min
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/1/36
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850072282770178048
author Seoyoon Kwon
Minsoo Ji
Min Kim
Juliana Y. Leung
Baehyun Min
author_facet Seoyoon Kwon
Minsoo Ji
Min Kim
Juliana Y. Leung
Baehyun Min
author_sort Seoyoon Kwon
collection DOAJ
description In geoenergy science and engineering, well placement optimization is the process of determining optimal well locations and configurations to maximize economic value while considering geological, engineering, economic, and environmental constraints. This complex multi-million-dollar problem involves optimizing multiple parameters using computationally intensive reservoir simulations, often employing advanced algorithms such as optimization algorithms and machine/deep learning techniques to find near-optimal solutions efficiently while accounting for uncertainties and risks. This study proposes a hybrid workflow for determining the locations of production wells during primary oil recovery using a multi-modal convolutional neural network (M-CNN) integrated with an evolutionary optimization algorithm. The particle swarm optimization algorithm provides the M-CNN with full-physics reservoir simulation results as learning data correlating an arbitrary well location and its cumulative oil production. The M-CNN learns the correlation between near-wellbore spatial properties (e.g., porosity, permeability, pressure, and saturation) and cumulative oil production as inputs and output, respectively. The learned M-CNN predicts oil productivity at every candidate well location and selects qualified well placement scenarios. The prediction performance of the M-CNN for hydrocarbon-prolific regions is improved by adding qualified scenarios to the learning data and re-training the M-CNN. This iterative learning scheme enhances the suitability of the proxy for solving the problem of maximizing oil productivity. The validity of the proxy is tested with a benchmark model, UNISIM-I-D, in which four oil production wells are sequentially drilled. The M-CNN approach demonstrates remarkable consistency and alignment with full-physics reservoir simulation results. It achieves prediction accuracy within a 3% relative error margin, while significantly reducing computational costs to just 11.18% of those associated with full-physics reservoir simulations. Moreover, the M-CNN-optimized well placement strategy yields a substantial 47.40% improvement in field cumulative oil production compared to the original configuration. These findings underscore the M-CNN’s effectiveness in sequential well placement optimization, striking an optimal balance between predictive accuracy and computational efficiency. The method’s ability to dramatically reduce processing time while maintaining high accuracy makes it a valuable tool for enhancing oil field productivity and streamlining reservoir management decisions.
format Article
id doaj-art-e2f6edb5e51747e3882f5874ef146f47
institution DOAJ
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-e2f6edb5e51747e3882f5874ef146f472025-08-20T02:47:06ZengMDPI AGMathematics2227-73902024-12-011313610.3390/math13010036Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary OptimizationSeoyoon Kwon0Minsoo Ji1Min Kim2Juliana Y. Leung3Baehyun Min4Department of Climate and Energy Systems Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760, Republic of KoreaDepartment of Climate and Energy Systems Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760, Republic of KoreaGlobal E&P Technology Center, Korea National Oil Corporation, 305 Jongga-ro, Jung-gu, Ulsan 44538, Republic of KoreaDepartment of Civil and Environmental Engineering, University of Alberta, Edmonton, AB T6G 1H9, CanadaDepartment of Climate and Energy Systems Engineering, Ewha Womans University, 52, Ewhayeodae-gil, Seodaemun-gu, Seoul 03760, Republic of KoreaIn geoenergy science and engineering, well placement optimization is the process of determining optimal well locations and configurations to maximize economic value while considering geological, engineering, economic, and environmental constraints. This complex multi-million-dollar problem involves optimizing multiple parameters using computationally intensive reservoir simulations, often employing advanced algorithms such as optimization algorithms and machine/deep learning techniques to find near-optimal solutions efficiently while accounting for uncertainties and risks. This study proposes a hybrid workflow for determining the locations of production wells during primary oil recovery using a multi-modal convolutional neural network (M-CNN) integrated with an evolutionary optimization algorithm. The particle swarm optimization algorithm provides the M-CNN with full-physics reservoir simulation results as learning data correlating an arbitrary well location and its cumulative oil production. The M-CNN learns the correlation between near-wellbore spatial properties (e.g., porosity, permeability, pressure, and saturation) and cumulative oil production as inputs and output, respectively. The learned M-CNN predicts oil productivity at every candidate well location and selects qualified well placement scenarios. The prediction performance of the M-CNN for hydrocarbon-prolific regions is improved by adding qualified scenarios to the learning data and re-training the M-CNN. This iterative learning scheme enhances the suitability of the proxy for solving the problem of maximizing oil productivity. The validity of the proxy is tested with a benchmark model, UNISIM-I-D, in which four oil production wells are sequentially drilled. The M-CNN approach demonstrates remarkable consistency and alignment with full-physics reservoir simulation results. It achieves prediction accuracy within a 3% relative error margin, while significantly reducing computational costs to just 11.18% of those associated with full-physics reservoir simulations. Moreover, the M-CNN-optimized well placement strategy yields a substantial 47.40% improvement in field cumulative oil production compared to the original configuration. These findings underscore the M-CNN’s effectiveness in sequential well placement optimization, striking an optimal balance between predictive accuracy and computational efficiency. The method’s ability to dramatically reduce processing time while maintaining high accuracy makes it a valuable tool for enhancing oil field productivity and streamlining reservoir management decisions.https://www.mdpi.com/2227-7390/13/1/36well placementmulti-modal convolutional neural networkevolutionary optimizationUNISIM-I-D
spellingShingle Seoyoon Kwon
Minsoo Ji
Min Kim
Juliana Y. Leung
Baehyun Min
Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization
Mathematics
well placement
multi-modal convolutional neural network
evolutionary optimization
UNISIM-I-D
title Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization
title_full Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization
title_fullStr Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization
title_full_unstemmed Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization
title_short Determination of Sequential Well Placements Using a Multi-Modal Convolutional Neural Network Integrated with Evolutionary Optimization
title_sort determination of sequential well placements using a multi modal convolutional neural network integrated with evolutionary optimization
topic well placement
multi-modal convolutional neural network
evolutionary optimization
UNISIM-I-D
url https://www.mdpi.com/2227-7390/13/1/36
work_keys_str_mv AT seoyoonkwon determinationofsequentialwellplacementsusingamultimodalconvolutionalneuralnetworkintegratedwithevolutionaryoptimization
AT minsooji determinationofsequentialwellplacementsusingamultimodalconvolutionalneuralnetworkintegratedwithevolutionaryoptimization
AT minkim determinationofsequentialwellplacementsusingamultimodalconvolutionalneuralnetworkintegratedwithevolutionaryoptimization
AT julianayleung determinationofsequentialwellplacementsusingamultimodalconvolutionalneuralnetworkintegratedwithevolutionaryoptimization
AT baehyunmin determinationofsequentialwellplacementsusingamultimodalconvolutionalneuralnetworkintegratedwithevolutionaryoptimization