Prediction of permeability from well logs using a new hybrid machine learning algorithm
Permeability is a measure of fluid transmissibility in the rock and is a crucial concept in the evaluation of formations and the production of hydrocarbon from the reservoirs. Various techniques such as intelligent methods have been introduced to estimate the permeability from other petrophysical fe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-03-01
|
| Series: | Petroleum |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405656122000219 |
| _version_ | 1797857713045110784 |
|---|---|
| author | Morteza Matinkia Romina Hashami Mohammad Mehrad Mohammad Reza Hajsaeedi Arian Velayati |
| author_facet | Morteza Matinkia Romina Hashami Mohammad Mehrad Mohammad Reza Hajsaeedi Arian Velayati |
| author_sort | Morteza Matinkia |
| collection | DOAJ |
| description | Permeability is a measure of fluid transmissibility in the rock and is a crucial concept in the evaluation of formations and the production of hydrocarbon from the reservoirs. Various techniques such as intelligent methods have been introduced to estimate the permeability from other petrophysical features. The efficiency and convergence issues associated with artificial neural networks have motivated researchers to use hybrid techniques for the optimization of the networks, where the artificial neural network is combined with heuristic algorithms.This research combines social ski-driver (SSD) algorithm with the multilayer perception (MLP) neural network and presents a new hybrid algorithm to predict the value of rock permeability. The performance of this novel technique is compared with two previously used hybrid methods (genetic algorithm-MLP and particle swarm optimization-MLP) to examine the effectiveness of these hybrid methods in predicting the permeability of the rock.The results indicate that the hybrid models can predict rock permeability with excellent accuracy. MLP-SSD method yields the highest coefficient of determination (0.9928) among all other methods in predicting the permeability values of the test data set, followed by MLP-PSO and MLP-GA, respectively. However, the MLP-GA converged faster than the other two methods and is computationally less expensive. |
| first_indexed | 2024-04-09T21:01:14Z |
| format | Article |
| id | doaj.art-cf4ce6f703aa4c2286e45606ec1d89e7 |
| institution | Directory Open Access Journal |
| issn | 2405-6561 |
| language | English |
| last_indexed | 2024-04-09T21:01:14Z |
| publishDate | 2023-03-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Petroleum |
| spelling | doaj.art-cf4ce6f703aa4c2286e45606ec1d89e72023-03-29T09:27:43ZengKeAi Communications Co., Ltd.Petroleum2405-65612023-03-0191108123Prediction of permeability from well logs using a new hybrid machine learning algorithmMorteza Matinkia0Romina Hashami1Mohammad Mehrad2Mohammad Reza Hajsaeedi3Arian Velayati4Department of Petroleum Engineering, Omidiyeh Branch, Islamic Azad University, Omidiyeh, IranDepartment of Applied Mathematics, Faculty of Mathematics and Computer Sciences, Amirkabir University of Technology, Tehran, IranFaculty of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran; Corresponding author.Faculty of Mining, Petroleum and Geophysics Engineering, Shahrood University of Technology, Shahrood, IranDepartment of Chemical and Materials Engineering, University of Alberta, Edmonton, CanadaPermeability is a measure of fluid transmissibility in the rock and is a crucial concept in the evaluation of formations and the production of hydrocarbon from the reservoirs. Various techniques such as intelligent methods have been introduced to estimate the permeability from other petrophysical features. The efficiency and convergence issues associated with artificial neural networks have motivated researchers to use hybrid techniques for the optimization of the networks, where the artificial neural network is combined with heuristic algorithms.This research combines social ski-driver (SSD) algorithm with the multilayer perception (MLP) neural network and presents a new hybrid algorithm to predict the value of rock permeability. The performance of this novel technique is compared with two previously used hybrid methods (genetic algorithm-MLP and particle swarm optimization-MLP) to examine the effectiveness of these hybrid methods in predicting the permeability of the rock.The results indicate that the hybrid models can predict rock permeability with excellent accuracy. MLP-SSD method yields the highest coefficient of determination (0.9928) among all other methods in predicting the permeability values of the test data set, followed by MLP-PSO and MLP-GA, respectively. However, the MLP-GA converged faster than the other two methods and is computationally less expensive.http://www.sciencedirect.com/science/article/pii/S2405656122000219PermeabilityArtificial neural networkMultilayer perceptronSocial ski driver algorithm |
| spellingShingle | Morteza Matinkia Romina Hashami Mohammad Mehrad Mohammad Reza Hajsaeedi Arian Velayati Prediction of permeability from well logs using a new hybrid machine learning algorithm Petroleum Permeability Artificial neural network Multilayer perceptron Social ski driver algorithm |
| title | Prediction of permeability from well logs using a new hybrid machine learning algorithm |
| title_full | Prediction of permeability from well logs using a new hybrid machine learning algorithm |
| title_fullStr | Prediction of permeability from well logs using a new hybrid machine learning algorithm |
| title_full_unstemmed | Prediction of permeability from well logs using a new hybrid machine learning algorithm |
| title_short | Prediction of permeability from well logs using a new hybrid machine learning algorithm |
| title_sort | prediction of permeability from well logs using a new hybrid machine learning algorithm |
| topic | Permeability Artificial neural network Multilayer perceptron Social ski driver algorithm |
| url | http://www.sciencedirect.com/science/article/pii/S2405656122000219 |
| work_keys_str_mv | AT mortezamatinkia predictionofpermeabilityfromwelllogsusinganewhybridmachinelearningalgorithm AT rominahashami predictionofpermeabilityfromwelllogsusinganewhybridmachinelearningalgorithm AT mohammadmehrad predictionofpermeabilityfromwelllogsusinganewhybridmachinelearningalgorithm AT mohammadrezahajsaeedi predictionofpermeabilityfromwelllogsusinganewhybridmachinelearningalgorithm AT arianvelayati predictionofpermeabilityfromwelllogsusinganewhybridmachinelearningalgorithm |