Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin

Abstract Geothermal energy is a large, renewable, and clean source of energy from the earth in the form of heat. Exploring the deeper layers of the Williston Basin has revealed favorable reservoir temperatures, particularly in the western areas where high heat flows are prevalent. The quality of a g...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdul-Muaizz Koray, Emmanuel Gyimah, Mohamed Metwally, Hamid Rahnema, Olusegun Tomomewo
Format: Article
Language:English
Published: SpringerOpen 2025-01-01
Series:Geothermal Energy
Subjects:
Online Access:https://doi.org/10.1186/s40517-024-00323-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832585898180476928
author Abdul-Muaizz Koray
Emmanuel Gyimah
Mohamed Metwally
Hamid Rahnema
Olusegun Tomomewo
author_facet Abdul-Muaizz Koray
Emmanuel Gyimah
Mohamed Metwally
Hamid Rahnema
Olusegun Tomomewo
author_sort Abdul-Muaizz Koray
collection DOAJ
description Abstract Geothermal energy is a large, renewable, and clean source of energy from the earth in the form of heat. Exploring the deeper layers of the Williston Basin has revealed favorable reservoir temperatures, particularly in the western areas where high heat flows are prevalent. The quality of a geothermal hotspot hinges on the reservoir quality index (RQI), which is determined by the accuracy of calculating the field reservoir permeability. The primary goal of this study is to apply machine learning techniques to accurately calculate the field permeability, which is important for optimizing the RQI. To enhance accuracy, we initially applied various clustering algorithms, including the density-based spatial clustering of applications with noise (DBSCAN), K-means, K-median, and hierarchical clustering methods, to delineate hydraulic flow units (HFU) within the reservoir using porosity, permeability and water saturation core data. Subsequently, regression models including supervised ML regression methods such as neural networks, support vector machine (SVM) regression, Gaussian process regression (GPR), ensemble regression, linear regression, and decision trees were employed for each flow unit to establish correlations and calculate field permeability with each of these models validated using cross-validation. In comparison to the other clustering methods, the hierarchical clustering method showed the best performance by showing a strong correlation between the actual and predicted permeability values. Overall, the SVM and GPR regression methods were observed to show consistent results with the training and testing datasets, with the SVM regression technique yielding higher R-squared values through regression across the different clustering techniques. In addition, cross-plots were employed to successfully delineate the Red River formation into distinct regions, aiding in the definition of formation lithology and the estimation of field water saturation. Our study showcases an integrated approach to predicting reservoir permeability, considering limited core data. ML emerges as an effective tool for characterizing the Red River formation as a geothermal hotspot in North Dakota, showcasing the potential for sustainable energy exploration and utilization which reduces the reliance on extensive coring in order to enhance geothermal exploration accuracy.
format Article
id doaj-art-1f8f525e41d24757b2385b6964a48121
institution Kabale University
issn 2195-9706
language English
publishDate 2025-01-01
publisher SpringerOpen
record_format Article
series Geothermal Energy
spelling doaj-art-1f8f525e41d24757b2385b6964a481212025-01-26T12:23:35ZengSpringerOpenGeothermal Energy2195-97062025-01-0113113310.1186/s40517-024-00323-4Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston BasinAbdul-Muaizz Koray0Emmanuel Gyimah1Mohamed Metwally2Hamid Rahnema3Olusegun Tomomewo4Department of Petroleum Engineering, New Mexico Institute of Mining and TechnologyCollege of Engineering and Mine Energy Studies, University of North DakotaDepartment of Petroleum Engineering, New Mexico Institute of Mining and TechnologyDepartment of Petroleum Engineering, New Mexico Institute of Mining and TechnologyCollege of Engineering and Mine Energy Studies, University of North DakotaAbstract Geothermal energy is a large, renewable, and clean source of energy from the earth in the form of heat. Exploring the deeper layers of the Williston Basin has revealed favorable reservoir temperatures, particularly in the western areas where high heat flows are prevalent. The quality of a geothermal hotspot hinges on the reservoir quality index (RQI), which is determined by the accuracy of calculating the field reservoir permeability. The primary goal of this study is to apply machine learning techniques to accurately calculate the field permeability, which is important for optimizing the RQI. To enhance accuracy, we initially applied various clustering algorithms, including the density-based spatial clustering of applications with noise (DBSCAN), K-means, K-median, and hierarchical clustering methods, to delineate hydraulic flow units (HFU) within the reservoir using porosity, permeability and water saturation core data. Subsequently, regression models including supervised ML regression methods such as neural networks, support vector machine (SVM) regression, Gaussian process regression (GPR), ensemble regression, linear regression, and decision trees were employed for each flow unit to establish correlations and calculate field permeability with each of these models validated using cross-validation. In comparison to the other clustering methods, the hierarchical clustering method showed the best performance by showing a strong correlation between the actual and predicted permeability values. Overall, the SVM and GPR regression methods were observed to show consistent results with the training and testing datasets, with the SVM regression technique yielding higher R-squared values through regression across the different clustering techniques. In addition, cross-plots were employed to successfully delineate the Red River formation into distinct regions, aiding in the definition of formation lithology and the estimation of field water saturation. Our study showcases an integrated approach to predicting reservoir permeability, considering limited core data. ML emerges as an effective tool for characterizing the Red River formation as a geothermal hotspot in North Dakota, showcasing the potential for sustainable energy exploration and utilization which reduces the reliance on extensive coring in order to enhance geothermal exploration accuracy.https://doi.org/10.1186/s40517-024-00323-4Geothermal energyReservoir characterizationMachine learningNeural networkRed River formationHeat flow
spellingShingle Abdul-Muaizz Koray
Emmanuel Gyimah
Mohamed Metwally
Hamid Rahnema
Olusegun Tomomewo
Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin
Geothermal Energy
Geothermal energy
Reservoir characterization
Machine learning
Neural network
Red River formation
Heat flow
title Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin
title_full Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin
title_fullStr Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin
title_full_unstemmed Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin
title_short Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin
title_sort leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots a case study of the williston basin
topic Geothermal energy
Reservoir characterization
Machine learning
Neural network
Red River formation
Heat flow
url https://doi.org/10.1186/s40517-024-00323-4
work_keys_str_mv AT abdulmuaizzkoray leveragingmachinelearningforenhancedreservoirpermeabilityestimationingeothermalhotspotsacasestudyofthewillistonbasin
AT emmanuelgyimah leveragingmachinelearningforenhancedreservoirpermeabilityestimationingeothermalhotspotsacasestudyofthewillistonbasin
AT mohamedmetwally leveragingmachinelearningforenhancedreservoirpermeabilityestimationingeothermalhotspotsacasestudyofthewillistonbasin
AT hamidrahnema leveragingmachinelearningforenhancedreservoirpermeabilityestimationingeothermalhotspotsacasestudyofthewillistonbasin
AT oluseguntomomewo leveragingmachinelearningforenhancedreservoirpermeabilityestimationingeothermalhotspotsacasestudyofthewillistonbasin