Prediction of permeability from well logs using a new hybrid machine learning algorithm

作     者：Morteza Matinkia Romina Hashami Mohammad Mehrad Mohammad Reza Hajsaeedi Arian Velayati 

作者机构：Department of Petroleum EngineeringOmidiyeh BranchIslamic Azad UniversityOmidiyehIran Department of Applied MathematicsFaculty of Mathematics and Computer SciencesAmirkabir University of TechnologyTehranIran Faculty of MiningPetroleum and Geophysics EngineeringShahrood University of TechnologyShahroodIran Department of Chemical and Materials EngineeringUniversity of AlbertaEdmontonCanada 

出 版 物：《Petroleum》 (油气（英文）)

年 卷 期：2023年第9卷第1期

页      面：108-123页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Permeability Artificial neural network Multilayer perceptron Social ski driver algorithm 

摘      要：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 *** techniques such as intelligent methods have been introduced to estimate the permeability from other petrophysical *** 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 *** 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 *** 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 *** results indicate that the hybrid models can predict rock permeability with excellent ***-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,***,the MLP-GA converged faster than the other two methods and is computationally less expensive.