TY - JOUR ID - 56089 TI - Application of artificial neural networks for the prediction of carbonate lithofacies, based on well log data, Sarvak Formation, Marun oil field, SW Iran JO - Geopersia JA - GEOPE LA - en SN - 2228-7817 AU - Mohseni, Hassan AU - Esfandyari, Moosa AU - Habibi Asl, Elham AD - Department of Geology, Faculty of Science, Bu-Ali Sina University, Hamedan, Iran Y1 - 2015 PY - 2015 VL - 5 IS - 2 SP - 111 EP - 123 KW - Sarvak Formation KW - Artificial Neural Networks KW - Reservoir Characterization KW - Lithofacies KW - Zagros basin DO - 10.22059/jgeope.2015.56089 N2 - Lithofacies identification can provide qualitative information about rocks. It can also explain rock textures which are importantcomponents for hydrocarbon reservoir description Sarvak Formation is an important reservoir which is being studied in the Marun oilfield, in the Dezful embayment (Zagros basin). This study establishes quantitative relationships between digital well logs data androutine petrographic data, obtained from thin sections description. Attempts were made to predict lithofacies in 13 wells, all drilled inthe Marun oil field. Seven well logs, namely, Gamma Ray (SGR and CGR), Deep Resistivity (RD), Formation Density (RHOB),Neutron Porosity (PHIN), Sonic log (DT), and photoelectric factor (PEF) as input data and thin section/core-derived lithofacies wereused as target data in the ANN (artificial neural network) to predict lithofacies. The results show a strong correlation between the givendata and those obtained from ANN (R²= 95%). The performance of the model has been measured by the Mean Squared Error functionwhich doesn't exceed 0.303. Hence, neural network techniques are recommended for those reservoirs in which facies geometry anddistribution are key factors controlling the heterogeneity and distribution of rock properties. Undoubtedly, this approach can reduceuncertainty and save plenty of time and cost for the oil industry. UR - https://geopersia.ut.ac.ir/article_56089.html L1 - https://geopersia.ut.ac.ir/article_56089_1dfe9f3ecdbc56e9b1876321eae020d7.pdf ER -