A hybrid stochastic-gradient optimization to estimating total organic carbon from petrophysical data: A case study from the Ahwaz oilfield, SW Iran

Created by W.Langdon from gp-bibliography.bib Revision:1.8010

@Article{Tabatabaei:2015:JPSE,

• author = "Seyed Mohammad Ehsan Tabatabaei and Ali Kadkhodaie-Ilkhchi and Ziba Hosseini and Asghar Asghari Moghaddam",
• title = "A hybrid stochastic-gradient optimization to estimating total organic carbon from petrophysical data: A case study from the {Ahwaz} oilfield, {SW Iran}",
• journal = "Journal of Petroleum Science and Engineering",
• year = "2015",
• volume = "127",
• pages = "35--43",
• month = mar,
• keywords = "genetic algorithms, genetic programming, total organic carbon (TOC), petrophysical logs, ACOR-BP, GA-BP, the Ahwaz oilfield",
• ISSN = "0920-4105",
• DOI = "doi:10.1016/j.petrol.2015.01.028",
• URL = "http://www.sciencedirect.com/science/article/pii/S0920410515000297",
• abstract = "One of the most important geochemical data in petroleum exploration is total organic carbon (TOC) which is used to evaluate the hydrocarbon generation potential of source rocks. To measure this parameter, expensive and time-consuming geochemical experiments are carried out on few cutting or core samples. In this study, stochastic optimisation algorithms (ant colony and genetic programming) were hybridised with gradient optimisation in a back propagation neural network structure to estimate TOC from petrophysical logs. The methodology is illustrated by using a case study from four wells of the Ahwaz oilfield. The results show that the hybrid ant colony-back propagation neural network model (ACOR-BP) provides better results compared to the other intelligent models used. MSE and R2 of the ACOR-BP model in testing samples are 0.0051 and 0.952, respectively. This level of accuracy along with the fast speed of the algorithm is highly desirable for the estimation of the TOC parameter. The findings of this research demonstrate that employing ant colony optimization to initialise weights and biases of neural networks minimises or avoids the risk of getting stuck in local minima. The methodology introduced in this study has a good performance and can be used to synthesise geochemical logs for the other wells of the Ahwaz oilfield.",

}

Genetic Programming entries for Seyed Mohammad Ehsan Tabatabaei Ali Kadkhodaie-Ilkhchi Ziba Hosseini Asghar Asghari Moghaddam

Citations